Upload 49 files

.gitattributes

@@ -32,3 +32,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+mask.mp4 filter=lfs diff=lfs merge=lfs -text
+MobileNetSSD_deploy.caffemodel filter=lfs diff=lfs merge=lfs -text
+model[[:space:]]files/face[[:space:]]detection[[:space:]]model/res10_300x300_ssd_iter_140000.caffemodel filter=lfs diff=lfs merge=lfs -text
+res10_300x300_ssd_iter_140000.caffemodel filter=lfs diff=lfs merge=lfs -text
+test_video.mp4 filter=lfs diff=lfs merge=lfs -text
+video/testvideo2.mp4 filter=lfs diff=lfs merge=lfs -text

LoginStatus.csv

@@ -0,0 +1,7 @@
+Id,Password
+
+ffg,ffg
+anas,12345
+test,12345
+test,12345
+imran,12345

MobileNetSSD_deploy.caffemodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:761c86fbae3d8361dd454f7c740a964f62975ed32f4324b8b85994edec30f6af
+size 23147564

MobileNetSSD_deploy.prototxt

@@ -0,0 +1,1912 @@
+name: "MobileNet-SSD"
+input: "data"
+input_shape {
+  dim: 1
+  dim: 3
+  dim: 300
+  dim: 300
+}
+layer {
+  name: "conv0"
+  type: "Convolution"
+  bottom: "data"
+  top: "conv0"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 32
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv0/relu"
+  type: "ReLU"
+  bottom: "conv0"
+  top: "conv0"
+}
+layer {
+  name: "conv1/dw"
+  type: "Convolution"
+  bottom: "conv0"
+  top: "conv1/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 32
+    pad: 1
+    kernel_size: 3
+    group: 32
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv1/dw/relu"
+  type: "ReLU"
+  bottom: "conv1/dw"
+  top: "conv1/dw"
+}
+layer {
+  name: "conv1"
+  type: "Convolution"
+  bottom: "conv1/dw"
+  top: "conv1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 64
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv1/relu"
+  type: "ReLU"
+  bottom: "conv1"
+  top: "conv1"
+}
+layer {
+  name: "conv2/dw"
+  type: "Convolution"
+  bottom: "conv1"
+  top: "conv2/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 64
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    group: 64
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv2/dw/relu"
+  type: "ReLU"
+  bottom: "conv2/dw"
+  top: "conv2/dw"
+}
+layer {
+  name: "conv2"
+  type: "Convolution"
+  bottom: "conv2/dw"
+  top: "conv2"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 128
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv2/relu"
+  type: "ReLU"
+  bottom: "conv2"
+  top: "conv2"
+}
+layer {
+  name: "conv3/dw"
+  type: "Convolution"
+  bottom: "conv2"
+  top: "conv3/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 128
+    pad: 1
+    kernel_size: 3
+    group: 128
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv3/dw/relu"
+  type: "ReLU"
+  bottom: "conv3/dw"
+  top: "conv3/dw"
+}
+layer {
+  name: "conv3"
+  type: "Convolution"
+  bottom: "conv3/dw"
+  top: "conv3"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 128
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv3/relu"
+  type: "ReLU"
+  bottom: "conv3"
+  top: "conv3"
+}
+layer {
+  name: "conv4/dw"
+  type: "Convolution"
+  bottom: "conv3"
+  top: "conv4/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 128
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    group: 128
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv4/dw/relu"
+  type: "ReLU"
+  bottom: "conv4/dw"
+  top: "conv4/dw"
+}
+layer {
+  name: "conv4"
+  type: "Convolution"
+  bottom: "conv4/dw"
+  top: "conv4"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 256
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv4/relu"
+  type: "ReLU"
+  bottom: "conv4"
+  top: "conv4"
+}
+layer {
+  name: "conv5/dw"
+  type: "Convolution"
+  bottom: "conv4"
+  top: "conv5/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+    group: 256
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv5/dw/relu"
+  type: "ReLU"
+  bottom: "conv5/dw"
+  top: "conv5/dw"
+}
+layer {
+  name: "conv5"
+  type: "Convolution"
+  bottom: "conv5/dw"
+  top: "conv5"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 256
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv5/relu"
+  type: "ReLU"
+  bottom: "conv5"
+  top: "conv5"
+}
+layer {
+  name: "conv6/dw"
+  type: "Convolution"
+  bottom: "conv5"
+  top: "conv6/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    group: 256
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv6/dw/relu"
+  type: "ReLU"
+  bottom: "conv6/dw"
+  top: "conv6/dw"
+}
+layer {
+  name: "conv6"
+  type: "Convolution"
+  bottom: "conv6/dw"
+  top: "conv6"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv6/relu"
+  type: "ReLU"
+  bottom: "conv6"
+  top: "conv6"
+}
+layer {
+  name: "conv7/dw"
+  type: "Convolution"
+  bottom: "conv6"
+  top: "conv7/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+    group: 512
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv7/dw/relu"
+  type: "ReLU"
+  bottom: "conv7/dw"
+  top: "conv7/dw"
+}
+layer {
+  name: "conv7"
+  type: "Convolution"
+  bottom: "conv7/dw"
+  top: "conv7"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv7/relu"
+  type: "ReLU"
+  bottom: "conv7"
+  top: "conv7"
+}
+layer {
+  name: "conv8/dw"
+  type: "Convolution"
+  bottom: "conv7"
+  top: "conv8/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+    group: 512
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv8/dw/relu"
+  type: "ReLU"
+  bottom: "conv8/dw"
+  top: "conv8/dw"
+}
+layer {
+  name: "conv8"
+  type: "Convolution"
+  bottom: "conv8/dw"
+  top: "conv8"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv8/relu"
+  type: "ReLU"
+  bottom: "conv8"
+  top: "conv8"
+}
+layer {
+  name: "conv9/dw"
+  type: "Convolution"
+  bottom: "conv8"
+  top: "conv9/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+    group: 512
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv9/dw/relu"
+  type: "ReLU"
+  bottom: "conv9/dw"
+  top: "conv9/dw"
+}
+layer {
+  name: "conv9"
+  type: "Convolution"
+  bottom: "conv9/dw"
+  top: "conv9"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv9/relu"
+  type: "ReLU"
+  bottom: "conv9"
+  top: "conv9"
+}
+layer {
+  name: "conv10/dw"
+  type: "Convolution"
+  bottom: "conv9"
+  top: "conv10/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+    group: 512
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv10/dw/relu"
+  type: "ReLU"
+  bottom: "conv10/dw"
+  top: "conv10/dw"
+}
+layer {
+  name: "conv10"
+  type: "Convolution"
+  bottom: "conv10/dw"
+  top: "conv10"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv10/relu"
+  type: "ReLU"
+  bottom: "conv10"
+  top: "conv10"
+}
+layer {
+  name: "conv11/dw"
+  type: "Convolution"
+  bottom: "conv10"
+  top: "conv11/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+    group: 512
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv11/dw/relu"
+  type: "ReLU"
+  bottom: "conv11/dw"
+  top: "conv11/dw"
+}
+layer {
+  name: "conv11"
+  type: "Convolution"
+  bottom: "conv11/dw"
+  top: "conv11"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv11/relu"
+  type: "ReLU"
+  bottom: "conv11"
+  top: "conv11"
+}
+layer {
+  name: "conv12/dw"
+  type: "Convolution"
+  bottom: "conv11"
+  top: "conv12/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    group: 512
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv12/dw/relu"
+  type: "ReLU"
+  bottom: "conv12/dw"
+  top: "conv12/dw"
+}
+layer {
+  name: "conv12"
+  type: "Convolution"
+  bottom: "conv12/dw"
+  top: "conv12"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 1024
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv12/relu"
+  type: "ReLU"
+  bottom: "conv12"
+  top: "conv12"
+}
+layer {
+  name: "conv13/dw"
+  type: "Convolution"
+  bottom: "conv12"
+  top: "conv13/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 1024
+    pad: 1
+    kernel_size: 3
+    group: 1024
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv13/dw/relu"
+  type: "ReLU"
+  bottom: "conv13/dw"
+  top: "conv13/dw"
+}
+layer {
+  name: "conv13"
+  type: "Convolution"
+  bottom: "conv13/dw"
+  top: "conv13"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 1024
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv13/relu"
+  type: "ReLU"
+  bottom: "conv13"
+  top: "conv13"
+}
+layer {
+  name: "conv14_1"
+  type: "Convolution"
+  bottom: "conv13"
+  top: "conv14_1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 256
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv14_1/relu"
+  type: "ReLU"
+  bottom: "conv14_1"
+  top: "conv14_1"
+}
+layer {
+  name: "conv14_2"
+  type: "Convolution"
+  bottom: "conv14_1"
+  top: "conv14_2"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv14_2/relu"
+  type: "ReLU"
+  bottom: "conv14_2"
+  top: "conv14_2"
+}
+layer {
+  name: "conv15_1"
+  type: "Convolution"
+  bottom: "conv14_2"
+  top: "conv15_1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 128
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv15_1/relu"
+  type: "ReLU"
+  bottom: "conv15_1"
+  top: "conv15_1"
+}
+layer {
+  name: "conv15_2"
+  type: "Convolution"
+  bottom: "conv15_1"
+  top: "conv15_2"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv15_2/relu"
+  type: "ReLU"
+  bottom: "conv15_2"
+  top: "conv15_2"
+}
+layer {
+  name: "conv16_1"
+  type: "Convolution"
+  bottom: "conv15_2"
+  top: "conv16_1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 128
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv16_1/relu"
+  type: "ReLU"
+  bottom: "conv16_1"
+  top: "conv16_1"
+}
+layer {
+  name: "conv16_2"
+  type: "Convolution"
+  bottom: "conv16_1"
+  top: "conv16_2"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv16_2/relu"
+  type: "ReLU"
+  bottom: "conv16_2"
+  top: "conv16_2"
+}
+layer {
+  name: "conv17_1"
+  type: "Convolution"
+  bottom: "conv16_2"
+  top: "conv17_1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 64
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv17_1/relu"
+  type: "ReLU"
+  bottom: "conv17_1"
+  top: "conv17_1"
+}
+layer {
+  name: "conv17_2"
+  type: "Convolution"
+  bottom: "conv17_1"
+  top: "conv17_2"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 128
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv17_2/relu"
+  type: "ReLU"
+  bottom: "conv17_2"
+  top: "conv17_2"
+}
+layer {
+  name: "conv11_mbox_loc"
+  type: "Convolution"
+  bottom: "conv11"
+  top: "conv11_mbox_loc"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 12
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv11_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv11_mbox_loc"
+  top: "conv11_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv11_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv11_mbox_loc_perm"
+  top: "conv11_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv11_mbox_conf"
+  type: "Convolution"
+  bottom: "conv11"
+  top: "conv11_mbox_conf"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 63
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv11_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv11_mbox_conf"
+  top: "conv11_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv11_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv11_mbox_conf_perm"
+  top: "conv11_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv11_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv11"
+  bottom: "data"
+  top: "conv11_mbox_priorbox"
+  prior_box_param {
+    min_size: 60.0
+    aspect_ratio: 2.0
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv13_mbox_loc"
+  type: "Convolution"
+  bottom: "conv13"
+  top: "conv13_mbox_loc"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 24
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv13_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv13_mbox_loc"
+  top: "conv13_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv13_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv13_mbox_loc_perm"
+  top: "conv13_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv13_mbox_conf"
+  type: "Convolution"
+  bottom: "conv13"
+  top: "conv13_mbox_conf"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 126
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv13_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv13_mbox_conf"
+  top: "conv13_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv13_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv13_mbox_conf_perm"
+  top: "conv13_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv13_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv13"
+  bottom: "data"
+  top: "conv13_mbox_priorbox"
+  prior_box_param {
+    min_size: 105.0
+    max_size: 150.0
+    aspect_ratio: 2.0
+    aspect_ratio: 3.0
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv14_2_mbox_loc"
+  type: "Convolution"
+  bottom: "conv14_2"
+  top: "conv14_2_mbox_loc"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 24
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv14_2_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv14_2_mbox_loc"
+  top: "conv14_2_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv14_2_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv14_2_mbox_loc_perm"
+  top: "conv14_2_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv14_2_mbox_conf"
+  type: "Convolution"
+  bottom: "conv14_2"
+  top: "conv14_2_mbox_conf"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 126
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv14_2_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv14_2_mbox_conf"
+  top: "conv14_2_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv14_2_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv14_2_mbox_conf_perm"
+  top: "conv14_2_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv14_2_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv14_2"
+  bottom: "data"
+  top: "conv14_2_mbox_priorbox"
+  prior_box_param {
+    min_size: 150.0
+    max_size: 195.0
+    aspect_ratio: 2.0
+    aspect_ratio: 3.0
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv15_2_mbox_loc"
+  type: "Convolution"
+  bottom: "conv15_2"
+  top: "conv15_2_mbox_loc"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 24
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv15_2_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv15_2_mbox_loc"
+  top: "conv15_2_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv15_2_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv15_2_mbox_loc_perm"
+  top: "conv15_2_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv15_2_mbox_conf"
+  type: "Convolution"
+  bottom: "conv15_2"
+  top: "conv15_2_mbox_conf"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 126
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv15_2_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv15_2_mbox_conf"
+  top: "conv15_2_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv15_2_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv15_2_mbox_conf_perm"
+  top: "conv15_2_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv15_2_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv15_2"
+  bottom: "data"
+  top: "conv15_2_mbox_priorbox"
+  prior_box_param {
+    min_size: 195.0
+    max_size: 240.0
+    aspect_ratio: 2.0
+    aspect_ratio: 3.0
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv16_2_mbox_loc"
+  type: "Convolution"
+  bottom: "conv16_2"
+  top: "conv16_2_mbox_loc"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 24
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv16_2_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv16_2_mbox_loc"
+  top: "conv16_2_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv16_2_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv16_2_mbox_loc_perm"
+  top: "conv16_2_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv16_2_mbox_conf"
+  type: "Convolution"
+  bottom: "conv16_2"
+  top: "conv16_2_mbox_conf"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 126
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv16_2_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv16_2_mbox_conf"
+  top: "conv16_2_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv16_2_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv16_2_mbox_conf_perm"
+  top: "conv16_2_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv16_2_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv16_2"
+  bottom: "data"
+  top: "conv16_2_mbox_priorbox"
+  prior_box_param {
+    min_size: 240.0
+    max_size: 285.0
+    aspect_ratio: 2.0
+    aspect_ratio: 3.0
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv17_2_mbox_loc"
+  type: "Convolution"
+  bottom: "conv17_2"
+  top: "conv17_2_mbox_loc"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 24
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv17_2_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv17_2_mbox_loc"
+  top: "conv17_2_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv17_2_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv17_2_mbox_loc_perm"
+  top: "conv17_2_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv17_2_mbox_conf"
+  type: "Convolution"
+  bottom: "conv17_2"
+  top: "conv17_2_mbox_conf"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 126
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv17_2_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv17_2_mbox_conf"
+  top: "conv17_2_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv17_2_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv17_2_mbox_conf_perm"
+  top: "conv17_2_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv17_2_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv17_2"
+  bottom: "data"
+  top: "conv17_2_mbox_priorbox"
+  prior_box_param {
+    min_size: 285.0
+    max_size: 300.0
+    aspect_ratio: 2.0
+    aspect_ratio: 3.0
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    offset: 0.5
+  }
+}
+layer {
+  name: "mbox_loc"
+  type: "Concat"
+  bottom: "conv11_mbox_loc_flat"
+  bottom: "conv13_mbox_loc_flat"
+  bottom: "conv14_2_mbox_loc_flat"
+  bottom: "conv15_2_mbox_loc_flat"
+  bottom: "conv16_2_mbox_loc_flat"
+  bottom: "conv17_2_mbox_loc_flat"
+  top: "mbox_loc"
+  concat_param {
+    axis: 1
+  }
+}
+layer {
+  name: "mbox_conf"
+  type: "Concat"
+  bottom: "conv11_mbox_conf_flat"
+  bottom: "conv13_mbox_conf_flat"
+  bottom: "conv14_2_mbox_conf_flat"
+  bottom: "conv15_2_mbox_conf_flat"
+  bottom: "conv16_2_mbox_conf_flat"
+  bottom: "conv17_2_mbox_conf_flat"
+  top: "mbox_conf"
+  concat_param {
+    axis: 1
+  }
+}
+layer {
+  name: "mbox_priorbox"
+  type: "Concat"
+  bottom: "conv11_mbox_priorbox"
+  bottom: "conv13_mbox_priorbox"
+  bottom: "conv14_2_mbox_priorbox"
+  bottom: "conv15_2_mbox_priorbox"
+  bottom: "conv16_2_mbox_priorbox"
+  bottom: "conv17_2_mbox_priorbox"
+  top: "mbox_priorbox"
+  concat_param {
+    axis: 2
+  }
+}
+layer {
+  name: "mbox_conf_reshape"
+  type: "Reshape"
+  bottom: "mbox_conf"
+  top: "mbox_conf_reshape"
+  reshape_param {
+    shape {
+      dim: 0
+      dim: -1
+      dim: 21
+    }
+  }
+}
+layer {
+  name: "mbox_conf_softmax"
+  type: "Softmax"
+  bottom: "mbox_conf_reshape"
+  top: "mbox_conf_softmax"
+  softmax_param {
+    axis: 2
+  }
+}
+layer {
+  name: "mbox_conf_flatten"
+  type: "Flatten"
+  bottom: "mbox_conf_softmax"
+  top: "mbox_conf_flatten"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "detection_out"
+  type: "DetectionOutput"
+  bottom: "mbox_loc"
+  bottom: "mbox_conf_flatten"
+  bottom: "mbox_priorbox"
+  top: "detection_out"
+  include {
+    phase: TEST
+  }
+  detection_output_param {
+    num_classes: 21
+    share_location: true
+    background_label_id: 0
+    nms_param {
+      nms_threshold: 0.45
+      top_k: 100
+    }
+    code_type: CENTER_SIZE
+    keep_top_k: 100
+    confidence_threshold: 0.25
+  }
+}

README.md

@@ -1,12 +1,45 @@
----
-title: Cheating Detection FYP
-emoji: ⚡
-colorFrom: indigo
-colorTo: blue
-sdk: streamlit
-sdk_version: 1.15.2
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# AIComputerVision
+This project contains various computer vision and AI related python scripts
+
+Link to full playlist: https://www.youtube.com/watch?v=UM9oDhhAg88&list=PLWw98q-Xe7iH8UHARl8RGk8MRj1raY4Eh
+
+Below is brief description for each script:
+
+1. Cat Dog detection:
+This script can detect cats and dogs in a frame. You can replace cat or dog with any other object you want to detect.
+
+2. Centroidtracker:
+This script helps in tracking any object in a frame. We have used this in person_tracking.py script in order to track persons in the frame.
+
+3. Dwell Time Calculation:
+This script calculates the time a person has spent in a frame. It is a good example of calculating total time a person was present in frame.
+
+4. Face Detection:
+This script detects face in person image or in a frame
+
+5. FPS Example:
+While inferencing on a video file or frame from live usb webcam, its always a good idea to keep a check on how much fps we are getting. This script shows approx fps on frame.
+
+6. OpenCV Example:
+This script shows basic usage of opencv
+
+7. Person Detection in Image File:
+This script detects person in image file
+
+8. Person Detection in Video File:
+This script detects person in video file. Test video file is present in video dir.
+
+9. Person Tracking:
+This script detects person and keeps tracking them in the frame. It assigns a unique ID to each detected person.
+
+10. Monitor Social Distance
+This script monitors social distance between the persons. If it is less than a threshold value, we display bounding box in red otherwise green.
+
+11. Drawing tracking line:
+This script draws a line denoting where the person has entered in the frame and where he has moved in the frame. 
+
+12. Face Mask Detection: 
+This script checks if a person is wearing face mask or not
+
+13. Person Counter:
+This script counts the number of person present in the frame.

app.py

@@ -0,0 +1,24 @@
+import streamlit as st
+from PIL import Image
+st.set_page_config(
+	page_title = "Cheating Detection Application")
+
+st.title("Cheating Application Final Year Project")
+
+st.sidebar.success("Select a page above")
+
+
+st.image("logo.jpeg")
+
+st.write("""
+Imran Ahmed (GL)
+SE-093-2019
+
+Mir Taimoor Iqbal
+SE-075-2019
+
+Muhammad Ali Akbar
+SE-019-2018
+
+FABEHA QADIR
+SE-076-2019""")

cat_dog_detection.py

@@ -0,0 +1,43 @@
+import cv2
+import numpy as np
+import imutils
+
+protopath = "MobileNetSSD_deploy.prototxt"
+modelpath = "MobileNetSSD_deploy.caffemodel"
+detector = cv2.dnn.readNetFromCaffe(prototxt=protopath, caffeModel=modelpath)
+
+CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
+           "bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
+           "dog", "horse", "motorbike", "person", "pottedplant", "sheep",
+           "sofa", "train", "tvmonitor"]
+
+
+def main():
+    image = cv2.imread('dog.jpg')
+    image = imutils.resize(image, width=600)
+
+    (H, W) = image.shape[:2]
+
+    blob = cv2.dnn.blobFromImage(image, 0.007843, (W, H), 127.5)
+
+    detector.setInput(blob)
+    person_detections = detector.forward()
+
+    for i in np.arange(0, person_detections.shape[2]):
+        confidence = person_detections[0, 0, i, 2]
+        if confidence > 0.5:
+            idx = int(person_detections[0, 0, i, 1])
+
+            if CLASSES[idx] != "dog":
+                continue
+
+            person_box = person_detections[0, 0, i, 3:7] * np.array([W, H, W, H])
+            (startX, startY, endX, endY) = person_box.astype("int")
+
+            cv2.rectangle(image, (startX, startY), (endX, endY), (0, 0, 255), 2)
+
+    cv2.imshow("Results", image)
+    cv2.waitKey(0)
+    cv2.destroyAllWindows()
+
+main()

