Spaces:
Sleeping
Sleeping
File size: 14,856 Bytes
9b3f85e 932c8f4 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 |
COLORS = [
[0.000, 0.447, 0.741],
[0.850, 0.325, 0.098],
[0.929, 0.694, 0.125],
[0.494, 0.184, 0.556],
[0.466, 0.674, 0.188],
[0.301, 0.745, 0.933],
[0.351, 0.760, 0.903],
]
MODELS_DETAILS = {
"DETR-RESNET-50": """DetrForObjectDetection(
(model): DetrModel(
(backbone): DetrConvModel(
(conv_encoder): DetrConvEncoder(
(model): FeatureListNet(
(conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
(bn1): DetrFrozenBatchNorm2d()
(act1): ReLU(inplace=True)
(maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
(layer1): Sequential(
(0): Bottleneck(
(conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): DetrFrozenBatchNorm2d()
(act1): ReLU(inplace=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): DetrFrozenBatchNorm2d()
(drop_block): Identity()
(act2): ReLU(inplace=True)
(aa): Identity()
(conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): DetrFrozenBatchNorm2d()
(act3): ReLU(inplace=True)
(downsample): Sequential(
(0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): Bottleneck(
(conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): DetrFrozenBatchNorm2d()
(act1): ReLU(inplace=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): DetrFrozenBatchNorm2d()
(drop_block): Identity()
(act2): ReLU(inplace=True)
(aa): Identity()
(conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): DetrFrozenBatchNorm2d()
(act3): ReLU(inplace=True)
)
(2): Bottleneck(
(conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): DetrFrozenBatchNorm2d()
(act1): ReLU(inplace=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): DetrFrozenBatchNorm2d()
(drop_block): Identity()
(act2): ReLU(inplace=True)
(aa): Identity()
(conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): DetrFrozenBatchNorm2d()
(act3): ReLU(inplace=True)
)
)
(layer2): Sequential(
(0): Bottleneck(
(conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): DetrFrozenBatchNorm2d()
(act1): ReLU(inplace=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn2): DetrFrozenBatchNorm2d()
(drop_block): Identity()
(act2): ReLU(inplace=True)
(aa): Identity()
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): DetrFrozenBatchNorm2d()
(act3): ReLU(inplace=True)
(downsample): Sequential(
(0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): Bottleneck(
(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): DetrFrozenBatchNorm2d()
(act1): ReLU(inplace=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): DetrFrozenBatchNorm2d()
(drop_block): Identity()
(act2): ReLU(inplace=True)
(aa): Identity()
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): DetrFrozenBatchNorm2d()
(act3): ReLU(inplace=True)
)
(2): Bottleneck(
(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): DetrFrozenBatchNorm2d()
(act1): ReLU(inplace=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): DetrFrozenBatchNorm2d()
(drop_block): Identity()
(act2): ReLU(inplace=True)
(aa): Identity()
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): DetrFrozenBatchNorm2d()
(act3): ReLU(inplace=True)
)
(3): Bottleneck(
(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): DetrFrozenBatchNorm2d()
(act1): ReLU(inplace=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): DetrFrozenBatchNorm2d()
(drop_block): Identity()
(act2): ReLU(inplace=True)
(aa): Identity()
(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): DetrFrozenBatchNorm2d()
(act3): ReLU(inplace=True)
)
)
(layer3): Sequential(
(0): Bottleneck(
(conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): DetrFrozenBatchNorm2d()
(act1): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn2): DetrFrozenBatchNorm2d()
(drop_block): Identity()
(act2): ReLU(inplace=True)
(aa): Identity()
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): DetrFrozenBatchNorm2d()
(act3): ReLU(inplace=True)
(downsample): Sequential(
(0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): DetrFrozenBatchNorm2d()
(act1): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): DetrFrozenBatchNorm2d()
(drop_block): Identity()
(act2): ReLU(inplace=True)
(aa): Identity()
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): DetrFrozenBatchNorm2d()
(act3): ReLU(inplace=True)
)
(2): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): DetrFrozenBatchNorm2d()
(act1): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): DetrFrozenBatchNorm2d()
(drop_block): Identity()
(act2): ReLU(inplace=True)
(aa): Identity()
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): DetrFrozenBatchNorm2d()