centroidtracker.py

@@ -0,0 +1,172 @@
+# import the necessary packages
+from scipy.spatial import distance as dist
+from collections import OrderedDict
+import numpy as np
+
+
+class CentroidTracker:
+    def __init__(self, maxDisappeared=50, maxDistance=50):
+        # initialize the next unique object ID along with two ordered
+        # dictionaries used to keep track of mapping a given object
+        # ID to its centroid and number of consecutive frames it has
+        # been marked as "disappeared", respectively
+        self.nextObjectID = 0
+        self.objects = OrderedDict()
+        self.disappeared = OrderedDict()
+        self.bbox = OrderedDict()  # CHANGE
+
+        # store the number of maximum consecutive frames a given
+        # object is allowed to be marked as "disappeared" until we
+        # need to deregister the object from tracking
+        self.maxDisappeared = maxDisappeared
+
+        # store the maximum distance between centroids to associate
+        # an object -- if the distance is larger than this maximum
+        # distance we'll start to mark the object as "disappeared"
+        self.maxDistance = maxDistance
+
+    def register(self, centroid, inputRect):
+        # when registering an object we use the next available object
+        # ID to store the centroid
+        self.objects[self.nextObjectID] = centroid
+        self.bbox[self.nextObjectID] = inputRect  # CHANGE
+        self.disappeared[self.nextObjectID] = 0
+        self.nextObjectID += 1
+
+    def deregister(self, objectID):
+        # to deregister an object ID we delete the object ID from
+        # both of our respective dictionaries
+        del self.objects[objectID]
+        del self.disappeared[objectID]
+        del self.bbox[objectID]  # CHANGE
+
+    def update(self, rects):
+        # check to see if the list of input bounding box rectangles
+        # is empty
+        if len(rects) == 0:
+            # loop over any existing tracked objects and mark them
+            # as disappeared
+            for objectID in list(self.disappeared.keys()):
+                self.disappeared[objectID] += 1
+
+                # if we have reached a maximum number of consecutive
+                # frames where a given object has been marked as
+                # missing, deregister it
+                if self.disappeared[objectID] > self.maxDisappeared:
+                    self.deregister(objectID)
+
+            # return early as there are no centroids or tracking info
+            # to update
+            # return self.objects
+            return self.bbox
+
+        # initialize an array of input centroids for the current frame
+        inputCentroids = np.zeros((len(rects), 2), dtype="int")
+        inputRects = []
+        # loop over the bounding box rectangles
+        for (i, (startX, startY, endX, endY)) in enumerate(rects):
+            # use the bounding box coordinates to derive the centroid
+            cX = int((startX + endX) / 2.0)
+            cY = int((startY + endY) / 2.0)
+            inputCentroids[i] = (cX, cY)
+            inputRects.append(rects[i])  # CHANGE
+
+        # if we are currently not tracking any objects take the input
+        # centroids and register each of them
+        if len(self.objects) == 0:
+            for i in range(0, len(inputCentroids)):
+                self.register(inputCentroids[i], inputRects[i])  # CHANGE
+
+        # otherwise, are are currently tracking objects so we need to
+        # try to match the input centroids to existing object
+        # centroids
+        else:
+            # grab the set of object IDs and corresponding centroids
+            objectIDs = list(self.objects.keys())
+            objectCentroids = list(self.objects.values())
+
+            # compute the distance between each pair of object
+            # centroids and input centroids, respectively -- our
+            # goal will be to match an input centroid to an existing
+            # object centroid
+            D = dist.cdist(np.array(objectCentroids), inputCentroids)
+
+            # in order to perform this matching we must (1) find the
+            # smallest value in each row and then (2) sort the row
+            # indexes based on their minimum values so that the row
+            # with the smallest value as at the *front* of the index
+            # list
+            rows = D.min(axis=1).argsort()
+
+            # next, we perform a similar process on the columns by
+            # finding the smallest value in each column and then
+            # sorting using the previously computed row index list
+            cols = D.argmin(axis=1)[rows]
+
+            # in order to determine if we need to update, register,
+            # or deregister an object we need to keep track of which
+            # of the rows and column indexes we have already examined
+            usedRows = set()
+            usedCols = set()
+
+            # loop over the combination of the (row, column) index
+            # tuples
+            for (row, col) in zip(rows, cols):
+                # if we have already examined either the row or
+                # column value before, ignore it
+                if row in usedRows or col in usedCols:
+                    continue
+
+                # if the distance between centroids is greater than
+                # the maximum distance, do not associate the two
+                # centroids to the same object
+                if D[row, col] > self.maxDistance:
+                    continue
+
+                # otherwise, grab the object ID for the current row,
+                # set its new centroid, and reset the disappeared
+                # counter
+                objectID = objectIDs[row]
+                self.objects[objectID] = inputCentroids[col]
+                self.bbox[objectID] = inputRects[col]  # CHANGE
+                self.disappeared[objectID] = 0
+
+                # indicate that we have examined each of the row and
+                # column indexes, respectively
+                usedRows.add(row)
+                usedCols.add(col)
+
+            # compute both the row and column index we have NOT yet
+            # examined
+            unusedRows = set(range(0, D.shape[0])).difference(usedRows)
+            unusedCols = set(range(0, D.shape[1])).difference(usedCols)
+
+            # in the event that the number of object centroids is
+            # equal or greater than the number of input centroids
+            # we need to check and see if some of these objects have
+            # potentially disappeared
+            if D.shape[0] >= D.shape[1]:
+                # loop over the unused row indexes
+                for row in unusedRows:
+                    # grab the object ID for the corresponding row
+                    # index and increment the disappeared counter
+                    objectID = objectIDs[row]
+                    self.disappeared[objectID] += 1
+
+                    # check to see if the number of consecutive
+                    # frames the object has been marked "disappeared"
+                    # for warrants deregistering the object
+                    if self.disappeared[objectID] > self.maxDisappeared:
+                        self.deregister(objectID)
+
+            # otherwise, if the number of input centroids is greater
+            # than the number of existing object centroids we need to
+            # register each new input centroid as a trackable object
+            else:
+                for col in unusedCols:
+                    self.register(inputCentroids[col], inputRects[col])
+
+        # return the set of trackable objects
+        # return self.objects
+        return self.bbox
+

deploy.prototxt

@@ -0,0 +1,1789 @@
+input: "data"
+input_shape {
+  dim: 1
+  dim: 3
+  dim: 300
+  dim: 300
+}
+
+layer {
+  name: "data_bn"
+  type: "BatchNorm"
+  bottom: "data"
+  top: "data_bn"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "data_scale"
+  type: "Scale"
+  bottom: "data_bn"
+  top: "data_bn"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "conv1_h"
+  type: "Convolution"
+  bottom: "data_bn"
+  top: "conv1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 32
+    pad: 3
+    kernel_size: 7
+    stride: 2
+    weight_filler {
+      type: "msra"
+      variance_norm: FAN_OUT
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv1_bn_h"
+  type: "BatchNorm"
+  bottom: "conv1_h"
+  top: "conv1_h"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "conv1_scale_h"
+  type: "Scale"
+  bottom: "conv1_h"
+  top: "conv1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "conv1_relu"
+  type: "ReLU"
+  bottom: "conv1_h"
+  top: "conv1_h"
+}
+layer {
+  name: "conv1_pool"
+  type: "Pooling"
+  bottom: "conv1_h"
+  top: "conv1_pool"
+  pooling_param {
+    kernel_size: 3
+    stride: 2
+  }
+}
+layer {
+  name: "layer_64_1_conv1_h"
+  type: "Convolution"
+  bottom: "conv1_pool"
+  top: "layer_64_1_conv1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 32
+    bias_term: false
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_64_1_bn2_h"
+  type: "BatchNorm"
+  bottom: "layer_64_1_conv1_h"
+  top: "layer_64_1_conv1_h"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "layer_64_1_scale2_h"
+  type: "Scale"
+  bottom: "layer_64_1_conv1_h"
+  top: "layer_64_1_conv1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "layer_64_1_relu2"
+  type: "ReLU"
+  bottom: "layer_64_1_conv1_h"
+  top: "layer_64_1_conv1_h"
+}
+layer {
+  name: "layer_64_1_conv2_h"
+  type: "Convolution"
+  bottom: "layer_64_1_conv1_h"
+  top: "layer_64_1_conv2_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 32
+    bias_term: false
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_64_1_sum"
+  type: "Eltwise"
+  bottom: "layer_64_1_conv2_h"
+  bottom: "conv1_pool"
+  top: "layer_64_1_sum"
+}
+layer {
+  name: "layer_128_1_bn1_h"
+  type: "BatchNorm"
+  bottom: "layer_64_1_sum"
+  top: "layer_128_1_bn1_h"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "layer_128_1_scale1_h"
+  type: "Scale"
+  bottom: "layer_128_1_bn1_h"
+  top: "layer_128_1_bn1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "layer_128_1_relu1"
+  type: "ReLU"
+  bottom: "layer_128_1_bn1_h"
+  top: "layer_128_1_bn1_h"
+}
+layer {
+  name: "layer_128_1_conv1_h"
+  type: "Convolution"
+  bottom: "layer_128_1_bn1_h"
+  top: "layer_128_1_conv1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 128
+    bias_term: false
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_128_1_bn2"
+  type: "BatchNorm"
+  bottom: "layer_128_1_conv1_h"
+  top: "layer_128_1_conv1_h"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "layer_128_1_scale2"
+  type: "Scale"
+  bottom: "layer_128_1_conv1_h"
+  top: "layer_128_1_conv1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "layer_128_1_relu2"
+  type: "ReLU"
+  bottom: "layer_128_1_conv1_h"
+  top: "layer_128_1_conv1_h"
+}
+layer {
+  name: "layer_128_1_conv2"
+  type: "Convolution"
+  bottom: "layer_128_1_conv1_h"
+  top: "layer_128_1_conv2"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 128
+    bias_term: false
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_128_1_conv_expand_h"
+  type: "Convolution"
+  bottom: "layer_128_1_bn1_h"
+  top: "layer_128_1_conv_expand_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 128
+    bias_term: false
+    pad: 0
+    kernel_size: 1
+    stride: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_128_1_sum"
+  type: "Eltwise"
+  bottom: "layer_128_1_conv2"
+  bottom: "layer_128_1_conv_expand_h"
+  top: "layer_128_1_sum"
+}
+layer {
+  name: "layer_256_1_bn1"
+  type: "BatchNorm"
+  bottom: "layer_128_1_sum"
+  top: "layer_256_1_bn1"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "layer_256_1_scale1"
+  type: "Scale"
+  bottom: "layer_256_1_bn1"
+  top: "layer_256_1_bn1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "layer_256_1_relu1"
+  type: "ReLU"
+  bottom: "layer_256_1_bn1"
+  top: "layer_256_1_bn1"
+}
+layer {
+  name: "layer_256_1_conv1"
+  type: "Convolution"
+  bottom: "layer_256_1_bn1"
+  top: "layer_256_1_conv1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 256
+    bias_term: false
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_256_1_bn2"
+  type: "BatchNorm"
+  bottom: "layer_256_1_conv1"
+  top: "layer_256_1_conv1"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "layer_256_1_scale2"
+  type: "Scale"
+  bottom: "layer_256_1_conv1"
+  top: "layer_256_1_conv1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "layer_256_1_relu2"
+  type: "ReLU"
+  bottom: "layer_256_1_conv1"
+  top: "layer_256_1_conv1"
+}
+layer {
+  name: "layer_256_1_conv2"
+  type: "Convolution"
+  bottom: "layer_256_1_conv1"
+  top: "layer_256_1_conv2"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 256
+    bias_term: false
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_256_1_conv_expand"
+  type: "Convolution"
+  bottom: "layer_256_1_bn1"
+  top: "layer_256_1_conv_expand"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 256
+    bias_term: false
+    pad: 0
+    kernel_size: 1
+    stride: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_256_1_sum"
+  type: "Eltwise"
+  bottom: "layer_256_1_conv2"
+  bottom: "layer_256_1_conv_expand"
+  top: "layer_256_1_sum"
+}
+layer {
+  name: "layer_512_1_bn1"
+  type: "BatchNorm"
+  bottom: "layer_256_1_sum"
+  top: "layer_512_1_bn1"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "layer_512_1_scale1"
+  type: "Scale"
+  bottom: "layer_512_1_bn1"
+  top: "layer_512_1_bn1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "layer_512_1_relu1"
+  type: "ReLU"
+  bottom: "layer_512_1_bn1"
+  top: "layer_512_1_bn1"
+}
+layer {
+  name: "layer_512_1_conv1_h"
+  type: "Convolution"
+  bottom: "layer_512_1_bn1"
+  top: "layer_512_1_conv1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 128
+    bias_term: false
+    pad: 1
+    kernel_size: 3
+    stride: 1 # 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_512_1_bn2_h"
+  type: "BatchNorm"
+  bottom: "layer_512_1_conv1_h"
+  top: "layer_512_1_conv1_h"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "layer_512_1_scale2_h"
+  type: "Scale"
+  bottom: "layer_512_1_conv1_h"
+  top: "layer_512_1_conv1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "layer_512_1_relu2"
+  type: "ReLU"
+  bottom: "layer_512_1_conv1_h"
+  top: "layer_512_1_conv1_h"
+}
+layer {
+  name: "layer_512_1_conv2_h"
+  type: "Convolution"
+  bottom: "layer_512_1_conv1_h"
+  top: "layer_512_1_conv2_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 256
+    bias_term: false
+    pad: 2 # 1
+    kernel_size: 3
+    stride: 1
+    dilation: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_512_1_conv_expand_h"
+  type: "Convolution"
+  bottom: "layer_512_1_bn1"
+  top: "layer_512_1_conv_expand_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 256
+    bias_term: false
+    pad: 0
+    kernel_size: 1
+    stride: 1 # 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_512_1_sum"
+  type: "Eltwise"
+  bottom: "layer_512_1_conv2_h"
+  bottom: "layer_512_1_conv_expand_h"
+  top: "layer_512_1_sum"
+}
+layer {
+  name: "last_bn_h"
+  type: "BatchNorm"
+  bottom: "layer_512_1_sum"
+  top: "layer_512_1_sum"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "last_scale_h"
+  type: "Scale"
+  bottom: "layer_512_1_sum"
+  top: "layer_512_1_sum"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "last_relu"
+  type: "ReLU"
+  bottom: "layer_512_1_sum"
+  top: "fc7"
+}
+
+layer {
+  name: "conv6_1_h"
+  type: "Convolution"
+  bottom: "fc7"
+  top: "conv6_1_h"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 128
+    pad: 0
+    kernel_size: 1
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv6_1_relu"
+  type: "ReLU"
+  bottom: "conv6_1_h"
+  top: "conv6_1_h"
+}
+layer {
+  name: "conv6_2_h"
+  type: "Convolution"
+  bottom: "conv6_1_h"
+  top: "conv6_2_h"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv6_2_relu"
+  type: "ReLU"
+  bottom: "conv6_2_h"
+  top: "conv6_2_h"
+}
+layer {
+  name: "conv7_1_h"
+  type: "Convolution"
+  bottom: "conv6_2_h"
+  top: "conv7_1_h"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 64
+    pad: 0
+    kernel_size: 1
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv7_1_relu"
+  type: "ReLU"
+  bottom: "conv7_1_h"
+  top: "conv7_1_h"
+}
+layer {
+  name: "conv7_2_h"
+  type: "Convolution"
+  bottom: "conv7_1_h"
+  top: "conv7_2_h"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 128
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv7_2_relu"
+  type: "ReLU"
+  bottom: "conv7_2_h"
+  top: "conv7_2_h"
+}
+layer {
+  name: "conv8_1_h"
+  type: "Convolution"
+  bottom: "conv7_2_h"
+  top: "conv8_1_h"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 64
+    pad: 0
+    kernel_size: 1
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv8_1_relu"
+  type: "ReLU"
+  bottom: "conv8_1_h"
+  top: "conv8_1_h"
+}
+layer {
+  name: "conv8_2_h"
+  type: "Convolution"
+  bottom: "conv8_1_h"
+  top: "conv8_2_h"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 128
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv8_2_relu"
+  type: "ReLU"
+  bottom: "conv8_2_h"
+  top: "conv8_2_h"
+}
+layer {
+  name: "conv9_1_h"
+  type: "Convolution"
+  bottom: "conv8_2_h"
+  top: "conv9_1_h"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 64
+    pad: 0
+    kernel_size: 1
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv9_1_relu"
+  type: "ReLU"
+  bottom: "conv9_1_h"
+  top: "conv9_1_h"
+}
+layer {
+  name: "conv9_2_h"
+  type: "Convolution"
+  bottom: "conv9_1_h"
+  top: "conv9_2_h"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 128
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv9_2_relu"
+  type: "ReLU"
+  bottom: "conv9_2_h"
+  top: "conv9_2_h"
+}
+layer {
+  name: "conv4_3_norm"
+  type: "Normalize"
+  bottom: "layer_256_1_bn1"
+  top: "conv4_3_norm"
+  norm_param {
+    across_spatial: false
+    scale_filler {
+      type: "constant"
+      value: 20
+    }
+    channel_shared: false
+  }
+}
+layer {
+  name: "conv4_3_norm_mbox_loc"
+  type: "Convolution"
+  bottom: "conv4_3_norm"
+  top: "conv4_3_norm_mbox_loc"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 16
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv4_3_norm_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv4_3_norm_mbox_loc"
+  top: "conv4_3_norm_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv4_3_norm_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv4_3_norm_mbox_loc_perm"
+  top: "conv4_3_norm_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv4_3_norm_mbox_conf"
+  type: "Convolution"
+  bottom: "conv4_3_norm"
+  top: "conv4_3_norm_mbox_conf"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 8 # 84
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv4_3_norm_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv4_3_norm_mbox_conf"
+  top: "conv4_3_norm_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv4_3_norm_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv4_3_norm_mbox_conf_perm"
+  top: "conv4_3_norm_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv4_3_norm_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv4_3_norm"
+  bottom: "data"
+  top: "conv4_3_norm_mbox_priorbox"
+  prior_box_param {
+    min_size: 30.0
+    max_size: 60.0
+    aspect_ratio: 2
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    step: 8
+    offset: 0.5
+  }
+}
+layer {
+  name: "fc7_mbox_loc"
+  type: "Convolution"
+  bottom: "fc7"
+  top: "fc7_mbox_loc"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 24
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "fc7_mbox_loc_perm"
+  type: "Permute"
+  bottom: "fc7_mbox_loc"
+  top: "fc7_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "fc7_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "fc7_mbox_loc_perm"
+  top: "fc7_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "fc7_mbox_conf"
+  type: "Convolution"
+  bottom: "fc7"
+  top: "fc7_mbox_conf"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 12 # 126
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "fc7_mbox_conf_perm"
+  type: "Permute"
+  bottom: "fc7_mbox_conf"
+  top: "fc7_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "fc7_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "fc7_mbox_conf_perm"
+  top: "fc7_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "fc7_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "fc7"
+  bottom: "data"
+  top: "fc7_mbox_priorbox"
+  prior_box_param {
+    min_size: 60.0
+    max_size: 111.0
+    aspect_ratio: 2
+    aspect_ratio: 3
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    step: 16
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv6_2_mbox_loc"
+  type: "Convolution"
+  bottom: "conv6_2_h"
+  top: "conv6_2_mbox_loc"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 24
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv6_2_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv6_2_mbox_loc"
+  top: "conv6_2_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv6_2_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv6_2_mbox_loc_perm"
+  top: "conv6_2_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv6_2_mbox_conf"
+  type: "Convolution"
+  bottom: "conv6_2_h"
+  top: "conv6_2_mbox_conf"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 12 # 126
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv6_2_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv6_2_mbox_conf"
+  top: "conv6_2_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv6_2_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv6_2_mbox_conf_perm"
+  top: "conv6_2_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv6_2_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv6_2_h"
+  bottom: "data"
+  top: "conv6_2_mbox_priorbox"
+  prior_box_param {
+    min_size: 111.0
+    max_size: 162.0
+    aspect_ratio: 2
+    aspect_ratio: 3
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    step: 32
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv7_2_mbox_loc"
+  type: "Convolution"
+  bottom: "conv7_2_h"
+  top: "conv7_2_mbox_loc"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 24
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv7_2_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv7_2_mbox_loc"
+  top: "conv7_2_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv7_2_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv7_2_mbox_loc_perm"
+  top: "conv7_2_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv7_2_mbox_conf"
+  type: "Convolution"
+  bottom: "conv7_2_h"
+  top: "conv7_2_mbox_conf"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 12 # 126
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv7_2_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv7_2_mbox_conf"
+  top: "conv7_2_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv7_2_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv7_2_mbox_conf_perm"
+  top: "conv7_2_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv7_2_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv7_2_h"
+  bottom: "data"
+  top: "conv7_2_mbox_priorbox"
+  prior_box_param {
+    min_size: 162.0
+    max_size: 213.0
+    aspect_ratio: 2
+    aspect_ratio: 3
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    step: 64
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv8_2_mbox_loc"
+  type: "Convolution"
+  bottom: "conv8_2_h"
+  top: "conv8_2_mbox_loc"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 16
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv8_2_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv8_2_mbox_loc"
+  top: "conv8_2_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv8_2_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv8_2_mbox_loc_perm"
+  top: "conv8_2_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv8_2_mbox_conf"
+  type: "Convolution"
+  bottom: "conv8_2_h"
+  top: "conv8_2_mbox_conf"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 8 # 84
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv8_2_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv8_2_mbox_conf"
+  top: "conv8_2_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv8_2_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv8_2_mbox_conf_perm"
+  top: "conv8_2_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv8_2_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv8_2_h"
+  bottom: "data"
+  top: "conv8_2_mbox_priorbox"
+  prior_box_param {
+    min_size: 213.0
+    max_size: 264.0
+    aspect_ratio: 2
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    step: 100
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv9_2_mbox_loc"
+  type: "Convolution"
+  bottom: "conv9_2_h"
+  top: "conv9_2_mbox_loc"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 16
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv9_2_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv9_2_mbox_loc"
+  top: "conv9_2_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv9_2_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv9_2_mbox_loc_perm"
+  top: "conv9_2_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv9_2_mbox_conf"
+  type: "Convolution"
+  bottom: "conv9_2_h"
+  top: "conv9_2_mbox_conf"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 8 # 84
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv9_2_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv9_2_mbox_conf"
+  top: "conv9_2_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv9_2_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv9_2_mbox_conf_perm"
+  top: "conv9_2_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv9_2_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv9_2_h"
+  bottom: "data"
+  top: "conv9_2_mbox_priorbox"
+  prior_box_param {
+    min_size: 264.0
+    max_size: 315.0
+    aspect_ratio: 2
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    step: 300
+    offset: 0.5
+  }
+}
+layer {
+  name: "mbox_loc"
+  type: "Concat"
+  bottom: "conv4_3_norm_mbox_loc_flat"
+  bottom: "fc7_mbox_loc_flat"
+  bottom: "conv6_2_mbox_loc_flat"
+  bottom: "conv7_2_mbox_loc_flat"
+  bottom: "conv8_2_mbox_loc_flat"
+  bottom: "conv9_2_mbox_loc_flat"
+  top: "mbox_loc"
+  concat_param {
+    axis: 1
+  }
+}
+layer {
+  name: "mbox_conf"
+  type: "Concat"
+  bottom: "conv4_3_norm_mbox_conf_flat"
+  bottom: "fc7_mbox_conf_flat"
+  bottom: "conv6_2_mbox_conf_flat"
+  bottom: "conv7_2_mbox_conf_flat"
+  bottom: "conv8_2_mbox_conf_flat"
+  bottom: "conv9_2_mbox_conf_flat"
+  top: "mbox_conf"
+  concat_param {
+    axis: 1
+  }
+}
+layer {
+  name: "mbox_priorbox"
+  type: "Concat"
+  bottom: "conv4_3_norm_mbox_priorbox"
+  bottom: "fc7_mbox_priorbox"
+  bottom: "conv6_2_mbox_priorbox"
+  bottom: "conv7_2_mbox_priorbox"
+  bottom: "conv8_2_mbox_priorbox"
+  bottom: "conv9_2_mbox_priorbox"
+  top: "mbox_priorbox"
+  concat_param {
+    axis: 2
+  }
+}
+
+layer {
+  name: "mbox_conf_reshape"
+  type: "Reshape"
+  bottom: "mbox_conf"
+  top: "mbox_conf_reshape"
+  reshape_param {
+    shape {
+      dim: 0
+      dim: -1
+      dim: 2
+    }
+  }
+}
+layer {
+  name: "mbox_conf_softmax"
+  type: "Softmax"
+  bottom: "mbox_conf_reshape"
+  top: "mbox_conf_softmax"
+  softmax_param {
+    axis: 2
+  }
+}
+layer {
+  name: "mbox_conf_flatten"
+  type: "Flatten"
+  bottom: "mbox_conf_softmax"
+  top: "mbox_conf_flatten"
+  flatten_param {
+    axis: 1
+  }
+}
+
+layer {
+  name: "detection_out"
+  type: "DetectionOutput"
+  bottom: "mbox_loc"
+  bottom: "mbox_conf_flatten"
+  bottom: "mbox_priorbox"
+  top: "detection_out"
+  include {
+    phase: TEST
+  }
+  detection_output_param {
+    num_classes: 2
+    share_location: true
+    background_label_id: 0
+    nms_param {
+      nms_threshold: 0.45
+      top_k: 400
+    }
+    code_type: CENTER_SIZE
+    keep_top_k: 200
+    confidence_threshold: 0.01
+  }
+}

draw_tracking_line.py

@@ -0,0 +1,152 @@
+import cv2
+import datetime
+import imutils
+import numpy as np
+from centroidtracker import CentroidTracker
+from collections import defaultdict
+
+protopath = "MobileNetSSD_deploy.prototxt"
+modelpath = "MobileNetSSD_deploy.caffemodel"
+detector = cv2.dnn.readNetFromCaffe(prototxt=protopath, caffeModel=modelpath)
+
+# Only enable it if you are using OpenVino environment
+# detector.setPreferableBackend(cv2.dnn.DNN_BACKEND_INFERENCE_ENGINE)
+# detector.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU)
+
+
+CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
+           "bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
+           "dog", "horse", "motorbike", "person", "pottedplant", "sheep",
+           "sofa", "train", "tvmonitor"]
+
+tracker = CentroidTracker(maxDisappeared=80, maxDistance=90)
+
+
+def non_max_suppression_fast(boxes, overlapThresh):
+    try:
+        if len(boxes) == 0:
+            return []
+
+        if boxes.dtype.kind == "i":
+            boxes = boxes.astype("float")
+
+        pick = []
+
+        x1 = boxes[:, 0]
+        y1 = boxes[:, 1]
+        x2 = boxes[:, 2]
+        y2 = boxes[:, 3]
+
+        area = (x2 - x1 + 1) * (y2 - y1 + 1)
+        idxs = np.argsort(y2)
+
+        while len(idxs) > 0:
+            last = len(idxs) - 1
+            i = idxs[last]
+            pick.append(i)
+
+            xx1 = np.maximum(x1[i], x1[idxs[:last]])
+            yy1 = np.maximum(y1[i], y1[idxs[:last]])
+            xx2 = np.minimum(x2[i], x2[idxs[:last]])
+            yy2 = np.minimum(y2[i], y2[idxs[:last]])
+
+            w = np.maximum(0, xx2 - xx1 + 1)
+            h = np.maximum(0, yy2 - yy1 + 1)
+
+            overlap = (w * h) / area[idxs[:last]]
+
+            idxs = np.delete(idxs, np.concatenate(([last],
+                                                   np.where(overlap > overlapThresh)[0])))
+
+        return boxes[pick].astype("int")
+    except Exception as e:
+        print("Exception occurred in non_max_suppression : {}".format(e))
+
+
+def main():
+    cap = cv2.VideoCapture('test_video.mp4')
+
+    fps_start_time = datetime.datetime.now()
+    fps = 0
+    total_frames = 0
+    centroid_dict = defaultdict(list)
+    object_id_list = []
+
+    while True:
+        ret, frame = cap.read()
+        frame = imutils.resize(frame, width=600)
+        total_frames = total_frames + 1
+
+        (H, W) = frame.shape[:2]
+
+        blob = cv2.dnn.blobFromImage(frame, 0.007843, (W, H), 127.5)
+
+        detector.setInput(blob)
+        person_detections = detector.forward()
+        rects = []
+        for i in np.arange(0, person_detections.shape[2]):
+            confidence = person_detections[0, 0, i, 2]
+            if confidence > 0.5:
+                idx = int(person_detections[0, 0, i, 1])
+
+                if CLASSES[idx] != "person":
+                    continue
+
+                person_box = person_detections[0, 0, i, 3:7] * np.array([W, H, W, H])
+                (startX, startY, endX, endY) = person_box.astype("int")
+                rects.append(person_box)
+
+        boundingboxes = np.array(rects)
+        boundingboxes = boundingboxes.astype(int)
+        rects = non_max_suppression_fast(boundingboxes, 0.3)
+
+        objects = tracker.update(rects)
+        for (objectId, bbox) in objects.items():
+            x1, y1, x2, y2 = bbox
+            x1 = int(x1)
+            y1 = int(y1)
+            x2 = int(x2)
+            y2 = int(y2)
+
+            cX = int((x1 + x2) / 2.0)
+            cY = int((y1 + y2) / 2.0)
+            cv2.circle(frame, (cX, cY), 4, (0, 255, 0), -1)
+
+            centroid_dict[objectId].append((cX, cY))
+            if objectId not in object_id_list:
+                object_id_list.append(objectId)
+                start_pt = (cX, cY)
+                end_pt = (cX, cY)
+                cv2.line(frame, start_pt, end_pt, (0, 255, 0), 2)
+            else:
+                l = len(centroid_dict[objectId])
+                for pt in range(len(centroid_dict[objectId])):
+                    if not pt + 1 == l:
+                        start_pt = (centroid_dict[objectId][pt][0], centroid_dict[objectId][pt][1])
+                        end_pt = (centroid_dict[objectId][pt + 1][0], centroid_dict[objectId][pt + 1][1])
+                        cv2.line(frame, start_pt, end_pt, (0, 255, 0), 2)
+                        
+            cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 0, 255), 2)
+            text = "ID: {}".format(objectId)
+            cv2.putText(frame, text, (x1, y1-5), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 255), 1)
+
+        fps_end_time = datetime.datetime.now()
+        time_diff = fps_end_time - fps_start_time
+        if time_diff.seconds == 0:
+            fps = 0.0
+        else:
+            fps = (total_frames / time_diff.seconds)
+
+        fps_text = "FPS: {:.2f}".format(fps)
+
+        cv2.putText(frame, fps_text, (5, 30), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 255), 1)
+
+        cv2.imshow("Application", frame)
+        key = cv2.waitKey(1)
+        if key == ord('q'):
+            break
+
+    cv2.destroyAllWindows()
+
+
+main()

dwell_time_calculation.py

@@ -0,0 +1,147 @@
+import cv2
+import datetime
+import imutils
+import numpy as np
+from centroidtracker import CentroidTracker
+
+protopath = "MobileNetSSD_deploy.prototxt"
+modelpath = "MobileNetSSD_deploy.caffemodel"
+detector = cv2.dnn.readNetFromCaffe(prototxt=protopath, caffeModel=modelpath)
+# Only enable it if you are using OpenVino environment
+# detector.setPreferableBackend(cv2.dnn.DNN_BACKEND_INFERENCE_ENGINE)
+# detector.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU)
+
+
+CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
+           "bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
+           "dog", "horse", "motorbike", "person", "pottedplant", "sheep",
+           "sofa", "train", "tvmonitor"]
+
+tracker = CentroidTracker(maxDisappeared=80, maxDistance=90)
+
+
+def non_max_suppression_fast(boxes, overlapThresh):
+    try:
+        if len(boxes) == 0:
+            return []
+
+        if boxes.dtype.kind == "i":
+            boxes = boxes.astype("float")
+
+        pick = []
+
+        x1 = boxes[:, 0]
+        y1 = boxes[:, 1]
+        x2 = boxes[:, 2]
+        y2 = boxes[:, 3]
+
+        area = (x2 - x1 + 1) * (y2 - y1 + 1)
+        idxs = np.argsort(y2)
+
+        while len(idxs) > 0:
+            last = len(idxs) - 1
+            i = idxs[last]
+            pick.append(i)
+
+            xx1 = np.maximum(x1[i], x1[idxs[:last]])
+            yy1 = np.maximum(y1[i], y1[idxs[:last]])
+            xx2 = np.minimum(x2[i], x2[idxs[:last]])
+            yy2 = np.minimum(y2[i], y2[idxs[:last]])
+
+            w = np.maximum(0, xx2 - xx1 + 1)
+            h = np.maximum(0, yy2 - yy1 + 1)
+
+            overlap = (w * h) / area[idxs[:last]]
+
+            idxs = np.delete(idxs, np.concatenate(([last],
+                                                   np.where(overlap > overlapThresh)[0])))
+
+        return boxes[pick].astype("int")
+    except Exception as e:
+        print("Exception occurred in non_max_suppression : {}".format(e))
+
+
+def main():
+    cap = cv2.VideoCapture('test_video.mp4')
+
+    fps_start_time = datetime.datetime.now()
+    fps = 0
+    total_frames = 0
+
+    object_id_list = []
+    dtime = dict()
+    dwell_time = dict()
+
+    while True:
+        ret, frame = cap.read()
+        frame = imutils.resize(frame, width=600)
+        total_frames = total_frames + 1
+
+        (H, W) = frame.shape[:2]
+
+        blob = cv2.dnn.blobFromImage(frame, 0.007843, (W, H), 127.5)
+
+        detector.setInput(blob)
+        person_detections = detector.forward()
+        rects = []
+        for i in np.arange(0, person_detections.shape[2]):
+            confidence = person_detections[0, 0, i, 2]
+            if confidence > 0.5:
+                idx = int(person_detections[0, 0, i, 1])
+
+                if CLASSES[idx] != "person":
+                    continue
+
+                person_box = person_detections[0, 0, i, 3:7] * np.array([W, H, W, H])
+                (startX, startY, endX, endY) = person_box.astype("int")
+                rects.append(person_box)
+
+        boundingboxes = np.array(rects)
+        boundingboxes = boundingboxes.astype(int)
+        rects = non_max_suppression_fast(boundingboxes, 0.3)
+
+        objects = tracker.update(rects)
+        for (objectId, bbox) in objects.items():
+            x1, y1, x2, y2 = bbox
+            x1 = int(x1)
+            y1 = int(y1)
+            x2 = int(x2)
+            y2 = int(y2)
+
+            if objectId not in object_id_list:
+                object_id_list.append(objectId)
+                dtime[objectId] = datetime.datetime.now()
+                dwell_time[objectId] = 0
+            else:
+                curr_time = datetime.datetime.now()
+                old_time = dtime[objectId]
+                time_diff = curr_time - old_time
+                dtime[objectId] = datetime.datetime.now()
+                sec = time_diff.total_seconds()
+                dwell_time[objectId] += sec
+
+
+            cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 0, 255), 2)
+            text = "{}|{}".format(objectId, int(dwell_time[objectId]))
+            cv2.putText(frame, text, (x1, y1-5), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 255), 1)
+
+        fps_end_time = datetime.datetime.now()
+        time_diff = fps_end_time - fps_start_time
+        if time_diff.seconds == 0:
+            fps = 0.0
+        else:
+            fps = (total_frames / time_diff.seconds)
+
+        fps_text = "FPS: {:.2f}".format(fps)
+
+        cv2.putText(frame, fps_text, (5, 30), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 255), 1)
+
+        cv2.imshow("Application", frame)
+        key = cv2.waitKey(1)
+        if key == ord('q'):
+            break
+
+    cv2.destroyAllWindows()
+
+
+main()

eg.py

@@ -0,0 +1,691 @@
+# import streamlit as st
+# import pandas as pd
+
+
+# # Security
+# #passlib,hashlib,bcrypt,scrypt
+# import hashlib
+# def make_hashes(password):
+# 	return hashlib.sha256(str.encode(password)).hexdigest()
+
+# def check_hashes(password,hashed_text):
+# 	if make_hashes(password) == hashed_text:
+# 		return hashed_text
+# 	return False
+# # DB Management
+# import sqlite3 
+# conn = sqlite3.connect('data.db')
+# c = conn.cursor()
+# # DB  Functions
+# def create_usertable():
+# 	c.execute('CREATE TABLE IF NOT EXISTS userstable(username TEXT,password TEXT)')
+
+
+# def add_userdata(username,password):
+# 	c.execute('INSERT INTO userstable(username,password) VALUES (?,?)',(username,password))
+# 	conn.commit()
+
+# def login_user(username,password):
+# 	c.execute('SELECT * FROM userstable WHERE username =? AND password = ?',(username,password))
+# 	data = c.fetchall()
+# 	return data
+
+
+# def view_all_users():
+# 	c.execute('SELECT * FROM userstable')
+# 	data = c.fetchall()
+# 	return data
+
+
+
+# def main():
+# 	"""Simple Login App"""
+
+# 	st.title("Simple Login App")
+
+# 	menu = ["Home","Login","SignUp"]
+# 	choice = st.sidebar.selectbox("Menu",menu)
+
+# 	if choice == "Home":
+# 		st.subheader("Home")
+
+# 	elif choice == "Login":
+# 		st.subheader("Login Section")
+
+# 		username = st.sidebar.text_input("User Name")
+# 		password = st.sidebar.text_input("Password",type='password')
+# 		if st.sidebar.checkbox("Login"):
+# 			# if password == '12345':
+# 			create_usertable()
+# 			hashed_pswd = make_hashes(password)
+
+# 			result = login_user(username,check_hashes(password,hashed_pswd))
+# 			if result:
+
+# 				st.success("Logged In as {}".format(username))
+
+# 				task = st.selectbox("Task",["Add Post","Analytics","Profiles"])
+# 				if task == "Add Post":
+# 					st.subheader("Add Your Post")
+
+# 				elif task == "Analytics":
+# 					st.subheader("Analytics")
+# 				elif task == "Profiles":
+# 					st.subheader("User Profiles")
+# 					user_result = view_all_users()
+# 					clean_db = pd.DataFrame(user_result,columns=["Username","Password"])
+# 					st.dataframe(clean_db)
+# 			else:
+# 				st.warning("Incorrect Username/Password")
+
+
+
+
+
+# 	elif choice == "SignUp":
+# 		st.subheader("Create New Account")
+# 		new_user = st.text_input("Username")
+# 		new_password = st.text_input("Password",type='password')
+
+# 		if st.button("Signup"):
+# 			create_usertable()
+# 			add_userdata(new_user,make_hashes(new_password))
+# 			st.success("You have successfully created a valid Account")
+# 			st.info("Go to Login Menu to login")
+
+
+
+# if __name__ == '__main__':
+# 	main()
+
+
+import cv2
+import datetime
+import imutils
+import numpy as np
+from centroidtracker import CentroidTracker
+import pandas as pd 
+import torch 
+import streamlit as st
+import mediapipe as mp
+import cv2 as cv
+import numpy as np
+import tempfile
+import time
+from PIL import Image
+import pandas as pd
+import torch
+import base64
+import streamlit.components.v1 as components
+import csv
+import pickle
+from pathlib import Path
+import streamlit_authenticator as stauth
+import os
+import csv
+#  x-x-x-x-x-x-x-x-x-x-x-x-x-x LOGIN FORM x-x-x-x-x-x-x-x-x
+
+                                
+data = ["student Count",'Date','Id','Mobile','Watch']
+with open('final.csv', 'w') as file:
+    writer = csv.writer(file)
+    writer.writerow(data)
+import streamlit as st
+import pandas as pd
+import hashlib
+import sqlite3 
+# if st.button("Open CRM !!"):
+    
+#     # Security
+#     #passlib,hashlib,bcrypt,scrypt
+#     def make_hashes(password):
+#         return hashlib.sha256(str.encode(password)).hexdigest()
+
+#     def check_hashes(password,hashed_text):
+#         if make_hashes(password) == hashed_text:
+#             return hashed_text
+#         return False
+#     # DB Management
+    
+#     conn = sqlite3.connect('data.db')
+#     c = conn.cursor()
+#     # DB  Functions
+#     def create_usertable():
+#         c.execute('CREATE TABLE IF NOT EXISTS userstable(username TEXT,password TEXT)')
+
+
+#     def add_userdata(username,password):
+#         c.execute('INSERT INTO userstable(username,password) VALUES (?,?)',(username,password))
+#         conn.commit()
+
+#     def login_user(username,password):
+#         c.execute('SELECT * FROM userstable WHERE username =? AND password = ?',(username,password))
+#         data = c.fetchall()
+#         return data
+
+
+#     def view_all_users():
+#         c.execute('SELECT * FROM userstable')
+#         data = c.fetchall()
+#         return data
+
+
+
+#     def main():
+#         """Simple Login App"""
+
+#         st.title("Simple Login App")
+
+#         menu = ["Home","Login","SignUp"]
+#         choice = st.sidebar.selectbox("Menu",menu)
+
+#         if choice == "Home":
+#             st.subheader("Home")
+
+#         elif choice == "Login":
+#             st.subheader("Login Section")
+
+#             username = st.sidebar.text_input("User Name")
+#             password = st.sidebar.text_input("Password",type='password')
+#             if st.sidebar.checkbox("Login"):
+#                 # if password == '12345':
+#                 create_usertable()
+#                 hashed_pswd = make_hashes(password)
+
+#                 result = login_user(username,check_hashes(password,hashed_pswd))
+#                 if result:
+
+#                     st.success("Logged In as {}".format(username))
+
+#                     # task = st.selectbox("Task",["Add Post","Analytics","Profiles"])
+#                     # if task == "Add Post":
+#                     #     st.subheader("Add Your Post")
+
+#                     # elif task == "Analytics":
+#                     #     st.subheader("Analytics")
+#                     # elif task == "Profiles":
+#                     #     st.subheader("User Profiles")
+#                     #     user_result = view_all_users()
+#                     #     clean_db = pd.DataFrame(user_result,columns=["Username","Password"])
+#                     #     st.dataframe(clean_db)
+#                 else:
+#                     st.warning("Incorrect Username/Password")
+
+
+
+
+
+#         elif choice == "SignUp":
+#             st.subheader("Create New Account")
+#             new_user = st.text_input("Username")
+#             new_password = st.text_input("Password",type='password')
+
+#             if st.button("Signup"):
+#                 create_usertable()
+#                 add_userdata(new_user,make_hashes(new_password))
+#                 st.success("You have successfully created a valid Account")
+#                 st.info("Go to Login Menu to login")
+
+
+
+#     if __name__ == '__main__':
+#         main()
+
+
+
+date_time = time.strftime("%b %d %Y %-I:%M %p")
+date = date_time.split()
+dates = date[0:3]
+times = date[3:5]
+# x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-xAPPLICACTION -x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x
+
+def non_max_suppression_fast(boxes, overlapThresh):
+    try:
+        if len(boxes) == 0:
+            return []
+
+        if boxes.dtype.kind == "i":
+            boxes = boxes.astype("float")
+
+        pick = []
+
+        x1 = boxes[:, 0]
+        y1 = boxes[:, 1]
+        x2 = boxes[:, 2]
+        y2 = boxes[:, 3]
+
+        area = (x2 - x1 + 1) * (y2 - y1 + 1)
+        idxs = np.argsort(y2)
+
+        while len(idxs) > 0:
+            last = len(idxs) - 1
+            i = idxs[last]
+            pick.append(i)
+
+            xx1 = np.maximum(x1[i], x1[idxs[:last]])
+            yy1 = np.maximum(y1[i], y1[idxs[:last]])
+            xx2 = np.minimum(x2[i], x2[idxs[:last]])
+            yy2 = np.minimum(y2[i], y2[idxs[:last]])
+
+            w = np.maximum(0, xx2 - xx1 + 1)
+            h = np.maximum(0, yy2 - yy1 + 1)
+
+            overlap = (w * h) / area[idxs[:last]]
+
+            idxs = np.delete(idxs, np.concatenate(([last],
+                                                np.where(overlap > overlapThresh)[0])))
+
+        return boxes[pick].astype("int")
+    except Exception as e:
+        print("Exception occurred in non_max_suppression : {}".format(e))
+
+
+protopath = "MobileNetSSD_deploy.prototxt"
+modelpath = "MobileNetSSD_deploy.caffemodel"
+detector = cv2.dnn.readNetFromCaffe(prototxt=protopath, caffeModel=modelpath)
+# Only enable it if you are using OpenVino environment
+# detector.setPreferableBackend(cv2.dnn.DNN_BACKEND_INFERENCE_ENGINE)
+# detector.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU)
+
+
+CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
+        "bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
+        "dog", "horse", "motorbike", "person", "pottedplant", "sheep",
+        "sofa", "train", "tvmonitor"]
+
+tracker = CentroidTracker(maxDisappeared=80, maxDistance=90)
+
+st.markdown(
+    """
+    <style>
+    [data-testid="stSidebar"][aria-expanded="true"] > div:first-child{
+        width: 350px
+    }
+    [data-testid="stSidebar"][aria-expanded="false"] > div:first-child{
+        width: 350px
+        margin-left: -350px
+    }
+    </style>
+    """,
+    unsafe_allow_html=True,
+)
+hide_streamlit_style = """
+        <style>
+        #MainMenu {visibility: hidden;}
+        footer {visibility: hidden;}
+        </style>
+        """
+st.markdown(hide_streamlit_style, unsafe_allow_html=True)
+# Create Sidebar
+st.sidebar.title('FaceMesh Sidebar')
+st.sidebar.subheader('Parameter')
+
+# Define available pages in selection box
+app_mode = st.sidebar.selectbox(
+    'App Mode',
+    ['About','Application']
+)
+
+# Resize Images to fit Container
+@st.cache()
+# Get Image Dimensions
+def image_resize(image, width=None, height=None, inter=cv.INTER_AREA):
+    dim = None
+    (h,w) = image.shape[:2]
+
+    if width is None and height is None:
+        return image
+
+    if width is None:
+        r = width/float(w)
+        dim = (int(w*r),height)
+
+    else:
+        r = width/float(w)
+        dim = width, int(h*r)
+
+    # Resize image
+    resized = cv.resize(image,dim,interpolation=inter)
+
+    return resized
+        
+# About Page
+# authenticator.logout('Logout','sidebar')
+if app_mode == 'About':
+    st.title('About Product And Team')
+    st.markdown('''
+                Imran Bhai Project
+    ''')
+    st.markdown(
+        """
+        <style>
+        [data-testid="stSidebar"][aria-expanded="true"] > div:first-child{
+            width: 350px
+        }
+        [data-testid="stSidebar"][aria-expanded="false"] > div:first-child{
+            width: 350px
+            margin-left: -350px
+        }
+        </style>
+        """,
+        unsafe_allow_html=True,
+    )
+
+    
+
+
+elif app_mode == 'Application':
+    
+    st.set_option('deprecation.showfileUploaderEncoding', False)
+
+    use_webcam = st.button('Use Webcam')
+    # record = st.sidebar.checkbox("Record Video")
+
+    # if record:
+    #     st.checkbox('Recording', True)
+
+    # drawing_spec = mp.solutions.drawing_utils.DrawingSpec(thickness=2, circle_radius=1)
+
+    # st.sidebar.markdown('---')
+
+    # ## Add Sidebar and Window style
+    # st.markdown(
+    #     """
+    #     <style>
+    #     [data-testid="stSidebar"][aria-expanded="true"] > div:first-child{
+    #         width: 350px
+    #     }
+    #     [data-testid="stSidebar"][aria-expanded="false"] > div:first-child{
+    #         width: 350px
+    #         margin-left: -350px
+    #     }
+    #     </style>
+    #     """,
+    #     unsafe_allow_html=True,
+    # )
+
+    # max_faces = st.sidebar.number_input('Maximum Number of Faces', value=5, min_value=1)
+    # st.sidebar.markdown('---')
+    # detection_confidence = st.sidebar.slider('Min Detection Confidence', min_value=0.0,max_value=1.0,value=0.5)
+    # tracking_confidence = st.sidebar.slider('Min Tracking Confidence', min_value=0.0,max_value=1.0,value=0.5)
+    # st.sidebar.markdown('---')
+
+    ## Get Video
+    stframe = st.empty()
+    video_file_buffer = st.file_uploader("Upload a Video", type=['mp4', 'mov', 'avi', 'asf', 'm4v'])
+    temp_file = tempfile.NamedTemporaryFile(delete=False)
+
+    
+    if not video_file_buffer:
+        if use_webcam:
+            video = cv.VideoCapture(0)
+        else:
+            try:
+                video = cv.VideoCapture(1)
+                temp_file.name = video
+            except:
+                pass
+    else:
+        temp_file.write(video_file_buffer.read())
+        video = cv.VideoCapture(temp_file.name)
+
+    width = int(video.get(cv.CAP_PROP_FRAME_WIDTH))
+    height = int(video.get(cv.CAP_PROP_FRAME_HEIGHT))
+    fps_input = int(video.get(cv.CAP_PROP_FPS))
+
+    ## Recording
+    codec = cv.VideoWriter_fourcc('a','v','c','1')
+    out = cv.VideoWriter('output1.mp4', codec, fps_input, (width,height))
+
+    st.sidebar.text('Input Video')
+    # st.sidebar.video(temp_file.name)
+
+    fps = 0
+    i = 0
+
+    drawing_spec = mp.solutions.drawing_utils.DrawingSpec(thickness=2, circle_radius=1)
+
+    kpil, kpil2, kpil3,kpil4,kpil5, kpil6 = st.columns(6)
+
+    with kpil:
+        st.markdown('**Frame Rate**')
+        kpil_text = st.markdown('0')
+
+    with kpil2:
+        st.markdown('**detection ID**')
+        kpil2_text = st.markdown('0')
+
+    with kpil3:
+        st.markdown('**Mobile**')
+        kpil3_text = st.markdown('0')
+    with kpil4:
+        st.markdown('**Watch**')
+        kpil4_text = st.markdown('0')
+    with kpil5:
+        st.markdown('**Count**')
+        kpil5_text = st.markdown('0')
+    with kpil6:
+        st.markdown('**Img Res**')
+        kpil6_text = st.markdown('0')
+    
+
+
+    st.markdown('<hr/>', unsafe_allow_html=True)
+    # try:
+    def main():
+        db = {}
+        
+        # cap = cv2.VideoCapture('//home//anas//PersonTracking//WebUI//movement.mp4')
+        path='/usr/local/lib/python3.10/dist-packages/yolo0vs5/yolov5s-int8.tflite'
+        #count=0
+        custom = 'yolov5s'
+
+        model = torch.hub.load('/usr/local/lib/python3.10/dist-packages/yolovs5', custom, path,source='local',force_reload=True)
+
+        b=model.names[0] = 'person'
+        mobile = model.names[67] = 'cell phone'
+        watch = model.names[75] = 'clock'
+
+        fps_start_time = datetime.datetime.now()
+        fps = 0
+        size=416
+
+        count=0
+        counter=0
+
+
+        color=(0,0,255)
+
+        cy1=250
+        offset=6
+
+
+        pt1 = (120, 100)
+        pt2 = (980, 1150)
+        color = (0, 255, 0)
+
+        pt3 = (283, 103)
+        pt4 = (1500, 1150)
+        
+        cy2 = 500
+        color = (0, 255, 0)
+        total_frames = 0
+        prevTime = 0
+        cur_frame = 0
+        count=0
+        counter=0
+        fps_start_time = datetime.datetime.now()
+        fps = 0
+        total_frames = 0
+        lpc_count = 0
+        opc_count = 0
+        object_id_list = []
+        # success = True
+        if st.button("Detect"):
+            try:
+                while video.isOpened():
+                    
+                    ret, frame = video.read()
+                    frame = imutils.resize(frame, width=600)
+                    total_frames = total_frames + 1
+
+                    (H, W) = frame.shape[:2]
+
+                    blob = cv2.dnn.blobFromImage(frame, 0.007843, (W, H), 127.5)
+
+                    detector.setInput(blob)
+                    person_detections = detector.forward()
+                    rects = []
+                    for i in np.arange(0, person_detections.shape[2]):
+                        confidence = person_detections[0, 0, i, 2]
+                        if confidence > 0.5:
+                            idx = int(person_detections[0, 0, i, 1])
+
+                            if CLASSES[idx] != "person":
+                                continue
+
+                            person_box = person_detections[0, 0, i, 3:7] * np.array([W, H, W, H])
+                            (startX, startY, endX, endY) = person_box.astype("int")
+                            rects.append(person_box)
+
+                    boundingboxes = np.array(rects)
+                    boundingboxes = boundingboxes.astype(int)
+                    rects = non_max_suppression_fast(boundingboxes, 0.3)
+
+                    objects = tracker.update(rects)
+                    for (objectId, bbox) in objects.items():
+                        x1, y1, x2, y2 = bbox
+                        x1 = int(x1)
+                        y1 = int(y1)
+                        x2 = int(x2)
+                        y2 = int(y2)
+
+                        cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 0, 255), 2)
+                        text = "ID: {}".format(objectId)
+                        # print(text)
+                        cv2.putText(frame, text, (x1, y1-5), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 255), 1)
+                        if objectId not in object_id_list:
+                            object_id_list.append(objectId)
+                    fps_end_time = datetime.datetime.now()
+                    time_diff = fps_end_time - fps_start_time
+                    if time_diff.seconds == 0:
+                        fps = 0.0
+                    else:
+                        fps = (total_frames / time_diff.seconds)
+
+                    fps_text = "FPS: {:.2f}".format(fps)
+
+                    cv2.putText(frame, fps_text, (5, 30), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 255), 1)
+                    lpc_count = len(objects)
+                    opc_count = len(object_id_list)
+
+                    lpc_txt = "LPC: {}".format(lpc_count)
+                    opc_txt = "OPC: {}".format(opc_count)
+                    
+                    count += 1
+                    if count % 4 != 0:
+                        continue
+                    # frame=cv.resize(frame, (600,500))
+                    # cv2.line(frame, pt1, pt2,color,2)
+                    # cv2.line(frame, pt3, pt4,color,2)
+                    results = model(frame,size)
+                    components = results.pandas().xyxy[0]
+                    for index, row in results.pandas().xyxy[0].iterrows():
+                        x1 = int(row['xmin'])
+                        y1 = int(row['ymin'])
+                        x2 = int(row['xmax'])
+                        y2 = int(row['ymax'])
+                        confidence  = (row['confidence'])
+                        obj = (row['class'])
+
+                        
+                        # min':x1,'ymin':y1,'xmax':x2,'ymax':y2,'confidence':confidence,'Object':obj}
+                        # if lpc_txt is not None:
+                        # 	try:
+                        # 		db["student Count"] = [lpc_txt]
+                        # 	except:
+                        # 		db["student Count"] = ['N/A']
+                        if obj == 0:
+                            cv2.rectangle(frame,(x1,y1),(x2,y2),(0,0,255),2)
+                            rectx1,recty1 = ((x1+x2)/2,(y1+y2)/2)
+                            rectcenter = int(rectx1),int(recty1)
+                            cx = rectcenter[0]
+                            cy = rectcenter[1]
+                            cv2.circle(frame,(cx,cy),3,(0,255,0),-1)
+                            cv2.putText(frame,str(b), (x1,y1), cv2.FONT_HERSHEY_PLAIN,2,(255,255,255),2)
+                            
+                            db["student Count"] = [lpc_txt]
+                            db['Date'] = [date_time]
+                            db['id'] = ['N/A']
+                            db['Mobile']=['N/A']
+                            db['Watch'] = ['N/A']
+                            if cy<(cy1+offset) and cy>(cy1-offset):
+                                DB = []
+                                counter+=1
+                                DB.append(counter)
+
+                                ff = DB[-1]
+                                fx = str(ff)
+                                # cv2.line(frame, pt1, pt2,(0, 0, 255),2)
+                                # if cy<(cy2+offset) and cy>(cy2-offset):
+
+                                # cv2.line(frame, pt3, pt4,(0, 0, 255),2)
+                                font = cv2.FONT_HERSHEY_TRIPLEX
+                                cv2.putText(frame,fx,(50, 50),font, 1,(0, 0, 255),2,cv2.LINE_4)
+                                cv2.putText(frame,"Movement",(70, 70),font, 1,(0, 0, 255),2,cv2.LINE_4)
+                                kpil2_text.write(f"<h5 style='text-align: left; color:red;'>{text}</h5>", unsafe_allow_html=True)
+                                
+                                
+                                db['id'] = [text]
+                                
+                                    
+                                
+                        if obj == 67:
+                            cv2.rectangle(frame,(x1,y1),(x2,y2),(0,0,255),2)
+                            rectx1,recty1 = ((x1+x2)/2,(y1+y2)/2)
+                            rectcenter = int(rectx1),int(recty1)
+                            cx = rectcenter[0]
+                            cy = rectcenter[1]
+                            cv2.circle(frame,(cx,cy),3,(0,255,0),-1)
+                            cv2.putText(frame,str(mobile), (x1,y1), cv2.FONT_HERSHEY_PLAIN,2,(255,255,255),2)
+                            cv2.putText(frame,'Mobile',(50, 50),cv2.FONT_HERSHEY_PLAIN, 1,(0, 0, 255),2,cv2.LINE_4)
+                            kpil3_text.write(f"<h5 style='text-align: left; color:red;'>{mobile}{text}</h5>", unsafe_allow_html=True)
+                            
+                            db['Mobile']=mobile+' '+text
+                            
+                                
+                            
+                        if obj == 75:
+                            cv2.rectangle(frame,(x1,y1),(x2,y2),(0,0,255),2)
+                            rectx1,recty1 = ((x1+x2)/2,(y1+y2)/2)
+                            rectcenter = int(rectx1),int(recty1)
+                            cx = rectcenter[0]
+                            cy = rectcenter[1]
+                            cv2.circle(frame,(cx,cy),3,(0,255,0),-1)
+                            cv2.putText(frame,str(watch), (x1,y1), cv2.FONT_HERSHEY_PLAIN,2,(255,255,255),2)
+                            cv2.putText(frame,'Watch',(50, 50),cv2.FONT_HERSHEY_PLAIN, 1,(0, 0, 255),2,cv2.LINE_4)
+                            kpil6_text.write(f"<h5 style='text-align: left; color:red;'>{watch}</h5>", unsafe_allow_html=True)
+                            
+                            
+                            db['Watch']=watch
+                        
+                            
+                    
+                    kpil_text.write(f"<h5 style='text-align: left; color:red;'>{int(fps)}</h5>", unsafe_allow_html=True)
+                    kpil5_text.write(f"<h5 style='text-align: left; color:red;'>{lpc_txt}</h5>", unsafe_allow_html=True)
+                    kpil6_text.write(f"<h5 style='text-align: left; color:red;'>{width*height}</h5>",
+                                    unsafe_allow_html=True)
+                    
+    
+                    frame = cv.resize(frame,(0,0), fx=0.8, fy=0.8)
+                    frame = image_resize(image=frame, width=640)
+                    stframe.image(frame,channels='BGR', use_column_width=True)
+                    df = pd.DataFrame(db)
+                    df.to_csv('final.csv',mode='a',header=False,index=False)
+            except:
+                pass
+            with open('final.csv') as f:
+                st.download_button(label = 'Download Cheating Report',data=f,file_name='data.csv')
+                
+            os.remove("final.csv")
+    main()