(act3): ReLU(inplace=True)
)
(3): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): DetrFrozenBatchNorm2d()
(act1): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): DetrFrozenBatchNorm2d()
(drop_block): Identity()
(act2): ReLU(inplace=True)
(aa): Identity()
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): DetrFrozenBatchNorm2d()
(act3): ReLU(inplace=True)
)
(4): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): DetrFrozenBatchNorm2d()
(act1): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): DetrFrozenBatchNorm2d()
(drop_block): Identity()
(act2): ReLU(inplace=True)
(aa): Identity()
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): DetrFrozenBatchNorm2d()
(act3): ReLU(inplace=True)
)
(5): Bottleneck(
(conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): DetrFrozenBatchNorm2d()
(act1): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): DetrFrozenBatchNorm2d()
(drop_block): Identity()
(act2): ReLU(inplace=True)
(aa): Identity()
(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): DetrFrozenBatchNorm2d()
(act3): ReLU(inplace=True)
)
)
(layer4): Sequential(
(0): Bottleneck(
(conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): DetrFrozenBatchNorm2d()
(act1): ReLU(inplace=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn2): DetrFrozenBatchNorm2d()
(drop_block): Identity()
(act2): ReLU(inplace=True)
(aa): Identity()
(conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): DetrFrozenBatchNorm2d()
(act3): ReLU(inplace=True)
(downsample): Sequential(
(0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): Bottleneck(
(conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): DetrFrozenBatchNorm2d()
(act1): ReLU(inplace=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): DetrFrozenBatchNorm2d()
(drop_block): Identity()
(act2): ReLU(inplace=True)
(aa): Identity()
(conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): DetrFrozenBatchNorm2d()
(act3): ReLU(inplace=True)
)
(2): Bottleneck(
(conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn1): DetrFrozenBatchNorm2d()
(act1): ReLU(inplace=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): DetrFrozenBatchNorm2d()
(drop_block): Identity()
(act2): ReLU(inplace=True)
(aa): Identity()
(conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
(bn3): DetrFrozenBatchNorm2d()
(act3): ReLU(inplace=True)
)
)
)
)
(position_embedding): DetrSinePositionEmbedding()
)
(input_projection): Conv2d(2048, 256, kernel_size=(1, 1), stride=(1, 1))
(query_position_embeddings): Embedding(100, 256)
(encoder): DetrEncoder(
(layers): ModuleList(
(0-5): 6 x DetrEncoderLayer(
(self_attn): DetrAttention(
(k_proj): Linear(in_features=256, out_features=256, bias=True)
(v_proj): Linear(in_features=256, out_features=256, bias=True)
(q_proj): Linear(in_features=256, out_features=256, bias=True)
(out_proj): Linear(in_features=256, out_features=256, bias=True)
)
(self_attn_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
(activation_fn): ReLU()
(fc1): Linear(in_features=256, out_features=2048, bias=True)
(fc2): Linear(in_features=2048, out_features=256, bias=True)
(final_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
)
)
)
(decoder): DetrDecoder(
(layers): ModuleList(
(0-5): 6 x DetrDecoderLayer(
(self_attn): DetrAttention(
(k_proj): Linear(in_features=256, out_features=256, bias=True)
(v_proj): Linear(in_features=256, out_features=256, bias=True)
(q_proj): Linear(in_features=256, out_features=256, bias=True)
(out_proj): Linear(in_features=256, out_features=256, bias=True)
)
(activation_fn): ReLU()
(self_attn_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
(encoder_attn): DetrAttention(
(k_proj): Linear(in_features=256, out_features=256, bias=True)
(v_proj): Linear(in_features=256, out_features=256, bias=True)
(q_proj): Linear(in_features=256, out_features=256, bias=True)
(out_proj): Linear(in_features=256, out_features=256, bias=True)
)
(encoder_attn_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
(fc1): Linear(in_features=256, out_features=2048, bias=True)
(fc2): Linear(in_features=2048, out_features=256, bias=True)
(final_layer_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
)
)
(layernorm): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
)
)
(class_labels_classifier): Linear(in_features=256, out_features=2, bias=True)
(bbox_predictor): DetrMLPPredictionHead(
(layers): ModuleList(
(0-1): 2 x Linear(in_features=256, out_features=256, bias=True)
(2): Linear(in_features=256, out_features=4, bias=True)
)
)
)"""
}
|