face_detections.py

@@ -0,0 +1,60 @@
+import cv2
+import datetime
+import imutils
+import numpy as np
+
+protopath = "deploy.prototxt"
+modelpath = "res10_300x300_ssd_iter_140000.caffemodel"
+detector = cv2.dnn.readNetFromCaffe(prototxt=protopath, caffeModel=modelpath)
+# Only enable it if you are using OpenVino environment
+# detector.setPreferableBackend(cv2.dnn.DNN_BACKEND_INFERENCE_ENGINE)
+# detector.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU)
+
+def main():
+    cap = cv2.VideoCapture('test_video.mp4')
+
+    fps_start_time = datetime.datetime.now()
+    fps = 0
+    total_frames = 0
+
+    while True:
+        ret, frame = cap.read()
+        frame = imutils.resize(frame, width=600)
+        total_frames = total_frames + 1
+
+        (H, W) = frame.shape[:2]
+
+        face_blob = cv2.dnn.blobFromImage(cv2.resize(frame, (300, 300)), 1.0, (300, 300), (104.0, 177.0, 123.0), False, False)
+
+        detector.setInput(face_blob)
+        face_detections = detector.forward()
+
+        for i in np.arange(0, face_detections.shape[2]):
+            confidence = face_detections[0, 0, i, 2]
+            if confidence > 0.5:
+
+                face_box = face_detections[0, 0, i, 3:7] * np.array([W, H, W, H])
+                (startX, startY, endX, endY) = face_box.astype("int")
+
+                cv2.rectangle(frame, (startX, startY), (endX, endY), (0, 0, 255), 2)
+
+        fps_end_time = datetime.datetime.now()
+        time_diff = fps_end_time - fps_start_time
+        if time_diff.seconds == 0:
+            fps = 0.0
+        else:
+            fps = (total_frames / time_diff.seconds)
+
+        fps_text = "FPS: {:.2f}".format(fps)
+
+        cv2.putText(frame, fps_text, (5, 30), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 255), 1)
+
+        cv2.imshow("Application", frame)
+        key = cv2.waitKey(1)
+        if key == ord('q'):
+            break
+
+    cv2.destroyAllWindows()
+
+
+main()

face_mask_detector.py

@@ -0,0 +1,73 @@
+from tensorflow.keras.applications.mobilenet_v2 import preprocess_input
+from tensorflow.keras.preprocessing.image import img_to_array
+from tensorflow.keras.models import load_model
+from imutils.video import VideoStream
+import numpy as np
+import argparse
+import imutils
+import time
+import cv2
+import os
+import datetime
+
+proto_txt_path = 'deploy.prototxt'
+model_path = 'res10_300x300_ssd_iter_140000.caffemodel'
+face_detector = cv2.dnn.readNetFromCaffe(proto_txt_path, model_path)
+
+mask_detector = load_model('mask_detector.model')
+
+cap = cv2.VideoCapture('mask.mp4')
+
+while True:
+    ret, frame = cap.read()
+    frame = imutils.resize(frame, width=400)
+    (h, w) = frame.shape[:2]
+    blob = cv2.dnn.blobFromImage(frame, 1.0, (300, 300), (104, 177, 123))
+
+    face_detector.setInput(blob)
+    detections = face_detector.forward()
+
+    faces = []
+    bbox = []
+    results = []
+
+    for i in range(0, detections.shape[2]):
+        confidence = detections[0, 0, i, 2]
+
+        if confidence > 0.5:
+            box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
+            (startX, startY, endX, endY) = box.astype("int")
+
+            face = frame[startY:endY, startX:endX]
+            face = cv2.cvtColor(face, cv2.COLOR_BGR2RGB)
+            face = cv2.resize(face, (224, 224))
+            face = img_to_array(face)
+            face = preprocess_input(face)
+            face = np.expand_dims(face, axis=0)
+
+            faces.append(face)
+            bbox.append((startX, startY, endX, endY))
+
+    if len(faces) > 0:
+        results = mask_detector.predict(faces)
+
+    for (face_box, result) in zip(bbox, results):
+        (startX, startY, endX, endY) = face_box
+        (mask, withoutMask) = result
+
+        label = ""
+        if mask > withoutMask:
+            label = "Mask"
+            color = (0, 255, 0)
+        else:
+            label = "No Mask"
+            color = (0, 0, 255)
+
+        cv2.putText(frame, label, (startX, startY-10), cv2.FONT_HERSHEY_SIMPLEX, 0.45, color, 2)
+        cv2.rectangle(frame, (startX, startY), (endX, endY), color, 2)
+
+        cv2.imshow("Frame", frame)
+        key = cv2.waitKey(1) & 0xFF
+
+        if key == ord('q'):
+            break

fps_example.py

@@ -0,0 +1,37 @@
+import cv2
+import datetime
+import imutils
+
+
+def main():
+    cap = cv2.VideoCapture('test_video.mp4')
+
+    fps_start_time = datetime.datetime.now()
+    fps = 0
+    total_frames = 0
+
+    while True:
+        ret, frame = cap.read()
+        frame = imutils.resize(frame, width=800)
+        total_frames = total_frames + 1
+
+        fps_end_time = datetime.datetime.now()
+        time_diff = fps_end_time - fps_start_time
+        if time_diff.seconds == 0:
+            fps = 0.0
+        else:
+            fps = (total_frames / time_diff.seconds)
+
+        fps_text = "FPS: {:.2f}".format(fps)
+
+        cv2.putText(frame, fps_text, (5, 30), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 255), 1)
+
+        cv2.imshow("Application", frame)
+        key = cv2.waitKey(1)
+        if key == ord('q'):
+            break
+
+    cv2.destroyAllWindows()
+
+
+main()

generate_keys.py

@@ -0,0 +1,17 @@
+import pickle
+from pathlib import Path
+import streamlit_authenticator as stauth
+# print("Done !!!")
+
+names = ["dmin", "ser"]
+
+username =["admin", "user"]
+
+password =["admin123", "user123"] 
+
+hashed_passwords =stauth.Hasher(password).generate()
+
+file_path = Path(__file__).parent / "hashed_pw.pkl"
+
+with file_path.open("wb") as file:
+    pickle.dump(hashed_passwords, file)

mask.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dc1d0ed71d79c29eaa4b8503c829fcf7c840cab93756baabf97238f999432e6
+size 6143986

mask_detector.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a62288c0832df0fad0e97b881b5268d3deb40ec372611b7d81c913715799af00
+size 11483536

model files/face detection model/deploy.prototxt

@@ -0,0 +1,1789 @@
+input: "data"
+input_shape {
+  dim: 1
+  dim: 3
+  dim: 300
+  dim: 300
+}
+
+layer {
+  name: "data_bn"
+  type: "BatchNorm"
+  bottom: "data"
+  top: "data_bn"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "data_scale"
+  type: "Scale"
+  bottom: "data_bn"
+  top: "data_bn"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "conv1_h"
+  type: "Convolution"
+  bottom: "data_bn"
+  top: "conv1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 32
+    pad: 3
+    kernel_size: 7
+    stride: 2
+    weight_filler {
+      type: "msra"
+      variance_norm: FAN_OUT
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv1_bn_h"
+  type: "BatchNorm"
+  bottom: "conv1_h"
+  top: "conv1_h"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "conv1_scale_h"
+  type: "Scale"
+  bottom: "conv1_h"
+  top: "conv1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "conv1_relu"
+  type: "ReLU"
+  bottom: "conv1_h"
+  top: "conv1_h"
+}
+layer {
+  name: "conv1_pool"
+  type: "Pooling"
+  bottom: "conv1_h"
+  top: "conv1_pool"
+  pooling_param {
+    kernel_size: 3
+    stride: 2
+  }
+}
+layer {
+  name: "layer_64_1_conv1_h"
+  type: "Convolution"
+  bottom: "conv1_pool"
+  top: "layer_64_1_conv1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 32
+    bias_term: false
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_64_1_bn2_h"
+  type: "BatchNorm"
+  bottom: "layer_64_1_conv1_h"
+  top: "layer_64_1_conv1_h"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "layer_64_1_scale2_h"
+  type: "Scale"
+  bottom: "layer_64_1_conv1_h"
+  top: "layer_64_1_conv1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "layer_64_1_relu2"
+  type: "ReLU"
+  bottom: "layer_64_1_conv1_h"
+  top: "layer_64_1_conv1_h"
+}
+layer {
+  name: "layer_64_1_conv2_h"
+  type: "Convolution"
+  bottom: "layer_64_1_conv1_h"
+  top: "layer_64_1_conv2_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 32
+    bias_term: false
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_64_1_sum"
+  type: "Eltwise"
+  bottom: "layer_64_1_conv2_h"
+  bottom: "conv1_pool"
+  top: "layer_64_1_sum"
+}
+layer {
+  name: "layer_128_1_bn1_h"
+  type: "BatchNorm"
+  bottom: "layer_64_1_sum"
+  top: "layer_128_1_bn1_h"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "layer_128_1_scale1_h"
+  type: "Scale"
+  bottom: "layer_128_1_bn1_h"
+  top: "layer_128_1_bn1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "layer_128_1_relu1"
+  type: "ReLU"
+  bottom: "layer_128_1_bn1_h"
+  top: "layer_128_1_bn1_h"
+}
+layer {
+  name: "layer_128_1_conv1_h"
+  type: "Convolution"
+  bottom: "layer_128_1_bn1_h"
+  top: "layer_128_1_conv1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 128
+    bias_term: false
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_128_1_bn2"
+  type: "BatchNorm"
+  bottom: "layer_128_1_conv1_h"
+  top: "layer_128_1_conv1_h"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "layer_128_1_scale2"
+  type: "Scale"
+  bottom: "layer_128_1_conv1_h"
+  top: "layer_128_1_conv1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "layer_128_1_relu2"
+  type: "ReLU"
+  bottom: "layer_128_1_conv1_h"
+  top: "layer_128_1_conv1_h"
+}
+layer {
+  name: "layer_128_1_conv2"
+  type: "Convolution"
+  bottom: "layer_128_1_conv1_h"
+  top: "layer_128_1_conv2"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 128
+    bias_term: false
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_128_1_conv_expand_h"
+  type: "Convolution"
+  bottom: "layer_128_1_bn1_h"
+  top: "layer_128_1_conv_expand_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 128
+    bias_term: false
+    pad: 0
+    kernel_size: 1
+    stride: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_128_1_sum"
+  type: "Eltwise"
+  bottom: "layer_128_1_conv2"
+  bottom: "layer_128_1_conv_expand_h"
+  top: "layer_128_1_sum"
+}
+layer {
+  name: "layer_256_1_bn1"
+  type: "BatchNorm"
+  bottom: "layer_128_1_sum"
+  top: "layer_256_1_bn1"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "layer_256_1_scale1"
+  type: "Scale"
+  bottom: "layer_256_1_bn1"
+  top: "layer_256_1_bn1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "layer_256_1_relu1"
+  type: "ReLU"
+  bottom: "layer_256_1_bn1"
+  top: "layer_256_1_bn1"
+}
+layer {
+  name: "layer_256_1_conv1"
+  type: "Convolution"
+  bottom: "layer_256_1_bn1"
+  top: "layer_256_1_conv1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 256
+    bias_term: false
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_256_1_bn2"
+  type: "BatchNorm"
+  bottom: "layer_256_1_conv1"
+  top: "layer_256_1_conv1"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "layer_256_1_scale2"
+  type: "Scale"
+  bottom: "layer_256_1_conv1"
+  top: "layer_256_1_conv1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "layer_256_1_relu2"
+  type: "ReLU"
+  bottom: "layer_256_1_conv1"
+  top: "layer_256_1_conv1"
+}
+layer {
+  name: "layer_256_1_conv2"
+  type: "Convolution"
+  bottom: "layer_256_1_conv1"
+  top: "layer_256_1_conv2"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 256
+    bias_term: false
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_256_1_conv_expand"
+  type: "Convolution"
+  bottom: "layer_256_1_bn1"
+  top: "layer_256_1_conv_expand"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 256
+    bias_term: false
+    pad: 0
+    kernel_size: 1
+    stride: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_256_1_sum"
+  type: "Eltwise"
+  bottom: "layer_256_1_conv2"
+  bottom: "layer_256_1_conv_expand"
+  top: "layer_256_1_sum"
+}
+layer {
+  name: "layer_512_1_bn1"
+  type: "BatchNorm"
+  bottom: "layer_256_1_sum"
+  top: "layer_512_1_bn1"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "layer_512_1_scale1"
+  type: "Scale"
+  bottom: "layer_512_1_bn1"
+  top: "layer_512_1_bn1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "layer_512_1_relu1"
+  type: "ReLU"
+  bottom: "layer_512_1_bn1"
+  top: "layer_512_1_bn1"
+}
+layer {
+  name: "layer_512_1_conv1_h"
+  type: "Convolution"
+  bottom: "layer_512_1_bn1"
+  top: "layer_512_1_conv1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 128
+    bias_term: false
+    pad: 1
+    kernel_size: 3
+    stride: 1 # 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_512_1_bn2_h"
+  type: "BatchNorm"
+  bottom: "layer_512_1_conv1_h"
+  top: "layer_512_1_conv1_h"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "layer_512_1_scale2_h"
+  type: "Scale"
+  bottom: "layer_512_1_conv1_h"
+  top: "layer_512_1_conv1_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "layer_512_1_relu2"
+  type: "ReLU"
+  bottom: "layer_512_1_conv1_h"
+  top: "layer_512_1_conv1_h"
+}
+layer {
+  name: "layer_512_1_conv2_h"
+  type: "Convolution"
+  bottom: "layer_512_1_conv1_h"
+  top: "layer_512_1_conv2_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 256
+    bias_term: false
+    pad: 2 # 1
+    kernel_size: 3
+    stride: 1
+    dilation: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_512_1_conv_expand_h"
+  type: "Convolution"
+  bottom: "layer_512_1_bn1"
+  top: "layer_512_1_conv_expand_h"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  convolution_param {
+    num_output: 256
+    bias_term: false
+    pad: 0
+    kernel_size: 1
+    stride: 1 # 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "layer_512_1_sum"
+  type: "Eltwise"
+  bottom: "layer_512_1_conv2_h"
+  bottom: "layer_512_1_conv_expand_h"
+  top: "layer_512_1_sum"
+}
+layer {
+  name: "last_bn_h"
+  type: "BatchNorm"
+  bottom: "layer_512_1_sum"
+  top: "layer_512_1_sum"
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+  param {
+    lr_mult: 0.0
+  }
+}
+layer {
+  name: "last_scale_h"
+  type: "Scale"
+  bottom: "layer_512_1_sum"
+  top: "layer_512_1_sum"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 1.0
+  }
+  scale_param {
+    bias_term: true
+  }
+}
+layer {
+  name: "last_relu"
+  type: "ReLU"
+  bottom: "layer_512_1_sum"
+  top: "fc7"
+}
+
+layer {
+  name: "conv6_1_h"
+  type: "Convolution"
+  bottom: "fc7"
+  top: "conv6_1_h"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 128
+    pad: 0
+    kernel_size: 1
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv6_1_relu"
+  type: "ReLU"
+  bottom: "conv6_1_h"
+  top: "conv6_1_h"
+}
+layer {
+  name: "conv6_2_h"
+  type: "Convolution"
+  bottom: "conv6_1_h"
+  top: "conv6_2_h"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv6_2_relu"
+  type: "ReLU"
+  bottom: "conv6_2_h"
+  top: "conv6_2_h"
+}
+layer {
+  name: "conv7_1_h"
+  type: "Convolution"
+  bottom: "conv6_2_h"
+  top: "conv7_1_h"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 64
+    pad: 0
+    kernel_size: 1
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv7_1_relu"
+  type: "ReLU"
+  bottom: "conv7_1_h"
+  top: "conv7_1_h"
+}
+layer {
+  name: "conv7_2_h"
+  type: "Convolution"
+  bottom: "conv7_1_h"
+  top: "conv7_2_h"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 128
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv7_2_relu"
+  type: "ReLU"
+  bottom: "conv7_2_h"
+  top: "conv7_2_h"
+}
+layer {
+  name: "conv8_1_h"
+  type: "Convolution"
+  bottom: "conv7_2_h"
+  top: "conv8_1_h"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 64
+    pad: 0
+    kernel_size: 1
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv8_1_relu"
+  type: "ReLU"
+  bottom: "conv8_1_h"
+  top: "conv8_1_h"
+}
+layer {
+  name: "conv8_2_h"
+  type: "Convolution"
+  bottom: "conv8_1_h"
+  top: "conv8_2_h"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 128
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv8_2_relu"
+  type: "ReLU"
+  bottom: "conv8_2_h"
+  top: "conv8_2_h"
+}
+layer {
+  name: "conv9_1_h"
+  type: "Convolution"
+  bottom: "conv8_2_h"
+  top: "conv9_1_h"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 64
+    pad: 0
+    kernel_size: 1
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv9_1_relu"
+  type: "ReLU"
+  bottom: "conv9_1_h"
+  top: "conv9_1_h"
+}
+layer {
+  name: "conv9_2_h"
+  type: "Convolution"
+  bottom: "conv9_1_h"
+  top: "conv9_2_h"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 128
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv9_2_relu"
+  type: "ReLU"
+  bottom: "conv9_2_h"
+  top: "conv9_2_h"
+}
+layer {
+  name: "conv4_3_norm"
+  type: "Normalize"
+  bottom: "layer_256_1_bn1"
+  top: "conv4_3_norm"
+  norm_param {
+    across_spatial: false
+    scale_filler {
+      type: "constant"
+      value: 20
+    }
+    channel_shared: false
+  }
+}
+layer {
+  name: "conv4_3_norm_mbox_loc"
+  type: "Convolution"
+  bottom: "conv4_3_norm"
+  top: "conv4_3_norm_mbox_loc"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 16
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv4_3_norm_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv4_3_norm_mbox_loc"
+  top: "conv4_3_norm_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv4_3_norm_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv4_3_norm_mbox_loc_perm"
+  top: "conv4_3_norm_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv4_3_norm_mbox_conf"
+  type: "Convolution"
+  bottom: "conv4_3_norm"
+  top: "conv4_3_norm_mbox_conf"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 8 # 84
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv4_3_norm_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv4_3_norm_mbox_conf"
+  top: "conv4_3_norm_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv4_3_norm_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv4_3_norm_mbox_conf_perm"
+  top: "conv4_3_norm_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv4_3_norm_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv4_3_norm"
+  bottom: "data"
+  top: "conv4_3_norm_mbox_priorbox"
+  prior_box_param {
+    min_size: 30.0
+    max_size: 60.0
+    aspect_ratio: 2
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    step: 8
+    offset: 0.5
+  }
+}
+layer {
+  name: "fc7_mbox_loc"
+  type: "Convolution"
+  bottom: "fc7"
+  top: "fc7_mbox_loc"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 24
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "fc7_mbox_loc_perm"
+  type: "Permute"
+  bottom: "fc7_mbox_loc"
+  top: "fc7_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "fc7_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "fc7_mbox_loc_perm"
+  top: "fc7_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "fc7_mbox_conf"
+  type: "Convolution"
+  bottom: "fc7"
+  top: "fc7_mbox_conf"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 12 # 126
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "fc7_mbox_conf_perm"
+  type: "Permute"
+  bottom: "fc7_mbox_conf"
+  top: "fc7_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "fc7_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "fc7_mbox_conf_perm"
+  top: "fc7_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "fc7_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "fc7"
+  bottom: "data"
+  top: "fc7_mbox_priorbox"
+  prior_box_param {
+    min_size: 60.0
+    max_size: 111.0
+    aspect_ratio: 2
+    aspect_ratio: 3
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    step: 16
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv6_2_mbox_loc"
+  type: "Convolution"
+  bottom: "conv6_2_h"
+  top: "conv6_2_mbox_loc"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 24
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv6_2_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv6_2_mbox_loc"
+  top: "conv6_2_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv6_2_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv6_2_mbox_loc_perm"
+  top: "conv6_2_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv6_2_mbox_conf"
+  type: "Convolution"
+  bottom: "conv6_2_h"
+  top: "conv6_2_mbox_conf"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 12 # 126
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv6_2_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv6_2_mbox_conf"
+  top: "conv6_2_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv6_2_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv6_2_mbox_conf_perm"
+  top: "conv6_2_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv6_2_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv6_2_h"
+  bottom: "data"
+  top: "conv6_2_mbox_priorbox"
+  prior_box_param {
+    min_size: 111.0
+    max_size: 162.0
+    aspect_ratio: 2
+    aspect_ratio: 3
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    step: 32
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv7_2_mbox_loc"
+  type: "Convolution"
+  bottom: "conv7_2_h"
+  top: "conv7_2_mbox_loc"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 24
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv7_2_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv7_2_mbox_loc"
+  top: "conv7_2_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv7_2_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv7_2_mbox_loc_perm"
+  top: "conv7_2_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv7_2_mbox_conf"
+  type: "Convolution"
+  bottom: "conv7_2_h"
+  top: "conv7_2_mbox_conf"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 12 # 126
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv7_2_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv7_2_mbox_conf"
+  top: "conv7_2_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv7_2_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv7_2_mbox_conf_perm"
+  top: "conv7_2_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv7_2_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv7_2_h"
+  bottom: "data"
+  top: "conv7_2_mbox_priorbox"
+  prior_box_param {
+    min_size: 162.0
+    max_size: 213.0
+    aspect_ratio: 2
+    aspect_ratio: 3
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    step: 64
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv8_2_mbox_loc"
+  type: "Convolution"
+  bottom: "conv8_2_h"
+  top: "conv8_2_mbox_loc"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 16
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv8_2_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv8_2_mbox_loc"
+  top: "conv8_2_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv8_2_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv8_2_mbox_loc_perm"
+  top: "conv8_2_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv8_2_mbox_conf"
+  type: "Convolution"
+  bottom: "conv8_2_h"
+  top: "conv8_2_mbox_conf"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 8 # 84
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv8_2_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv8_2_mbox_conf"
+  top: "conv8_2_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv8_2_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv8_2_mbox_conf_perm"
+  top: "conv8_2_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv8_2_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv8_2_h"
+  bottom: "data"
+  top: "conv8_2_mbox_priorbox"
+  prior_box_param {
+    min_size: 213.0
+    max_size: 264.0
+    aspect_ratio: 2
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    step: 100
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv9_2_mbox_loc"
+  type: "Convolution"
+  bottom: "conv9_2_h"
+  top: "conv9_2_mbox_loc"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 16
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv9_2_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv9_2_mbox_loc"
+  top: "conv9_2_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv9_2_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv9_2_mbox_loc_perm"
+  top: "conv9_2_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv9_2_mbox_conf"
+  type: "Convolution"
+  bottom: "conv9_2_h"
+  top: "conv9_2_mbox_conf"
+  param {
+    lr_mult: 1
+    decay_mult: 1
+  }
+  param {
+    lr_mult: 2
+    decay_mult: 0
+  }
+  convolution_param {
+    num_output: 8 # 84
+    pad: 1
+    kernel_size: 3
+    stride: 1
+    weight_filler {
+      type: "xavier"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0
+    }
+  }
+}
+layer {
+  name: "conv9_2_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv9_2_mbox_conf"
+  top: "conv9_2_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv9_2_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv9_2_mbox_conf_perm"
+  top: "conv9_2_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv9_2_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv9_2_h"
+  bottom: "data"
+  top: "conv9_2_mbox_priorbox"
+  prior_box_param {
+    min_size: 264.0
+    max_size: 315.0
+    aspect_ratio: 2
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    step: 300
+    offset: 0.5
+  }
+}
+layer {
+  name: "mbox_loc"
+  type: "Concat"
+  bottom: "conv4_3_norm_mbox_loc_flat"
+  bottom: "fc7_mbox_loc_flat"
+  bottom: "conv6_2_mbox_loc_flat"
+  bottom: "conv7_2_mbox_loc_flat"
+  bottom: "conv8_2_mbox_loc_flat"
+  bottom: "conv9_2_mbox_loc_flat"
+  top: "mbox_loc"
+  concat_param {
+    axis: 1
+  }
+}
+layer {
+  name: "mbox_conf"
+  type: "Concat"
+  bottom: "conv4_3_norm_mbox_conf_flat"
+  bottom: "fc7_mbox_conf_flat"
+  bottom: "conv6_2_mbox_conf_flat"
+  bottom: "conv7_2_mbox_conf_flat"
+  bottom: "conv8_2_mbox_conf_flat"
+  bottom: "conv9_2_mbox_conf_flat"
+  top: "mbox_conf"
+  concat_param {
+    axis: 1
+  }
+}
+layer {
+  name: "mbox_priorbox"
+  type: "Concat"
+  bottom: "conv4_3_norm_mbox_priorbox"
+  bottom: "fc7_mbox_priorbox"
+  bottom: "conv6_2_mbox_priorbox"
+  bottom: "conv7_2_mbox_priorbox"
+  bottom: "conv8_2_mbox_priorbox"
+  bottom: "conv9_2_mbox_priorbox"
+  top: "mbox_priorbox"
+  concat_param {
+    axis: 2
+  }
+}
+
+layer {
+  name: "mbox_conf_reshape"
+  type: "Reshape"
+  bottom: "mbox_conf"
+  top: "mbox_conf_reshape"
+  reshape_param {
+    shape {
+      dim: 0
+      dim: -1
+      dim: 2
+    }
+  }
+}
+layer {
+  name: "mbox_conf_softmax"
+  type: "Softmax"
+  bottom: "mbox_conf_reshape"
+  top: "mbox_conf_softmax"
+  softmax_param {
+    axis: 2
+  }
+}
+layer {
+  name: "mbox_conf_flatten"
+  type: "Flatten"
+  bottom: "mbox_conf_softmax"
+  top: "mbox_conf_flatten"
+  flatten_param {
+    axis: 1
+  }
+}
+
+layer {
+  name: "detection_out"
+  type: "DetectionOutput"
+  bottom: "mbox_loc"
+  bottom: "mbox_conf_flatten"
+  bottom: "mbox_priorbox"
+  top: "detection_out"
+  include {
+    phase: TEST
+  }
+  detection_output_param {
+    num_classes: 2
+    share_location: true
+    background_label_id: 0
+    nms_param {
+      nms_threshold: 0.45
+      top_k: 400
+    }
+    code_type: CENTER_SIZE
+    keep_top_k: 200
+    confidence_threshold: 0.01
+  }
+}

model files/face detection model/readme.txt

@@ -0,0 +1 @@
+This model can detect face in any frame or person image.

model files/face detection model/res10_300x300_ssd_iter_140000.caffemodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a56a11a57a4a295956b0660b4a3d76bbdca2206c4961cea8efe7d95c7cb2f2d
+size 10666211

model files/face mask detection model/mask_detector.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a62288c0832df0fad0e97b881b5268d3deb40ec372611b7d81c913715799af00
+size 11483536

model files/generic object detection model/MobileNetSSD_deploy.caffemodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:761c86fbae3d8361dd454f7c740a964f62975ed32f4324b8b85994edec30f6af
+size 23147564

model files/generic object detection model/MobileNetSSD_deploy.prototxt

@@ -0,0 +1,1912 @@
+name: "MobileNet-SSD"
+input: "data"
+input_shape {
+  dim: 1
+  dim: 3
+  dim: 300
+  dim: 300
+}
+layer {
+  name: "conv0"
+  type: "Convolution"
+  bottom: "data"
+  top: "conv0"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 32
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv0/relu"
+  type: "ReLU"
+  bottom: "conv0"
+  top: "conv0"
+}
+layer {
+  name: "conv1/dw"
+  type: "Convolution"
+  bottom: "conv0"
+  top: "conv1/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 32
+    pad: 1
+    kernel_size: 3
+    group: 32
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv1/dw/relu"
+  type: "ReLU"
+  bottom: "conv1/dw"
+  top: "conv1/dw"
+}
+layer {
+  name: "conv1"
+  type: "Convolution"
+  bottom: "conv1/dw"
+  top: "conv1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 64
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv1/relu"
+  type: "ReLU"
+  bottom: "conv1"
+  top: "conv1"
+}
+layer {
+  name: "conv2/dw"
+  type: "Convolution"
+  bottom: "conv1"
+  top: "conv2/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 64
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    group: 64
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv2/dw/relu"
+  type: "ReLU"
+  bottom: "conv2/dw"
+  top: "conv2/dw"
+}
+layer {
+  name: "conv2"
+  type: "Convolution"
+  bottom: "conv2/dw"
+  top: "conv2"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 128
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv2/relu"
+  type: "ReLU"
+  bottom: "conv2"
+  top: "conv2"
+}
+layer {
+  name: "conv3/dw"
+  type: "Convolution"
+  bottom: "conv2"
+  top: "conv3/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 128
+    pad: 1
+    kernel_size: 3
+    group: 128
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv3/dw/relu"
+  type: "ReLU"
+  bottom: "conv3/dw"
+  top: "conv3/dw"
+}
+layer {
+  name: "conv3"
+  type: "Convolution"
+  bottom: "conv3/dw"
+  top: "conv3"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 128
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv3/relu"
+  type: "ReLU"
+  bottom: "conv3"
+  top: "conv3"
+}
+layer {
+  name: "conv4/dw"
+  type: "Convolution"
+  bottom: "conv3"
+  top: "conv4/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 128
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    group: 128
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv4/dw/relu"
+  type: "ReLU"
+  bottom: "conv4/dw"
+  top: "conv4/dw"
+}
+layer {
+  name: "conv4"
+  type: "Convolution"
+  bottom: "conv4/dw"
+  top: "conv4"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 256
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv4/relu"
+  type: "ReLU"
+  bottom: "conv4"
+  top: "conv4"
+}
+layer {
+  name: "conv5/dw"
+  type: "Convolution"
+  bottom: "conv4"
+  top: "conv5/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+    group: 256
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv5/dw/relu"
+  type: "ReLU"
+  bottom: "conv5/dw"
+  top: "conv5/dw"
+}
+layer {
+  name: "conv5"
+  type: "Convolution"
+  bottom: "conv5/dw"
+  top: "conv5"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 256
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv5/relu"
+  type: "ReLU"
+  bottom: "conv5"
+  top: "conv5"
+}
+layer {
+  name: "conv6/dw"
+  type: "Convolution"
+  bottom: "conv5"
+  top: "conv6/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    group: 256
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv6/dw/relu"
+  type: "ReLU"
+  bottom: "conv6/dw"
+  top: "conv6/dw"
+}
+layer {
+  name: "conv6"
+  type: "Convolution"
+  bottom: "conv6/dw"
+  top: "conv6"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv6/relu"
+  type: "ReLU"
+  bottom: "conv6"
+  top: "conv6"
+}
+layer {
+  name: "conv7/dw"
+  type: "Convolution"
+  bottom: "conv6"
+  top: "conv7/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+    group: 512
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv7/dw/relu"
+  type: "ReLU"
+  bottom: "conv7/dw"
+  top: "conv7/dw"
+}
+layer {
+  name: "conv7"
+  type: "Convolution"
+  bottom: "conv7/dw"
+  top: "conv7"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv7/relu"
+  type: "ReLU"
+  bottom: "conv7"
+  top: "conv7"
+}
+layer {
+  name: "conv8/dw"
+  type: "Convolution"
+  bottom: "conv7"
+  top: "conv8/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+    group: 512
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv8/dw/relu"
+  type: "ReLU"
+  bottom: "conv8/dw"
+  top: "conv8/dw"
+}
+layer {
+  name: "conv8"
+  type: "Convolution"
+  bottom: "conv8/dw"
+  top: "conv8"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv8/relu"
+  type: "ReLU"
+  bottom: "conv8"
+  top: "conv8"
+}
+layer {
+  name: "conv9/dw"
+  type: "Convolution"
+  bottom: "conv8"
+  top: "conv9/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+    group: 512
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv9/dw/relu"
+  type: "ReLU"
+  bottom: "conv9/dw"
+  top: "conv9/dw"
+}
+layer {
+  name: "conv9"
+  type: "Convolution"
+  bottom: "conv9/dw"
+  top: "conv9"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv9/relu"
+  type: "ReLU"
+  bottom: "conv9"
+  top: "conv9"
+}
+layer {
+  name: "conv10/dw"
+  type: "Convolution"
+  bottom: "conv9"
+  top: "conv10/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+    group: 512
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv10/dw/relu"
+  type: "ReLU"
+  bottom: "conv10/dw"
+  top: "conv10/dw"
+}
+layer {
+  name: "conv10"
+  type: "Convolution"
+  bottom: "conv10/dw"
+  top: "conv10"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv10/relu"
+  type: "ReLU"
+  bottom: "conv10"
+  top: "conv10"
+}
+layer {
+  name: "conv11/dw"
+  type: "Convolution"
+  bottom: "conv10"
+  top: "conv11/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+    group: 512
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv11/dw/relu"
+  type: "ReLU"
+  bottom: "conv11/dw"
+  top: "conv11/dw"
+}
+layer {
+  name: "conv11"
+  type: "Convolution"
+  bottom: "conv11/dw"
+  top: "conv11"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv11/relu"
+  type: "ReLU"
+  bottom: "conv11"
+  top: "conv11"
+}
+layer {
+  name: "conv12/dw"
+  type: "Convolution"
+  bottom: "conv11"
+  top: "conv12/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    group: 512
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv12/dw/relu"
+  type: "ReLU"
+  bottom: "conv12/dw"
+  top: "conv12/dw"
+}
+layer {
+  name: "conv12"
+  type: "Convolution"
+  bottom: "conv12/dw"
+  top: "conv12"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 1024
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv12/relu"
+  type: "ReLU"
+  bottom: "conv12"
+  top: "conv12"
+}
+layer {
+  name: "conv13/dw"
+  type: "Convolution"
+  bottom: "conv12"
+  top: "conv13/dw"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 1024
+    pad: 1
+    kernel_size: 3
+    group: 1024
+    engine: CAFFE
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv13/dw/relu"
+  type: "ReLU"
+  bottom: "conv13/dw"
+  top: "conv13/dw"
+}
+layer {
+  name: "conv13"
+  type: "Convolution"
+  bottom: "conv13/dw"
+  top: "conv13"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 1024
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv13/relu"
+  type: "ReLU"
+  bottom: "conv13"
+  top: "conv13"
+}
+layer {
+  name: "conv14_1"
+  type: "Convolution"
+  bottom: "conv13"
+  top: "conv14_1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 256
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv14_1/relu"
+  type: "ReLU"
+  bottom: "conv14_1"
+  top: "conv14_1"
+}
+layer {
+  name: "conv14_2"
+  type: "Convolution"
+  bottom: "conv14_1"
+  top: "conv14_2"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 512
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv14_2/relu"
+  type: "ReLU"
+  bottom: "conv14_2"
+  top: "conv14_2"
+}
+layer {
+  name: "conv15_1"
+  type: "Convolution"
+  bottom: "conv14_2"
+  top: "conv15_1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 128
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv15_1/relu"
+  type: "ReLU"
+  bottom: "conv15_1"
+  top: "conv15_1"
+}
+layer {
+  name: "conv15_2"
+  type: "Convolution"
+  bottom: "conv15_1"
+  top: "conv15_2"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv15_2/relu"
+  type: "ReLU"
+  bottom: "conv15_2"
+  top: "conv15_2"
+}
+layer {
+  name: "conv16_1"
+  type: "Convolution"
+  bottom: "conv15_2"
+  top: "conv16_1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 128
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv16_1/relu"
+  type: "ReLU"
+  bottom: "conv16_1"
+  top: "conv16_1"
+}
+layer {
+  name: "conv16_2"
+  type: "Convolution"
+  bottom: "conv16_1"
+  top: "conv16_2"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 256
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv16_2/relu"
+  type: "ReLU"
+  bottom: "conv16_2"
+  top: "conv16_2"
+}
+layer {
+  name: "conv17_1"
+  type: "Convolution"
+  bottom: "conv16_2"
+  top: "conv17_1"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 64
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv17_1/relu"
+  type: "ReLU"
+  bottom: "conv17_1"
+  top: "conv17_1"
+}
+layer {
+  name: "conv17_2"
+  type: "Convolution"
+  bottom: "conv17_1"
+  top: "conv17_2"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 128
+    pad: 1
+    kernel_size: 3
+    stride: 2
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv17_2/relu"
+  type: "ReLU"
+  bottom: "conv17_2"
+  top: "conv17_2"
+}
+layer {
+  name: "conv11_mbox_loc"
+  type: "Convolution"
+  bottom: "conv11"
+  top: "conv11_mbox_loc"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 12
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv11_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv11_mbox_loc"
+  top: "conv11_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv11_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv11_mbox_loc_perm"
+  top: "conv11_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv11_mbox_conf"
+  type: "Convolution"
+  bottom: "conv11"
+  top: "conv11_mbox_conf"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 63
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv11_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv11_mbox_conf"
+  top: "conv11_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv11_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv11_mbox_conf_perm"
+  top: "conv11_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv11_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv11"
+  bottom: "data"
+  top: "conv11_mbox_priorbox"
+  prior_box_param {
+    min_size: 60.0
+    aspect_ratio: 2.0
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv13_mbox_loc"
+  type: "Convolution"
+  bottom: "conv13"
+  top: "conv13_mbox_loc"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 24
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv13_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv13_mbox_loc"
+  top: "conv13_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv13_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv13_mbox_loc_perm"
+  top: "conv13_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv13_mbox_conf"
+  type: "Convolution"
+  bottom: "conv13"
+  top: "conv13_mbox_conf"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 126
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv13_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv13_mbox_conf"
+  top: "conv13_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv13_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv13_mbox_conf_perm"
+  top: "conv13_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv13_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv13"
+  bottom: "data"
+  top: "conv13_mbox_priorbox"
+  prior_box_param {
+    min_size: 105.0
+    max_size: 150.0
+    aspect_ratio: 2.0
+    aspect_ratio: 3.0
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv14_2_mbox_loc"
+  type: "Convolution"
+  bottom: "conv14_2"
+  top: "conv14_2_mbox_loc"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 24
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv14_2_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv14_2_mbox_loc"
+  top: "conv14_2_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv14_2_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv14_2_mbox_loc_perm"
+  top: "conv14_2_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv14_2_mbox_conf"
+  type: "Convolution"
+  bottom: "conv14_2"
+  top: "conv14_2_mbox_conf"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 126
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv14_2_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv14_2_mbox_conf"
+  top: "conv14_2_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv14_2_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv14_2_mbox_conf_perm"
+  top: "conv14_2_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv14_2_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv14_2"
+  bottom: "data"
+  top: "conv14_2_mbox_priorbox"
+  prior_box_param {
+    min_size: 150.0
+    max_size: 195.0
+    aspect_ratio: 2.0
+    aspect_ratio: 3.0
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv15_2_mbox_loc"
+  type: "Convolution"
+  bottom: "conv15_2"
+  top: "conv15_2_mbox_loc"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 24
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv15_2_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv15_2_mbox_loc"
+  top: "conv15_2_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv15_2_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv15_2_mbox_loc_perm"
+  top: "conv15_2_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv15_2_mbox_conf"
+  type: "Convolution"
+  bottom: "conv15_2"
+  top: "conv15_2_mbox_conf"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 126
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv15_2_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv15_2_mbox_conf"
+  top: "conv15_2_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv15_2_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv15_2_mbox_conf_perm"
+  top: "conv15_2_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv15_2_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv15_2"
+  bottom: "data"
+  top: "conv15_2_mbox_priorbox"
+  prior_box_param {
+    min_size: 195.0
+    max_size: 240.0
+    aspect_ratio: 2.0
+    aspect_ratio: 3.0
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv16_2_mbox_loc"
+  type: "Convolution"
+  bottom: "conv16_2"
+  top: "conv16_2_mbox_loc"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 24
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv16_2_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv16_2_mbox_loc"
+  top: "conv16_2_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv16_2_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv16_2_mbox_loc_perm"
+  top: "conv16_2_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv16_2_mbox_conf"
+  type: "Convolution"
+  bottom: "conv16_2"
+  top: "conv16_2_mbox_conf"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 126
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv16_2_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv16_2_mbox_conf"
+  top: "conv16_2_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv16_2_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv16_2_mbox_conf_perm"
+  top: "conv16_2_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv16_2_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv16_2"
+  bottom: "data"
+  top: "conv16_2_mbox_priorbox"
+  prior_box_param {
+    min_size: 240.0
+    max_size: 285.0
+    aspect_ratio: 2.0
+    aspect_ratio: 3.0
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    offset: 0.5
+  }
+}
+layer {
+  name: "conv17_2_mbox_loc"
+  type: "Convolution"
+  bottom: "conv17_2"
+  top: "conv17_2_mbox_loc"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 24
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv17_2_mbox_loc_perm"
+  type: "Permute"
+  bottom: "conv17_2_mbox_loc"
+  top: "conv17_2_mbox_loc_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv17_2_mbox_loc_flat"
+  type: "Flatten"
+  bottom: "conv17_2_mbox_loc_perm"
+  top: "conv17_2_mbox_loc_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv17_2_mbox_conf"
+  type: "Convolution"
+  bottom: "conv17_2"
+  top: "conv17_2_mbox_conf"
+  param {
+    lr_mult: 1.0
+    decay_mult: 1.0
+  }
+  param {
+    lr_mult: 2.0
+    decay_mult: 0.0
+  }
+  convolution_param {
+    num_output: 126
+    kernel_size: 1
+    weight_filler {
+      type: "msra"
+    }
+    bias_filler {
+      type: "constant"
+      value: 0.0
+    }
+  }
+}
+layer {
+  name: "conv17_2_mbox_conf_perm"
+  type: "Permute"
+  bottom: "conv17_2_mbox_conf"
+  top: "conv17_2_mbox_conf_perm"
+  permute_param {
+    order: 0
+    order: 2
+    order: 3
+    order: 1
+  }
+}
+layer {
+  name: "conv17_2_mbox_conf_flat"
+  type: "Flatten"
+  bottom: "conv17_2_mbox_conf_perm"
+  top: "conv17_2_mbox_conf_flat"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "conv17_2_mbox_priorbox"
+  type: "PriorBox"
+  bottom: "conv17_2"
+  bottom: "data"
+  top: "conv17_2_mbox_priorbox"
+  prior_box_param {
+    min_size: 285.0
+    max_size: 300.0
+    aspect_ratio: 2.0
+    aspect_ratio: 3.0
+    flip: true
+    clip: false
+    variance: 0.1
+    variance: 0.1
+    variance: 0.2
+    variance: 0.2
+    offset: 0.5
+  }
+}
+layer {
+  name: "mbox_loc"
+  type: "Concat"
+  bottom: "conv11_mbox_loc_flat"
+  bottom: "conv13_mbox_loc_flat"
+  bottom: "conv14_2_mbox_loc_flat"
+  bottom: "conv15_2_mbox_loc_flat"
+  bottom: "conv16_2_mbox_loc_flat"
+  bottom: "conv17_2_mbox_loc_flat"
+  top: "mbox_loc"
+  concat_param {
+    axis: 1
+  }
+}
+layer {
+  name: "mbox_conf"
+  type: "Concat"
+  bottom: "conv11_mbox_conf_flat"
+  bottom: "conv13_mbox_conf_flat"
+  bottom: "conv14_2_mbox_conf_flat"
+  bottom: "conv15_2_mbox_conf_flat"
+  bottom: "conv16_2_mbox_conf_flat"
+  bottom: "conv17_2_mbox_conf_flat"
+  top: "mbox_conf"
+  concat_param {
+    axis: 1
+  }
+}
+layer {
+  name: "mbox_priorbox"
+  type: "Concat"
+  bottom: "conv11_mbox_priorbox"
+  bottom: "conv13_mbox_priorbox"
+  bottom: "conv14_2_mbox_priorbox"
+  bottom: "conv15_2_mbox_priorbox"
+  bottom: "conv16_2_mbox_priorbox"
+  bottom: "conv17_2_mbox_priorbox"
+  top: "mbox_priorbox"
+  concat_param {
+    axis: 2
+  }
+}
+layer {
+  name: "mbox_conf_reshape"
+  type: "Reshape"
+  bottom: "mbox_conf"
+  top: "mbox_conf_reshape"
+  reshape_param {
+    shape {
+      dim: 0
+      dim: -1
+      dim: 21
+    }
+  }
+}
+layer {
+  name: "mbox_conf_softmax"
+  type: "Softmax"
+  bottom: "mbox_conf_reshape"
+  top: "mbox_conf_softmax"
+  softmax_param {
+    axis: 2
+  }
+}
+layer {
+  name: "mbox_conf_flatten"
+  type: "Flatten"
+  bottom: "mbox_conf_softmax"
+  top: "mbox_conf_flatten"
+  flatten_param {
+    axis: 1
+  }
+}
+layer {
+  name: "detection_out"
+  type: "DetectionOutput"
+  bottom: "mbox_loc"
+  bottom: "mbox_conf_flatten"
+  bottom: "mbox_priorbox"
+  top: "detection_out"
+  include {
+    phase: TEST
+  }
+  detection_output_param {
+    num_classes: 21
+    share_location: true
+    background_label_id: 0
+    nms_param {
+      nms_threshold: 0.45
+      top_k: 100
+    }
+    code_type: CENTER_SIZE
+    keep_top_k: 100
+    confidence_threshold: 0.25
+  }
+}

model files/generic object detection model/readme.txt

@@ -0,0 +1,8 @@
+This model can detect multiple objects like person, cat, dog, bus, car, airplane etc.
+
+Here is the full list:
+
+"background", "aeroplane", "bicycle", "bird", "boat",
+"bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
+"dog", "horse", "motorbike", "person", "pottedplant", "sheep",
+"sofa", "train", "tvmonitor"

opencv-example.py

@@ -0,0 +1,22 @@
+import cv2
+import imutils
+
+# image = cv2.imread('input_image.jpg')
+cap = cv2.VideoCapture(1)
+
+while True:
+    ret, frame = cap.read()
+    frame = imutils.resize(frame, width=800)
+
+    text = "This is my custom text"
+    cv2.putText(frame, text, (5, 30), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 255), 1)
+
+    cv2.rectangle(frame, (50, 50), (500, 500), (0, 0, 255), 2)
+
+    cv2.imshow('Application', frame)
+
+    key = cv2.waitKey(1)
+    if key == ord('q'):
+        break
+
+cv2.destroyAllWindows()

pages/Login.py

@@ -0,0 +1,679 @@
+import cv2
+import datetime
+import imutils
+import numpy as np
+from centroidtracker import CentroidTracker
+import pandas as pd 
+import torch 
+import streamlit as st
+import mediapipe as mp
+import cv2 as cv
+import numpy as np
+import tempfile
+import time
+from PIL import Image
+import pandas as pd
+import torch
+import base64
+import streamlit.components.v1 as components
+import csv
+import pickle
+from pathlib import Path
+import streamlit_authenticator as stauth
+import os
+import csv
+from streamlit_option_menu import option_menu
+#  x-x-x-x-x-x-x-x-x-x-x-x-x-x LOGIN FORM x-x-x-x-x-x-x-x-x
+
+                                
+import streamlit as st
+import pandas as pd
+import hashlib
+import sqlite3 
+#
+
+import pickle
+from pathlib import Path
+import streamlit_authenticator as stauth
+import pyautogui
+
+# print("Done !!!")
+
+data = ["student Count",'Date','Id','Mobile','Watch']
+with open('final.csv', 'w') as file:
+    writer = csv.writer(file)
+    writer.writerow(data)
+    
+
+# # l1 = []
+# # l2 = []
+# # if st.button('signup'):
+    
+    
+# #     usernames = st.text_input('Username')
+# #     pwd = st.text_input('Password') 
+# #     l1.append(usernames)
+# #     l2.append(pwd)
+
+# #     names = ["dmin", "ser"]
+# #     if st.button("signupsss"):
+# #         username =l1
+
+# #         password =l2
+
+# #         hashed_passwords =stauth.Hasher(password).generate()
+
+# #         file_path = Path(__file__).parent / "hashed_pw.pkl"
+
+# #         with file_path.open("wb") as file:
+# #             pickle.dump(hashed_passwords, file)
+            
+    
+# # elif st.button('Logins'):
+# names = ['dmin', 'ser']
+
+# username = []
+
+# file_path = Path(__file__).parent / 'hashed_pw.pkl'
+
+# with file_path.open('rb') as file:
+#     hashed_passwords = pickle.load(file)
+
+# authenticator = stauth.Authenticate(names,username,hashed_passwords,'Cheating Detection','abcdefg',cookie_expiry_days=180)
+
+# name,authentication_status,username= authenticator.login('Login','main')
+
+
+# if authentication_status == False:
+#     st.error('Username/Password is incorrect')
+    
+# if authentication_status == None:
+#     st.error('Please enter a username and password')
+
+@st.experimental_memo
+def get_img_as_base64(file):
+    with open(file, "rb") as f:
+        data = f.read()
+    return base64.b64encode(data).decode()
+
+
+#img = get_img_as_base64("/home/anas/PersonTracking/WebUI/attendence.jpg")
+
+page_bg_img = f"""
+<style>
+[data-testid="stAppViewContainer"] > .main {{
+background-image: url("https://www.xmple.com/wallpaper/blue-gradient-black-linear-1920x1080-c2-87cefa-000000-a-180-f-14.svg");
+background-size: 180%;
+background-position: top left;
+background-repeat: no-repeat;
+background-attachment: local;
+}}
+
+[data-testid="stHeader"] {{
+background: rgba(0,0,0,0);
+}}
+[data-testid="stToolbar"] {{
+right: 2rem;
+}}
+</style>
+"""
+
+st.markdown(page_bg_img, unsafe_allow_html=True)
+files = pd.read_csv('LoginStatus.csv')
+
+
+idS = list(files['Id'])
+Pwd = list(files['Password'].astype(str))
+
+# print(type(Pwd))
+ids = st.sidebar.text_input('Enter a username')
+Pswd = st.sidebar.text_input('Enter a password',type="password",key="password")
+
+# print('list : ',type(Pwd))
+
+    
+        
+if (ids in idS) and(str(Pswd) in Pwd):
+    
+        # st.empty()    
+        date_time = time.strftime("%b %d %Y %-I:%M %p")
+        date = date_time.split()
+        dates = date[0:3]
+        times = date[3:5]
+        # x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-xAPPLICACTION -x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x
+
+        def non_max_suppression_fast(boxes, overlapThresh):
+            try:
+                if len(boxes) == 0:
+                    return []
+
+                if boxes.dtype.kind == "i":
+                    boxes = boxes.astype("float")
+
+                pick = []
+
+                x1 = boxes[:, 0]
+                y1 = boxes[:, 1]
+                x2 = boxes[:, 2]
+                y2 = boxes[:, 3]
+
+                area = (x2 - x1 + 1) * (y2 - y1 + 1)
+                idxs = np.argsort(y2)
+
+                while len(idxs) > 0:
+                    last = len(idxs) - 1
+                    i = idxs[last]
+                    pick.append(i)
+
+                    xx1 = np.maximum(x1[i], x1[idxs[:last]])
+                    yy1 = np.maximum(y1[i], y1[idxs[:last]])
+                    xx2 = np.minimum(x2[i], x2[idxs[:last]])
+                    yy2 = np.minimum(y2[i], y2[idxs[:last]])
+
+                    w = np.maximum(0, xx2 - xx1 + 1)
+                    h = np.maximum(0, yy2 - yy1 + 1)
+
+                    overlap = (w * h) / area[idxs[:last]]
+
+                    idxs = np.delete(idxs, np.concatenate(([last],
+                                                        np.where(overlap > overlapThresh)[0])))
+
+                return boxes[pick].astype("int")
+            except Exception as e:
+                print("Exception occurred in non_max_suppression : {}".format(e))
+
+
+        protopath = "MobileNetSSD_deploy.prototxt"
+        modelpath = "MobileNetSSD_deploy.caffemodel"
+        detector = cv2.dnn.readNetFromCaffe(prototxt=protopath, caffeModel=modelpath)
+        # Only enable it if you are using OpenVino environment
+        # detector.setPreferableBackend(cv2.dnn.DNN_BACKEND_INFERENCE_ENGINE)
+        # detector.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU)
+
+
+        CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
+                "bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
+                "dog", "horse", "motorbike", "person", "pottedplant", "sheep",
+                "sofa", "train", "tvmonitor"]
+
+        tracker = CentroidTracker(maxDisappeared=80, maxDistance=90)
+
+        st.markdown(
+            """
+            <style>
+            [data-testid="stSidebar"][aria-expanded="true"] > div:first-child{
+                width: 350px
+            }
+            [data-testid="stSidebar"][aria-expanded="false"] > div:first-child{
+                width: 350px
+                margin-left: -350px
+            }
+            </style>
+            """,
+            unsafe_allow_html=True,
+        )
+        hide_streamlit_style = """
+                <style>
+                #MainMenu {visibility: hidden;}
+                footer {visibility: hidden;}
+                </style>
+                """
+        st.markdown(hide_streamlit_style, unsafe_allow_html=True)
+
+
+        # Resize Images to fit Container
+        @st.cache()
+        # Get Image Dimensions
+        def image_resize(image, width=None, height=None, inter=cv.INTER_AREA):
+            dim = None
+            (h,w) = image.shape[:2]
+
+            if width is None and height is None:
+                return image
+
+            if width is None:
+                r = width/float(w)
+                dim = (int(w*r),height)
+
+            else:
+                r = width/float(w)
+                dim = width, int(h*r)
+
+            # Resize image
+            resized = cv.resize(image,dim,interpolation=inter)
+
+            return resized
+                
+        # About Page
+        # authenticator.logout('Logout')
+        EXAMPLE_NO = 3
+
+
+        def streamlit_menu(example=1):
+            if example == 1:
+                # 1. as sidebar menu
+                with st.sidebar:
+                    selected = option_menu(
+                        menu_title="Main Menu",  # required
+                        options=["Home", "Projects", "Contact"],  # required
+                        icons=["house", "book", "envelope"],  # optional
+                        menu_icon="cast",  # optional
+                        default_index=0,  # optional
+                    )
+                return selected
+
+            if example == 2:
+                # 2. horizontal menu w/o custom style
+                selected = option_menu(
+                    menu_title=None,  # required
+                    options=["Home", "Projects", "Contact"],  # required
+                    icons=["house", "book", "envelope"],  # optional
+                    menu_icon="cast",  # optional
+                    default_index=0,  # optional
+                    orientation="horizontal",
+                )
+                return selected
+
+            if example == 3:
+                # 2. horizontal menu with custom style
+                selected = option_menu(
+                    menu_title=None,  # required
+                    options=["Home", "Projects", "Contact"],  # required
+                    icons=["house", "book", "envelope"],  # optional
+                    menu_icon="cast",  # optional
+                    default_index=0,  # optional
+                    orientation="horizontal",
+                    styles={
+                        "container": {"padding": "0!important", "background-color": "#eaeaea"},
+                        "icon": {"color": "#080602", "font-size": "18px"},
+                        "nav-link": {
+                            "font-size": "18px",
+                            "text-align": "left",
+                            "color": "#000000",
+                            "margin": "0px",
+                            "--hover-color": "#E1A031",
+                        },
+                        "nav-link-selected": {"background-color": "#ffffff"},
+                    },
+                )
+                return selected
+
+
+        selected = streamlit_menu(example=EXAMPLE_NO)
+
+        if selected == "Home":
+            st.title(f"You have selected {selected}")
+        # if selected == "Projects":
+        #     st.title(f"You have selected {selected}")
+        if selected == "Contact":
+            st.title(f"You have selected {selected}")
+        # app_mode = st.sidebar.selectbox(
+        #                 'App Mode',
+        #                 ['Application']
+        #                 )
+        if selected == 'Projects':
+        # 2. horizontal menu with custom style
+            # selected = option_menu(
+            #     menu_title=None,  # required
+            #     options=["Home", "Projects", "Contact"],  # required
+            #     icons=["house", "book", "envelope"],  # optional
+            #     menu_icon="cast",  # optional
+            #     default_index=0,  # optional
+            #     orientation="horizontal",
+            #     styles={
+            #         "container": {"padding": "0!important", "background-color": "#fafafa"},
+            #         "icon": {"color": "orange", "font-size": "25px"},
+            #         "nav-link": {
+            #             "font-size": "25px",
+            #             "text-align": "left",
+            #             "margin": "0px",
+            #             "--hover-color": "#eee",
+            #         },
+            #         "nav-link-selected": {"background-color": "blue"},
+            #     },
+            # )
+        # if app_mode == 'About':
+        #     st.title('About Product And Team')
+        #     st.markdown('''
+        #                 Imran Bhai Project
+        #     ''')
+        #     st.markdown(
+        #         """
+        #         <style>
+        #         [data-testid="stSidebar"][aria-expanded="true"] > div:first-child{
+        #             width: 350px
+        #         }
+        #         [data-testid="stSidebar"][aria-expanded="false"] > div:first-child{
+        #             width: 350px
+        #             margin-left: -350px
+        #         }
+        #         </style>
+        #         """,
+        #         unsafe_allow_html=True,
+        #     )
+
+            
+
+
+        # elif app_mode == 'Application':
+            
+            st.set_option('deprecation.showfileUploaderEncoding', False)
+
+            use_webcam = "pass"
+            # record = st.sidebar.checkbox("Record Video")
+
+            # if record:
+            #     st.checkbox('Recording', True)
+
+            # drawing_spec = mp.solutions.drawing_utils.DrawingSpec(thickness=2, circle_radius=1)
+
+            # st.sidebar.markdown('---')
+
+            # ## Add Sidebar and Window style
+            # st.markdown(
+            #     """
+            #     <style>
+            #     [data-testid="stSidebar"][aria-expanded="true"] > div:first-child{
+            #         width: 350px
+            #     }
+            #     [data-testid="stSidebar"][aria-expanded="false"] > div:first-child{
+            #         width: 350px
+            #         margin-left: -350px
+            #     }
+            #     </style>
+            #     """,
+            #     unsafe_allow_html=True,
+            # )
+
+            # max_faces = st.sidebar.number_input('Maximum Number of Faces', value=5, min_value=1)
+            # st.sidebar.markdown('---')
+            # detection_confidence = st.sidebar.slider('Min Detection Confidence', min_value=0.0,max_value=1.0,value=0.5)
+            # tracking_confidence = st.sidebar.slider('Min Tracking Confidence', min_value=0.0,max_value=1.0,value=0.5)
+            # st.sidebar.markdown('---')
+
+            ## Get Video
+            stframe = st.empty()
+            video_file_buffer = st.file_uploader("Upload a Video", type=['mp4', 'mov', 'avi', 'asf', 'm4v'])
+            temp_file = tempfile.NamedTemporaryFile(delete=False)
+
+            
+            if not video_file_buffer:
+                if use_webcam:
+                    video = cv.VideoCapture(0)
+                else:
+                    try:
+                        video = cv.VideoCapture(1)
+                        temp_file.name = video
+                    except:
+                        pass
+            else:
+                temp_file.write(video_file_buffer.read())
+                video = cv.VideoCapture(temp_file.name)
+
+            width = int(video.get(cv.CAP_PROP_FRAME_WIDTH))
+            height = int(video.get(cv.CAP_PROP_FRAME_HEIGHT))
+            fps_input = int(video.get(cv.CAP_PROP_FPS))
+
+            ## Recording
+            codec = cv.VideoWriter_fourcc('a','v','c','1')
+            out = cv.VideoWriter('output1.mp4', codec, fps_input, (width,height))
+
+            # st.sidebar.text('Input Video')
+            # st.sidebar.video(temp_file.name)
+
+            fps = 0
+            i = 0
+
+            drawing_spec = mp.solutions.drawing_utils.DrawingSpec(thickness=2, circle_radius=1)
+
+            kpil, kpil2, kpil3,kpil4,kpil5, kpil6 = st.columns(6)
+
+            with kpil:
+                st.markdown('**Frame Rate**')
+                kpil_text = st.markdown('0')
+
+            with kpil2:
+                st.markdown('**detection ID**')
+                kpil2_text = st.markdown('0')
+
+            with kpil3:
+                st.markdown('**Mobile**')
+                kpil3_text = st.markdown('0')
+            with kpil4:
+                st.markdown('**Watch**')
+                kpil4_text = st.markdown('0')
+            with kpil5:
+                st.markdown('**Count**')
+                kpil5_text = st.markdown('0')
+            with kpil6:
+                st.markdown('**Img Res**')
+                kpil6_text = st.markdown('0')
+            
+
+
+            st.markdown('<hr/>', unsafe_allow_html=True)
+            # try:
+            def main():
+                db = {}
+                
+                # cap = cv2.VideoCapture('//home//anas//PersonTracking//WebUI//movement.mp4')
+                path='/usr/local/lib/python3.10/dist-packages/yolo0vs5/yolov5s-int8.tflite'
+                #count=0
+                custom = 'yolov5s'
+
+                model = torch.hub.load('/usr/local/lib/python3.10/dist-packages/yolovs5', custom, path,source='local',force_reload=True)
+
+                b=model.names[0] = 'person'
+                mobile = model.names[67] = 'cell phone'
+                watch = model.names[75] = 'clock'
+
+                fps_start_time = datetime.datetime.now()
+                fps = 0
+                size=416
+
+                count=0
+                counter=0
+
+
+                color=(0,0,255)
+
+                cy1=250
+                offset=6
+
+
+                pt1 = (120, 100)
+                pt2 = (980, 1150)
+                color = (0, 255, 0)
+
+                pt3 = (283, 103)
+                pt4 = (1500, 1150)
+                
+                cy2 = 500
+                color = (0, 255, 0)
+                total_frames = 0
+                prevTime = 0
+                cur_frame = 0
+                count=0
+                counter=0
+                fps_start_time = datetime.datetime.now()
+                fps = 0
+                total_frames = 0
+                lpc_count = 0
+                opc_count = 0
+                object_id_list = []
+                # success = True
+                if st.button("Detect"):
+                    try:
+                        while video.isOpened():
+                            
+                            ret, frame = video.read()
+                            frame = imutils.resize(frame, width=600)
+                            total_frames = total_frames + 1
+
+                            (H, W) = frame.shape[:2]
+
+                            blob = cv2.dnn.blobFromImage(frame, 0.007843, (W, H), 127.5)
+
+                            detector.setInput(blob)
+                            person_detections = detector.forward()
+                            rects = []
+                            for i in np.arange(0, person_detections.shape[2]):
+                                confidence = person_detections[0, 0, i, 2]
+                                if confidence > 0.5:
+                                    idx = int(person_detections[0, 0, i, 1])
+
+                                    if CLASSES[idx] != "person":
+                                        continue
+
+                                    person_box = person_detections[0, 0, i, 3:7] * np.array([W, H, W, H])
+                                    (startX, startY, endX, endY) = person_box.astype("int")
+                                    rects.append(person_box)
+
+                            boundingboxes = np.array(rects)
+                            boundingboxes = boundingboxes.astype(int)
+                            rects = non_max_suppression_fast(boundingboxes, 0.3)
+
+                            objects = tracker.update(rects)
+                            for (objectId, bbox) in objects.items():
+                                x1, y1, x2, y2 = bbox
+                                x1 = int(x1)
+                                y1 = int(y1)
+                                x2 = int(x2)
+                                y2 = int(y2)
+
+                                cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 0, 255), 2)
+                                text = "ID: {}".format(objectId)
+                                # print(text)
+                                cv2.putText(frame, text, (x1, y1-5), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 255), 1)
+                                if objectId not in object_id_list:
+                                    object_id_list.append(objectId)
+                            fps_end_time = datetime.datetime.now()
+                            time_diff = fps_end_time - fps_start_time
+                            if time_diff.seconds == 0:
+                                fps = 0.0
+                            else:
+                                fps = (total_frames / time_diff.seconds)
+
+                            fps_text = "FPS: {:.2f}".format(fps)
+
+                            cv2.putText(frame, fps_text, (5, 30), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 255), 1)
+                            lpc_count = len(objects)
+                            opc_count = len(object_id_list)
+
+                            lpc_txt = "LPC: {}".format(lpc_count)
+                            opc_txt = "OPC: {}".format(opc_count)
+                            
+                            count += 1
+                            if count % 4 != 0:
+                                continue
+                            # frame=cv.resize(frame, (600,500))
+                            # cv2.line(frame, pt1, pt2,color,2)
+                            # cv2.line(frame, pt3, pt4,color,2)
+                            results = model(frame,size)
+                            components = results.pandas().xyxy[0]
+                            for index, row in results.pandas().xyxy[0].iterrows():
+                                x1 = int(row['xmin'])
+                                y1 = int(row['ymin'])
+                                x2 = int(row['xmax'])
+                                y2 = int(row['ymax'])
+                                confidence  = (row['confidence'])
+                                obj = (row['class'])
+
+                                
+                                # min':x1,'ymin':y1,'xmax':x2,'ymax':y2,'confidence':confidence,'Object':obj}
+                                # if lpc_txt is not None:
+                                # 	try:
+                                # 		db["student Count"] = [lpc_txt]
+                                # 	except:
+                                # 		db["student Count"] = ['N/A']
+                                if obj == 0:
+                                    cv2.rectangle(frame,(x1,y1),(x2,y2),(0,0,255),2)
+                                    rectx1,recty1 = ((x1+x2)/2,(y1+y2)/2)
+                                    rectcenter = int(rectx1),int(recty1)
+                                    cx = rectcenter[0]
+                                    cy = rectcenter[1]
+                                    cv2.circle(frame,(cx,cy),3,(0,255,0),-1)
+                                    cv2.putText(frame,str(b), (x1,y1), cv2.FONT_HERSHEY_PLAIN,2,(255,255,255),2)
+                                    
+                                    db["student Count"] = [lpc_txt]
+                                    db['Date'] = [date_time]
+                                    db['id'] = ['N/A']
+                                    db['Mobile']=['N/A']
+                                    db['Watch'] = ['N/A']
+                                    if cy<(cy1+offset) and cy>(cy1-offset):
+                                        DB = []
+                                        counter+=1
+                                        DB.append(counter)
+
+                                        ff = DB[-1]
+                                        fx = str(ff)
+                                        # cv2.line(frame, pt1, pt2,(0, 0, 255),2)
+                                        # if cy<(cy2+offset) and cy>(cy2-offset):
+
+                                        # cv2.line(frame, pt3, pt4,(0, 0, 255),2)
+                                        font = cv2.FONT_HERSHEY_TRIPLEX
+                                        cv2.putText(frame,fx,(50, 50),font, 1,(0, 0, 255),2,cv2.LINE_4)
+                                        cv2.putText(frame,"Movement",(70, 70),font, 1,(0, 0, 255),2,cv2.LINE_4)
+                                        kpil2_text.write(f"<h5 style='text-align: left; color:red;'>{text}</h5>", unsafe_allow_html=True)
+                                        
+                                        
+                                        db['id'] = [text]
+                                        # myScreenshot = pyautogui.screenshot()
+                                        # if st.buttn("Dowload ss"):
+                                        #     myScreenshot.save(r'name.png')   
+                                        # myScreenshot.save(r'/home/anas/PersonTracking/AIComputerVision-master/pages/name.png')
+                                if obj == 67:
+                                    cv2.rectangle(frame,(x1,y1),(x2,y2),(0,0,255),2)
+                                    rectx1,recty1 = ((x1+x2)/2,(y1+y2)/2)
+                                    rectcenter = int(rectx1),int(recty1)
+                                    cx = rectcenter[0]
+                                    cy = rectcenter[1]
+                                    cv2.circle(frame,(cx,cy),3,(0,255,0),-1)
+                                    cv2.putText(frame,str(mobile), (x1,y1), cv2.FONT_HERSHEY_PLAIN,2,(255,255,255),2)
+                                    cv2.putText(frame,'Mobile',(50, 50),cv2.FONT_HERSHEY_PLAIN, 1,(0, 0, 255),2,cv2.LINE_4)
+                                    kpil3_text.write(f"<h5 style='text-align: left; color:red;'>{mobile}{text}</h5>", unsafe_allow_html=True)
+                                    
+                                    db['Mobile']=mobile+' '+text
+                                    # myScreenshot = pyautogui.screenshot()
+                                    # if st.buttn("Dowload ss"):
+                                    # myScreenshot.save(r'/home/anas/PersonTracking/AIComputerVision-master/pages/name.png')
+                                    # myScreenshot.save(r'name.png')     
+                                    
+                                if obj == 75:
+                                    cv2.rectangle(frame,(x1,y1),(x2,y2),(0,0,255),2)
+                                    rectx1,recty1 = ((x1+x2)/2,(y1+y2)/2)
+                                    rectcenter = int(rectx1),int(recty1)
+                                    cx = rectcenter[0]
+                                    cy = rectcenter[1]
+                                    cv2.circle(frame,(cx,cy),3,(0,255,0),-1)
+                                    cv2.putText(frame,str(watch), (x1,y1), cv2.FONT_HERSHEY_PLAIN,2,(255,255,255),2)
+                                    cv2.putText(frame,'Watch',(50, 50),cv2.FONT_HERSHEY_PLAIN, 1,(0, 0, 255),2,cv2.LINE_4)
+                                    kpil6_text.write(f"<h5 style='text-align: left; color:red;'>{watch}</h5>", unsafe_allow_html=True)
+                                    
+                                    
+                                    db['Watch']=watch
+                                    myScreenshot = pyautogui.screenshot()
+                                    # if st.buttn("Dowload ss"):
+                                            # myScreenshot.save(r'/home/anas/PersonTracking/AIComputerVision-master/pages/name.png')
+                                    # myScreenshot.save(r'name.png')  
+                                
+                                    
+                            
+                            kpil_text.write(f"<h5 style='text-align: left; color:red;'>{int(fps)}</h5>", unsafe_allow_html=True)
+                            kpil5_text.write(f"<h5 style='text-align: left; color:red;'>{lpc_txt}</h5>", unsafe_allow_html=True)
+                            kpil6_text.write(f"<h5 style='text-align: left; color:red;'>{width*height}</h5>",
+                                            unsafe_allow_html=True)
+                            
+            
+                            frame = cv.resize(frame,(0,0), fx=0.8, fy=0.8)
+                            frame = image_resize(image=frame, width=640)
+                            stframe.image(frame,channels='BGR', use_column_width=True)
+                            df = pd.DataFrame(db)
+                            df.to_csv('final.csv',mode='a',header=False,index=False)
+                    except:
+                        pass
+                    with open('final.csv') as f:
+                        st.download_button(label = 'Download Cheating Report',data=f,file_name='data.csv')
+                        
+                    os.remove("final.csv")
+            main()

pages/LoginStatus.csv

@@ -0,0 +1,3 @@
+Id,Password
+,gjk
+yg,ghhg

pages/hashed_pw.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec0a6ccf9debf1c16781445c4b9106080d00478b0559469336db7c7b7b9711c8
+size 5

pages/signup.py

@@ -0,0 +1,81 @@
+import pickle
+from pathlib import Path
+import streamlit as st
+import os
+import pandas as pd 
+import csv 
+data = ['Id','Password']
+
+# with open('LoginStatus.csv', 'w') as file:
+#     writer = csv.writer(file)
+#     writer.writerow(data)
+db = {}
+
+l1 = []
+l2 = []
+ids = st.text_input("Email Address")
+password = st.text_input("Password",type="password",key="password")
+# l1.append(ids)
+# l2.append(password)
+
+# l1.append(ids)
+# l2.append(password)
+key1 = "Id"
+db.setdefault(key1, [])
+db[key1].append(ids)
+
+key2 = "password"
+db.setdefault(key2, [])
+db[key2].append(password)
+
+# print(db)
+# db['Id'] = l1
+# db['Password'] = l2
+# for i in db:
+df = pd.DataFrame(db)
+# st.write(db)
+# df
+if st.button("Add Data"):
+    df.to_csv('LoginStatus.csv', mode='a', header=False, index=False)
+
+    
+
+# import streamlit as st
+# def check_password():
+#     """Returns `True` if the user had a correct password."""
+
+#     def password_entered():
+#         """Checks whether a password entered by the user is correct."""
+#         if (
+#             st.session_state["username"] in st.secrets["passwords"]
+#             and st.session_state["password"]
+#             == st.secrets["passwords"][st.session_state["username"]]
+#         ):
+#             st.session_state["password_correct"] = True
+#             del st.session_state["password"]  # don't store username + password
+#             del st.session_state["username"]
+#         else:
+#             st.session_state["password_correct"] = False
+
+#     if "password_correct" not in st.session_state:
+#         # First run, show inputs for username + password.
+#         st.text_input("Username", on_change=password_entered, key="username")
+#         st.text_input(
+#             "Password", type="password", on_change=password_entered, key="password"
+#         )
+#         return False
+#     elif not st.session_state["password_correct"]:
+#         # Password not correct, show input + error.
+#         st.text_input("Username", on_change=password_entered, key="username")
+#         st.text_input(
+#             "Password", type="password", on_change=password_entered, key="password"
+#         )
+#         st.error("😕 User not known or password incorrect")
+#         return False
+#     else:
+#         # Password correct.
+#         return True
+
+# if check_password():
+#     st.write("Here goes your normal Streamlit app...")
+#     st.button("Click me")

person_counter.py

@@ -0,0 +1,143 @@
+import cv2
+import datetime
+import imutils
+import numpy as np
+from centroidtracker import CentroidTracker
+
+protopath = "MobileNetSSD_deploy.prototxt"
+modelpath = "MobileNetSSD_deploy.caffemodel"
+detector = cv2.dnn.readNetFromCaffe(prototxt=protopath, caffeModel=modelpath)
+detector.setPreferableBackend(cv2.dnn.DNN_BACKEND_INFERENCE_ENGINE)
+detector.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU)
+
+
+CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
+           "bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
+           "dog", "horse", "motorbike", "person", "pottedplant", "sheep",
+           "sofa", "train", "tvmonitor"]
+
+tracker = CentroidTracker(maxDisappeared=80, maxDistance=90)
+
+
+def non_max_suppression_fast(boxes, overlapThresh):
+    try:
+        if len(boxes) == 0:
+            return []
+
+        if boxes.dtype.kind == "i":
+            boxes = boxes.astype("float")
+
+        pick = []
+
+        x1 = boxes[:, 0]
+        y1 = boxes[:, 1]
+        x2 = boxes[:, 2]
+        y2 = boxes[:, 3]
+
+        area = (x2 - x1 + 1) * (y2 - y1 + 1)
+        idxs = np.argsort(y2)
+
+        while len(idxs) > 0:
+            last = len(idxs) - 1
+            i = idxs[last]
+            pick.append(i)
+
+            xx1 = np.maximum(x1[i], x1[idxs[:last]])
+            yy1 = np.maximum(y1[i], y1[idxs[:last]])
+            xx2 = np.minimum(x2[i], x2[idxs[:last]])
+            yy2 = np.minimum(y2[i], y2[idxs[:last]])
+
+            w = np.maximum(0, xx2 - xx1 + 1)
+            h = np.maximum(0, yy2 - yy1 + 1)
+
+            overlap = (w * h) / area[idxs[:last]]
+
+            idxs = np.delete(idxs, np.concatenate(([last],
+                                                   np.where(overlap > overlapThresh)[0])))
+
+        return boxes[pick].astype("int")
+    except Exception as e:
+        print("Exception occurred in non_max_suppression : {}".format(e))
+
+
+def main():
+    cap = cv2.VideoCapture('test_video.mp4')
+
+    fps_start_time = datetime.datetime.now()
+    fps = 0
+    total_frames = 0
+    lpc_count = 0
+    opc_count = 0
+    object_id_list = []
+    while True:
+        ret, frame = cap.read()
+        frame = imutils.resize(frame, width=600)
+        total_frames = total_frames + 1
+
+        (H, W) = frame.shape[:2]
+
+        blob = cv2.dnn.blobFromImage(frame, 0.007843, (W, H), 127.5)
+
+        detector.setInput(blob)
+        person_detections = detector.forward()
+        rects = []
+        for i in np.arange(0, person_detections.shape[2]):
+            confidence = person_detections[0, 0, i, 2]
+            if confidence > 0.5:
+                idx = int(person_detections[0, 0, i, 1])
+
+                if CLASSES[idx] != "person":
+                    continue
+
+                person_box = person_detections[0, 0, i, 3:7] * np.array([W, H, W, H])
+                (startX, startY, endX, endY) = person_box.astype("int")
+                rects.append(person_box)
+
+        boundingboxes = np.array(rects)
+        boundingboxes = boundingboxes.astype(int)
+        rects = non_max_suppression_fast(boundingboxes, 0.3)
+
+        objects = tracker.update(rects)
+        for (objectId, bbox) in objects.items():
+            x1, y1, x2, y2 = bbox
+            x1 = int(x1)
+            y1 = int(y1)
+            x2 = int(x2)
+            y2 = int(y2)
+
+            cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 0, 255), 2)
+            text = "ID: {}".format(objectId)
+            cv2.putText(frame, text, (x1, y1-5), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 255), 1)
+
+            if objectId not in object_id_list:
+                object_id_list.append(objectId)
+
+        fps_end_time = datetime.datetime.now()
+        time_diff = fps_end_time - fps_start_time
+        if time_diff.seconds == 0:
+            fps = 0.0
+        else:
+            fps = (total_frames / time_diff.seconds)
+
+        fps_text = "FPS: {:.2f}".format(fps)
+
+        cv2.putText(frame, fps_text, (5, 30), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 255), 1)
+
+        lpc_count = len(objects)
+        opc_count = len(object_id_list)
+
+        lpc_txt = "LPC: {}".format(lpc_count)
+        opc_txt = "OPC: {}".format(opc_count)
+
+        cv2.putText(frame, lpc_txt, (5, 60), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 255), 1)
+        cv2.putText(frame, opc_txt, (5, 90), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 255), 1)
+
+        cv2.imshow("Application", frame)
+        key = cv2.waitKey(1)
+        if key == ord('q'):
+            break
+
+    cv2.destroyAllWindows()
+
+
+main()

person_detection_image.py

@@ -0,0 +1,43 @@
+import cv2
+import numpy as np
+import imutils
+
+protopath = "MobileNetSSD_deploy.prototxt"
+modelpath = "MobileNetSSD_deploy.caffemodel"
+detector = cv2.dnn.readNetFromCaffe(prototxt=protopath, caffeModel=modelpath)
+
+CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
+           "bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
+           "dog", "horse", "motorbike", "person", "pottedplant", "sheep",
+           "sofa", "train", "tvmonitor"]
+
+
+def main():
+    image = cv2.imread('people.jpg')
+    image = imutils.resize(image, width=600)
+
+    (H, W) = image.shape[:2]
+
+    blob = cv2.dnn.blobFromImage(image, 0.007843, (W, H), 127.5)
+
+    detector.setInput(blob)
+    person_detections = detector.forward()
+
+    for i in np.arange(0, person_detections.shape[2]):
+        confidence = person_detections[0, 0, i, 2]
+        if confidence > 0.5:
+            idx = int(person_detections[0, 0, i, 1])
+
+            if CLASSES[idx] != "person":
+                continue
+
+            person_box = person_detections[0, 0, i, 3:7] * np.array([W, H, W, H])
+            (startX, startY, endX, endY) = person_box.astype("int")
+
+            cv2.rectangle(image, (startX, startY), (endX, endY), (0, 0, 255), 2)
+
+    cv2.imshow("Results", image)
+    cv2.waitKey(0)
+    cv2.destroyAllWindows()
+
+main()

person_detection_video.py

@@ -0,0 +1,71 @@
+import cv2
+import datetime
+import imutils
+import numpy as np
+
+protopath = "MobileNetSSD_deploy.prototxt"
+modelpath = "MobileNetSSD_deploy.caffemodel"
+detector = cv2.dnn.readNetFromCaffe(prototxt=protopath, caffeModel=modelpath)
+# Only enable it if you are using OpenVino environment
+# detector.setPreferableBackend(cv2.dnn.DNN_BACKEND_INFERENCE_ENGINE)
+# detector.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU)
+
+
+CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
+           "bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
+           "dog", "horse", "motorbike", "person", "pottedplant", "sheep",
+           "sofa", "train", "tvmonitor"]
+
+
+def main():
+    cap = cv2.VideoCapture('test_video.mp4')
+
+    fps_start_time = datetime.datetime.now()
+    fps = 0
+    total_frames = 0
+
+    while True:
+        ret, frame = cap.read()
+        frame = imutils.resize(frame, width=600)
+        total_frames = total_frames + 1
+
+        (H, W) = frame.shape[:2]
+
+        blob = cv2.dnn.blobFromImage(frame, 0.007843, (W, H), 127.5)
+
+        detector.setInput(blob)
+        person_detections = detector.forward()
+
+        for i in np.arange(0, person_detections.shape[2]):
+            confidence = person_detections[0, 0, i, 2]
+            if confidence > 0.5:
+                idx = int(person_detections[0, 0, i, 1])
+
+                if CLASSES[idx] != "person":
+                    continue
+
+                person_box = person_detections[0, 0, i, 3:7] * np.array([W, H, W, H])
+                (startX, startY, endX, endY) = person_box.astype("int")
+
+                cv2.rectangle(frame, (startX, startY), (endX, endY), (0, 0, 255), 2)
+
+        fps_end_time = datetime.datetime.now()
+        time_diff = fps_end_time - fps_start_time
+        if time_diff.seconds == 0:
+            fps = 0.0
+        else:
+            fps = (total_frames / time_diff.seconds)
+
+        fps_text = "FPS: {:.2f}".format(fps)
+
+        cv2.putText(frame, fps_text, (5, 30), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 255), 1)
+
+        cv2.imshow("Application", frame)
+        key = cv2.waitKey(1)
+        if key == ord('q'):
+            break
+
+    cv2.destroyAllWindows()
+
+
+main()

person_tracking.py

@@ -0,0 +1,542 @@
+import cv2
+import datetime
+import imutils
+import numpy as np
+from centroidtracker import CentroidTracker
+import pandas as pd 
+import torch 
+import streamlit as st
+import mediapipe as mp
+import cv2 as cv
+import numpy as np
+import tempfile
+import time
+from PIL import Image
+import pandas as pd
+import torch
+import base64
+import streamlit.components.v1 as components
+import csv
+import pickle
+from pathlib import Path
+import streamlit_authenticator as stauth
+import os
+import csv
+#  x-x-x-x-x-x-x-x-x-x-x-x-x-x LOGIN FORM x-x-x-x-x-x-x-x-x
+
+                                
+import streamlit as st
+import pandas as pd
+import hashlib
+import sqlite3 
+#
+
+import pickle
+from pathlib import Path
+import streamlit_authenticator as stauth
+# print("Done !!!")
+
+data = ["student Count",'Date','Id','Mobile','Watch']
+with open('final.csv', 'w') as file:
+    writer = csv.writer(file)
+    writer.writerow(data)
+    
+
+l1 = []
+l2 = []
+if st.button('signup'):
+    
+    
+    usernames = st.text_input('Username')
+    pwd = st.text_input('Password') 
+    l1.append(usernames)
+    l2.append(pwd)
+
+    names = ["dmin", "ser"]
+    if st.button("signupsss"):
+        username =l1
+
+        password =l2
+
+        hashed_passwords =stauth.Hasher(password).generate()
+
+        file_path = Path(__file__).parent / "hashed_pw.pkl"
+
+        with file_path.open("wb") as file:
+            pickle.dump(hashed_passwords, file)
+            
+    
+elif st.button('Logins'):
+    names = ['dmin', 'ser']
+
+    username =l1
+
+    file_path = Path(__file__).parent / 'hashed_pw.pkl'
+
+    with file_path.open('rb') as file:
+        hashed_passwords = pickle.load(file)
+
+    authenticator = stauth.Authenticate(names,username,hashed_passwords,'Cheating Detection','abcdefg',cookie_expiry_days=180)
+
+    name,authentication_status,username= authenticator.login('Login','main')
+
+
+    if authentication_status == False:
+        st.error('Username/Password is incorrect')
+        
+    if authentication_status == None:
+        st.error('Please enter a username and password')
+        
+    if authentication_status:
+        date_time = time.strftime("%b %d %Y %-I:%M %p")
+        date = date_time.split()
+        dates = date[0:3]
+        times = date[3:5]
+        # x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-xAPPLICACTION -x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x-x
+
+        def non_max_suppression_fast(boxes, overlapThresh):
+            try:
+                if len(boxes) == 0:
+                    return []
+
+                if boxes.dtype.kind == "i":
+                    boxes = boxes.astype("float")
+
+                pick = []
+
+                x1 = boxes[:, 0]
+                y1 = boxes[:, 1]
+                x2 = boxes[:, 2]
+                y2 = boxes[:, 3]
+
+                area = (x2 - x1 + 1) * (y2 - y1 + 1)
+                idxs = np.argsort(y2)
+
+                while len(idxs) > 0:
+                    last = len(idxs) - 1
+                    i = idxs[last]
+                    pick.append(i)
+
+                    xx1 = np.maximum(x1[i], x1[idxs[:last]])
+                    yy1 = np.maximum(y1[i], y1[idxs[:last]])
+                    xx2 = np.minimum(x2[i], x2[idxs[:last]])
+                    yy2 = np.minimum(y2[i], y2[idxs[:last]])
+
+                    w = np.maximum(0, xx2 - xx1 + 1)
+                    h = np.maximum(0, yy2 - yy1 + 1)
+
+                    overlap = (w * h) / area[idxs[:last]]
+
+                    idxs = np.delete(idxs, np.concatenate(([last],
+                                                        np.where(overlap > overlapThresh)[0])))
+
+                return boxes[pick].astype("int")
+            except Exception as e:
+                print("Exception occurred in non_max_suppression : {}".format(e))
+
+
+        protopath = "MobileNetSSD_deploy.prototxt"
+        modelpath = "MobileNetSSD_deploy.caffemodel"
+        detector = cv2.dnn.readNetFromCaffe(prototxt=protopath, caffeModel=modelpath)
+        # Only enable it if you are using OpenVino environment
+        # detector.setPreferableBackend(cv2.dnn.DNN_BACKEND_INFERENCE_ENGINE)
+        # detector.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU)
+
+
+        CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
+                "bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
+                "dog", "horse", "motorbike", "person", "pottedplant", "sheep",
+                "sofa", "train", "tvmonitor"]
+
+        tracker = CentroidTracker(maxDisappeared=80, maxDistance=90)
+
+        st.markdown(
+            """
+            <style>
+            [data-testid="stSidebar"][aria-expanded="true"] > div:first-child{
+                width: 350px
+            }
+            [data-testid="stSidebar"][aria-expanded="false"] > div:first-child{
+                width: 350px
+                margin-left: -350px
+            }
+            </style>
+            """,
+            unsafe_allow_html=True,
+        )
+        hide_streamlit_style = """
+                <style>
+                #MainMenu {visibility: hidden;}
+                footer {visibility: hidden;}
+                </style>
+                """
+        st.markdown(hide_streamlit_style, unsafe_allow_html=True)
+
+
+        # Resize Images to fit Container
+        @st.cache()
+        # Get Image Dimensions
+        def image_resize(image, width=None, height=None, inter=cv.INTER_AREA):
+            dim = None
+            (h,w) = image.shape[:2]
+
+            if width is None and height is None:
+                return image
+
+            if width is None:
+                r = width/float(w)
+                dim = (int(w*r),height)
+
+            else:
+                r = width/float(w)
+                dim = width, int(h*r)
+
+            # Resize image
+            resized = cv.resize(image,dim,interpolation=inter)
+
+            return resized
+                
+        # About Page
+        authenticator.logout('Logout')
+        app_mode = st.sidebar.selectbox(
+                        'App Mode',
+                        ['About','Application']
+                        )
+        if app_mode == 'About':
+            st.title('About Product And Team')
+            st.markdown('''
+                        Imran Bhai Project
+            ''')
+            st.markdown(
+                """
+                <style>
+                [data-testid="stSidebar"][aria-expanded="true"] > div:first-child{
+                    width: 350px
+                }
+                [data-testid="stSidebar"][aria-expanded="false"] > div:first-child{
+                    width: 350px
+                    margin-left: -350px
+                }
+                </style>
+                """,
+                unsafe_allow_html=True,
+            )
+
+            
+
+
+        elif app_mode == 'Application':
+            
+            st.set_option('deprecation.showfileUploaderEncoding', False)
+
+            use_webcam = st.button('Use Webcam')
+            # record = st.sidebar.checkbox("Record Video")
+
+            # if record:
+            #     st.checkbox('Recording', True)
+
+            # drawing_spec = mp.solutions.drawing_utils.DrawingSpec(thickness=2, circle_radius=1)
+
+            # st.sidebar.markdown('---')
+
+            # ## Add Sidebar and Window style
+            # st.markdown(
+            #     """
+            #     <style>
+            #     [data-testid="stSidebar"][aria-expanded="true"] > div:first-child{
+            #         width: 350px
+            #     }
+            #     [data-testid="stSidebar"][aria-expanded="false"] > div:first-child{
+            #         width: 350px
+            #         margin-left: -350px
+            #     }
+            #     </style>
+            #     """,
+            #     unsafe_allow_html=True,
+            # )
+
+            # max_faces = st.sidebar.number_input('Maximum Number of Faces', value=5, min_value=1)
+            # st.sidebar.markdown('---')
+            # detection_confidence = st.sidebar.slider('Min Detection Confidence', min_value=0.0,max_value=1.0,value=0.5)
+            # tracking_confidence = st.sidebar.slider('Min Tracking Confidence', min_value=0.0,max_value=1.0,value=0.5)
+            # st.sidebar.markdown('---')
+
+            ## Get Video
+            stframe = st.empty()
+            video_file_buffer = st.file_uploader("Upload a Video", type=['mp4', 'mov', 'avi', 'asf', 'm4v'])
+            temp_file = tempfile.NamedTemporaryFile(delete=False)
+
+            
+            if not video_file_buffer:
+                if use_webcam:
+                    video = cv.VideoCapture(0)
+                else:
+                    try:
+                        video = cv.VideoCapture(1)
+                        temp_file.name = video
+                    except:
+                        pass
+            else:
+                temp_file.write(video_file_buffer.read())
+                video = cv.VideoCapture(temp_file.name)
+
+            width = int(video.get(cv.CAP_PROP_FRAME_WIDTH))
+            height = int(video.get(cv.CAP_PROP_FRAME_HEIGHT))
+            fps_input = int(video.get(cv.CAP_PROP_FPS))
+
+            ## Recording
+            codec = cv.VideoWriter_fourcc('a','v','c','1')
+            out = cv.VideoWriter('output1.mp4', codec, fps_input, (width,height))
+
+            st.sidebar.text('Input Video')
+            # st.sidebar.video(temp_file.name)
+
+            fps = 0
+            i = 0
+
+            drawing_spec = mp.solutions.drawing_utils.DrawingSpec(thickness=2, circle_radius=1)
+
+            kpil, kpil2, kpil3,kpil4,kpil5, kpil6 = st.columns(6)
+
+            with kpil:
+                st.markdown('**Frame Rate**')
+                kpil_text = st.markdown('0')
+
+            with kpil2:
+                st.markdown('**detection ID**')
+                kpil2_text = st.markdown('0')
+
+            with kpil3:
+                st.markdown('**Mobile**')
+                kpil3_text = st.markdown('0')
+            with kpil4:
+                st.markdown('**Watch**')
+                kpil4_text = st.markdown('0')
+            with kpil5:
+                st.markdown('**Count**')
+                kpil5_text = st.markdown('0')
+            with kpil6:
+                st.markdown('**Img Res**')
+                kpil6_text = st.markdown('0')
+            
+
+
+            st.markdown('<hr/>', unsafe_allow_html=True)
+            # try:
+            def main():
+                db = {}
+                
+                # cap = cv2.VideoCapture('//home//anas//PersonTracking//WebUI//movement.mp4')
+                path='/usr/local/lib/python3.10/dist-packages/yolo0vs5/yolov5s-int8.tflite'
+                #count=0
+                custom = 'yolov5s'
+
+                model = torch.hub.load('/usr/local/lib/python3.10/dist-packages/yolovs5', custom, path,source='local',force_reload=True)
+
+                b=model.names[0] = 'person'
+                mobile = model.names[67] = 'cell phone'
+                watch = model.names[75] = 'clock'
+
+                fps_start_time = datetime.datetime.now()
+                fps = 0
+                size=416
+
+                count=0
+                counter=0
+
+
+                color=(0,0,255)
+
+                cy1=250
+                offset=6
+
+
+                pt1 = (120, 100)
+                pt2 = (980, 1150)
+                color = (0, 255, 0)
+
+                pt3 = (283, 103)
+                pt4 = (1500, 1150)
+                
+                cy2 = 500
+                color = (0, 255, 0)
+                total_frames = 0
+                prevTime = 0
+                cur_frame = 0
+                count=0
+                counter=0
+                fps_start_time = datetime.datetime.now()
+                fps = 0
+                total_frames = 0
+                lpc_count = 0
+                opc_count = 0
+                object_id_list = []
+                # success = True
+                if st.button("Detect"):
+                    try:
+                        while video.isOpened():
+                            
+                            ret, frame = video.read()
+                            frame = imutils.resize(frame, width=600)
+                            total_frames = total_frames + 1
+
+                            (H, W) = frame.shape[:2]
+
+                            blob = cv2.dnn.blobFromImage(frame, 0.007843, (W, H), 127.5)
+
+                            detector.setInput(blob)
+                            person_detections = detector.forward()
+                            rects = []
+                            for i in np.arange(0, person_detections.shape[2]):
+                                confidence = person_detections[0, 0, i, 2]
+                                if confidence > 0.5:
+                                    idx = int(person_detections[0, 0, i, 1])
+
+                                    if CLASSES[idx] != "person":
+                                        continue
+
+                                    person_box = person_detections[0, 0, i, 3:7] * np.array([W, H, W, H])
+                                    (startX, startY, endX, endY) = person_box.astype("int")
+                                    rects.append(person_box)
+
+                            boundingboxes = np.array(rects)
+                            boundingboxes = boundingboxes.astype(int)
+                            rects = non_max_suppression_fast(boundingboxes, 0.3)
+
+                            objects = tracker.update(rects)
+                            for (objectId, bbox) in objects.items():
+                                x1, y1, x2, y2 = bbox
+                                x1 = int(x1)
+                                y1 = int(y1)
+                                x2 = int(x2)
+                                y2 = int(y2)
+
+                                cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 0, 255), 2)
+                                text = "ID: {}".format(objectId)
+                                # print(text)
+                                cv2.putText(frame, text, (x1, y1-5), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 255), 1)
+                                if objectId not in object_id_list:
+                                    object_id_list.append(objectId)
+                            fps_end_time = datetime.datetime.now()
+                            time_diff = fps_end_time - fps_start_time
+                            if time_diff.seconds == 0:
+                                fps = 0.0
+                            else:
+                                fps = (total_frames / time_diff.seconds)
+
+                            fps_text = "FPS: {:.2f}".format(fps)
+
+                            cv2.putText(frame, fps_text, (5, 30), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 255), 1)
+                            lpc_count = len(objects)
+                            opc_count = len(object_id_list)
+
+                            lpc_txt = "LPC: {}".format(lpc_count)
+                            opc_txt = "OPC: {}".format(opc_count)
+                            
+                            count += 1
+                            if count % 4 != 0:
+                                continue
+                            # frame=cv.resize(frame, (600,500))
+                            # cv2.line(frame, pt1, pt2,color,2)
+                            # cv2.line(frame, pt3, pt4,color,2)
+                            results = model(frame,size)
+                            components = results.pandas().xyxy[0]
+                            for index, row in results.pandas().xyxy[0].iterrows():
+                                x1 = int(row['xmin'])
+                                y1 = int(row['ymin'])
+                                x2 = int(row['xmax'])
+                                y2 = int(row['ymax'])
+                                confidence  = (row['confidence'])
+                                obj = (row['class'])
+
+                                
+                                # min':x1,'ymin':y1,'xmax':x2,'ymax':y2,'confidence':confidence,'Object':obj}
+                                # if lpc_txt is not None:
+                                # 	try:
+                                # 		db["student Count"] = [lpc_txt]
+                                # 	except:
+                                # 		db["student Count"] = ['N/A']
+                                if obj == 0:
+                                    cv2.rectangle(frame,(x1,y1),(x2,y2),(0,0,255),2)
+                                    rectx1,recty1 = ((x1+x2)/2,(y1+y2)/2)
+                                    rectcenter = int(rectx1),int(recty1)
+                                    cx = rectcenter[0]
+                                    cy = rectcenter[1]
+                                    cv2.circle(frame,(cx,cy),3,(0,255,0),-1)
+                                    cv2.putText(frame,str(b), (x1,y1), cv2.FONT_HERSHEY_PLAIN,2,(255,255,255),2)
+                                    
+                                    db["student Count"] = [lpc_txt]
+                                    db['Date'] = [date_time]
+                                    db['id'] = ['N/A']
+                                    db['Mobile']=['N/A']
+                                    db['Watch'] = ['N/A']
+                                    if cy<(cy1+offset) and cy>(cy1-offset):
+                                        DB = []
+                                        counter+=1
+                                        DB.append(counter)
+
+                                        ff = DB[-1]
+                                        fx = str(ff)
+                                        # cv2.line(frame, pt1, pt2,(0, 0, 255),2)
+                                        # if cy<(cy2+offset) and cy>(cy2-offset):
+
+                                        # cv2.line(frame, pt3, pt4,(0, 0, 255),2)
+                                        font = cv2.FONT_HERSHEY_TRIPLEX
+                                        cv2.putText(frame,fx,(50, 50),font, 1,(0, 0, 255),2,cv2.LINE_4)
+                                        cv2.putText(frame,"Movement",(70, 70),font, 1,(0, 0, 255),2,cv2.LINE_4)
+                                        kpil2_text.write(f"<h5 style='text-align: left; color:red;'>{text}</h5>", unsafe_allow_html=True)
+                                        
+                                        
+                                        db['id'] = [text]
+                                        
+                                            
+                                        
+                                if obj == 67:
+                                    cv2.rectangle(frame,(x1,y1),(x2,y2),(0,0,255),2)
+                                    rectx1,recty1 = ((x1+x2)/2,(y1+y2)/2)
+                                    rectcenter = int(rectx1),int(recty1)
+                                    cx = rectcenter[0]
+                                    cy = rectcenter[1]
+                                    cv2.circle(frame,(cx,cy),3,(0,255,0),-1)
+                                    cv2.putText(frame,str(mobile), (x1,y1), cv2.FONT_HERSHEY_PLAIN,2,(255,255,255),2)
+                                    cv2.putText(frame,'Mobile',(50, 50),cv2.FONT_HERSHEY_PLAIN, 1,(0, 0, 255),2,cv2.LINE_4)
+                                    kpil3_text.write(f"<h5 style='text-align: left; color:red;'>{mobile}{text}</h5>", unsafe_allow_html=True)
+                                    
+                                    db['Mobile']=mobile+' '+text
+                                    
+                                        
+                                    
+                                if obj == 75:
+                                    cv2.rectangle(frame,(x1,y1),(x2,y2),(0,0,255),2)
+                                    rectx1,recty1 = ((x1+x2)/2,(y1+y2)/2)
+                                    rectcenter = int(rectx1),int(recty1)
+                                    cx = rectcenter[0]
+                                    cy = rectcenter[1]
+                                    cv2.circle(frame,(cx,cy),3,(0,255,0),-1)
+                                    cv2.putText(frame,str(watch), (x1,y1), cv2.FONT_HERSHEY_PLAIN,2,(255,255,255),2)
+                                    cv2.putText(frame,'Watch',(50, 50),cv2.FONT_HERSHEY_PLAIN, 1,(0, 0, 255),2,cv2.LINE_4)
+                                    kpil6_text.write(f"<h5 style='text-align: left; color:red;'>{watch}</h5>", unsafe_allow_html=True)
+                                    
+                                    
+                                    db['Watch']=watch
+                                
+                                    
+                            
+                            kpil_text.write(f"<h5 style='text-align: left; color:red;'>{int(fps)}</h5>", unsafe_allow_html=True)
+                            kpil5_text.write(f"<h5 style='text-align: left; color:red;'>{lpc_txt}</h5>", unsafe_allow_html=True)
+                            kpil6_text.write(f"<h5 style='text-align: left; color:red;'>{width*height}</h5>",
+                                            unsafe_allow_html=True)
+                            
+            
+                            frame = cv.resize(frame,(0,0), fx=0.8, fy=0.8)
+                            frame = image_resize(image=frame, width=640)
+                            stframe.image(frame,channels='BGR', use_column_width=True)
+                            df = pd.DataFrame(db)
+                            df.to_csv('final.csv',mode='a',header=False,index=False)
+                    except:
+                        pass
+                    with open('final.csv') as f:
+                        st.download_button(label = 'Download Cheating Report',data=f,file_name='data.csv')
+                        
+                    os.remove("final.csv")
+            main()

requirements.txt

@@ -0,0 +1,120 @@
+absl-py==1.3.0
+altair==4.2.0
+asttokens==2.1.0
+astunparse==1.6.3
+attrs==22.1.0
+backcall==0.2.0
+bcrypt==4.0.1
+blinker==1.5
+cachetools==5.2.0
+centroid-tracker==0.0.9
+certifi==2022.9.24
+charset-normalizer==2.1.1
+click==8.1.3
+commonmark==0.9.1
+contourpy==1.0.6
+cvzone==1.5.6
+cycler==0.11.0
+decorator==5.1.1
+entrypoints==0.4
+executing==1.2.0
+extra-streamlit-components==0.1.56
+flatbuffers==22.11.23
+fonttools==4.38.0
+gast==0.4.0
+gitdb==4.0.9
+GitPython==3.1.29
+google-auth==2.14.1
+google-auth-oauthlib==0.4.6
+google-pasta==0.2.0
+grpcio==1.51.0
+h5py==3.7.0
+idna==3.4
+importlib-metadata==5.1.0
+imutils==0.5.4
+ipython==8.6.0
+jedi==0.18.2
+Jinja2==3.1.2
+jsonschema==4.17.1
+keras==2.11.0
+kiwisolver==1.4.4
+libclang==14.0.6
+Markdown==3.4.1
+MarkupSafe==2.1.1
+matplotlib==3.6.2
+matplotlib-inline==0.1.6
+mediapipe==0.9.0
+numpy==1.23.5
+nvidia-cublas-cu11==11.10.3.66
+nvidia-cuda-nvrtc-cu11==11.7.99
+nvidia-cuda-runtime-cu11==11.7.99
+nvidia-cudnn-cu11==8.5.0.96
+oauthlib==3.2.2
+opencv-contrib-python==4.6.0.66
+opencv-python==4.6.0.66
+opt-einsum==3.3.0
+packaging==21.3
+pafy==0.5.5
+pandas==1.5.1
+parso==0.8.3
+pexpect==4.8.0
+pickleshare==0.7.5
+Pillow==9.3.0
+prompt-toolkit==3.0.33
+protobuf==3.19.6
+psutil==5.9.4
+ptyprocess==0.7.0
+pure-eval==0.2.2
+pyarrow==10.0.1
+pyasn1==0.4.8
+pyasn1-modules==0.2.8
+pydeck==0.8.0
+Pygments==2.13.0
+PyJWT==2.6.0
+Pympler==1.0.1
+pyparsing==3.0.9
+pyrsistent==0.19.2
+python-dateutil==2.8.2
+pytz==2022.6
+pytz-deprecation-shim==0.1.0.post0
+PyYAML==6.0
+requests==2.28.1
+requests-oauthlib==1.3.1
+rich==12.6.0
+rsa==4.9
+scipy==1.9.3
+seaborn==0.12.1
+semver==2.13.0
+six==1.16.0
+smmap==5.0.0
+stack-data==0.6.1
+streamlit==1.15.1
+streamlit-authenticator==0.1.5
+streamlit-option-menu==0.3.2
+tensorboard==2.11.0
+tensorboard-data-server==0.6.1
+tensorboard-plugin-wit==1.8.1
+tensorflow==2.11.0
+tensorflow-estimator==2.11.0
+tensorflow-hub==0.12.0
+tensorflow-io-gcs-filesystem==0.28.0
+termcolor==2.1.1
+thop==0.1.1.post2209072238
+toml==0.10.2
+toolz==0.12.0
+torch==1.13.0
+torchvision==0.14.0
+tornado==6.2
+tqdm==4.64.1
+traitlets==5.5.0
+typing_extensions==4.4.0
+tzdata==2022.6
+tzlocal==4.2
+urllib3==1.26.12
+validators==0.20.0
+watchdog==2.1.9
+wcwidth==0.2.5
+Werkzeug==2.2.2
+wrapt==1.14.1
+youtube-dl==2020.12.2
+zipp==3.11.0

res10_300x300_ssd_iter_140000.caffemodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a56a11a57a4a295956b0660b4a3d76bbdca2206c4961cea8efe7d95c7cb2f2d
+size 10666211

social_distancing.py

@@ -0,0 +1,152 @@
+import cv2
+import datetime
+import imutils
+import numpy as np
+from centroidtracker import CentroidTracker
+from itertools import combinations
+import math
+
+protopath = "MobileNetSSD_deploy.prototxt"
+modelpath = "MobileNetSSD_deploy.caffemodel"
+detector = cv2.dnn.readNetFromCaffe(prototxt=protopath, caffeModel=modelpath)
+# detector.setPreferableBackend(cv2.dnn.DNN_BACKEND_INFERENCE_ENGINE)
+# detector.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU)
+
+
+CLASSES = ["background", "aeroplane", "bicycle", "bird", "boat",
+           "bottle", "bus", "car", "cat", "chair", "cow", "diningtable",
+           "dog", "horse", "motorbike", "person", "pottedplant", "sheep",
+           "sofa", "train", "tvmonitor"]
+
+tracker = CentroidTracker(maxDisappeared=40, maxDistance=50)
+
+
+def non_max_suppression_fast(boxes, overlapThresh):
+    try:
+        if len(boxes) == 0:
+            return []
+
+        if boxes.dtype.kind == "i":
+            boxes = boxes.astype("float")
+
+        pick = []
+
+        x1 = boxes[:, 0]
+        y1 = boxes[:, 1]
+        x2 = boxes[:, 2]
+        y2 = boxes[:, 3]
+
+        area = (x2 - x1 + 1) * (y2 - y1 + 1)
+        idxs = np.argsort(y2)
+
+        while len(idxs) > 0:
+            last = len(idxs) - 1
+            i = idxs[last]
+            pick.append(i)
+
+            xx1 = np.maximum(x1[i], x1[idxs[:last]])
+            yy1 = np.maximum(y1[i], y1[idxs[:last]])
+            xx2 = np.minimum(x2[i], x2[idxs[:last]])
+            yy2 = np.minimum(y2[i], y2[idxs[:last]])
+
+            w = np.maximum(0, xx2 - xx1 + 1)
+            h = np.maximum(0, yy2 - yy1 + 1)
+
+            overlap = (w * h) / area[idxs[:last]]
+
+            idxs = np.delete(idxs, np.concatenate(([last],
+                                                   np.where(overlap > overlapThresh)[0])))
+
+        return boxes[pick].astype("int")
+    except Exception as e:
+        print("Exception occurred in non_max_suppression : {}".format(e))
+
+
+def main():
+    cap = cv2.VideoCapture('testvideo2.mp4')
+
+    fps_start_time = datetime.datetime.now()
+    fps = 0
+    total_frames = 0
+
+    while True:
+        ret, frame = cap.read()
+        frame = imutils.resize(frame, width=600)
+        total_frames = total_frames + 1
+
+        (H, W) = frame.shape[:2]
+
+        blob = cv2.dnn.blobFromImage(frame, 0.007843, (W, H), 127.5)
+
+        detector.setInput(blob)
+        person_detections = detector.forward()
+        rects = []
+        for i in np.arange(0, person_detections.shape[2]):
+            confidence = person_detections[0, 0, i, 2]
+            if confidence > 0.5:
+                idx = int(person_detections[0, 0, i, 1])
+
+                if CLASSES[idx] != "person":
+                    continue
+
+                person_box = person_detections[0, 0, i, 3:7] * np.array([W, H, W, H])
+                (startX, startY, endX, endY) = person_box.astype("int")
+                rects.append(person_box)
+
+        boundingboxes = np.array(rects)
+        boundingboxes = boundingboxes.astype(int)
+        rects = non_max_suppression_fast(boundingboxes, 0.3)
+        centroid_dict = dict()
+        objects = tracker.update(rects)
+        for (objectId, bbox) in objects.items():
+            x1, y1, x2, y2 = bbox
+            x1 = int(x1)
+            y1 = int(y1)
+            x2 = int(x2)
+            y2 = int(y2)
+            cX = int((x1 + x2) / 2.0)
+            cY = int((y1 + y2) / 2.0)
+
+
+            centroid_dict[objectId] = (cX, cY, x1, y1, x2, y2)
+
+            # text = "ID: {}".format(objectId)
+            # cv2.putText(frame, text, (x1, y1-5), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 255), 1)
+
+        red_zone_list = []
+        for (id1, p1), (id2, p2) in combinations(centroid_dict.items(), 2):
+            dx, dy = p1[0] - p2[0], p1[1] - p2[1]
+            distance = math.sqrt(dx * dx + dy * dy)
+            if distance < 75.0:
+                if id1 not in red_zone_list:
+                    red_zone_list.append(id1)
+                if id2 not in red_zone_list:
+                    red_zone_list.append(id2)
+
+        for id, box in centroid_dict.items():
+            if id in red_zone_list:
+                cv2.rectangle(frame, (box[2], box[3]), (box[4], box[5]), (0, 0, 255), 2)
+            else:
+                cv2.rectangle(frame, (box[2], box[3]), (box[4], box[5]), (0, 255, 0), 2)
+
+
+        fps_end_time = datetime.datetime.now()
+        time_diff = fps_end_time - fps_start_time
+        if time_diff.seconds == 0:
+            fps = 0.0
+        else:
+            fps = (total_frames / time_diff.seconds)
+
+        fps_text = "FPS: {:.2f}".format(fps)
+
+        cv2.putText(frame, fps_text, (5, 30), cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 255), 1)
+
+        cv2.imshow("Application", frame)
+        key = cv2.waitKey(1)
+        if key == ord('q'):
+            break
+
+    cv2.destroyAllWindows()
+
+
+main()

test4.csv

@@ -0,0 +1,4 @@
+
+student Count,Date,id
+
+student Count,Date,id

test_video.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0ba636766524dd0bdfa52a2a62108aafb585acd138cb0e08226d12ae35b64c5
+size 27534166

video/mask.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dc1d0ed71d79c29eaa4b8503c829fcf7c840cab93756baabf97238f999432e6
+size 6143986

video/test_video.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0ba636766524dd0bdfa52a2a62108aafb585acd138cb0e08226d12ae35b64c5
+size 27534166

video/testvideo2.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15153e2c3d7221d693ec634e5288416fdc330427ccea9f4fc520a362977755e8
+size 5468270

yolov5s.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b3b748c1e592ddd8868022e8732fde20025197328490623cc16c6f24d0782ee
+size 14808437