Upload 3 files

.gitattributes

@@ -25,3 +25,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+input_0.mp4 filter=lfs diff=lfs merge=lfs -text
+input_1.mp4 filter=lfs diff=lfs merge=lfs -text

app.py

@@ -1,197 +1,178 @@
+import torch
 import gradio as gr
-import os
-
-import argparse
-import time
-from pathlib import Path
-
 import cv2
-import torch
-import torch.backends.cudnn as cudnn
-from numpy import random
-
+import numpy as np
+import random
+import numpy as np
 from models.experimental import attempt_load
-from utils.datasets import LoadStreams, LoadImages
-from utils.general import check_img_size, check_requirements, check_imshow, non_max_suppression, apply_classifier, \
-    scale_coords, xyxy2xywh, strip_optimizer, set_logging, increment_path
+from utils.general import check_img_size, non_max_suppression, \
+    scale_coords
 from utils.plots import plot_one_box
-from utils.torch_utils import select_device, load_classifier, time_synchronized, TracedModel
-from PIL import Image
- 
+from utils.torch_utils import time_synchronized
+
 from huggingface_hub import hf_hub_download
 
 
-def load_model(model_name):
-    model_path = hf_hub_download(repo_id=f"Yolov7/{model_name}", filename=f"{model_name}.pt")
-
-    return model_path
-
-
-model_names = [
-    "yolov7",
-    "yolov7-e6e",
-    "yolov7-e6",
-]
-
-models = {model_name: load_model(model_name) for model_name in model_names}
-
-
-def detect(img,model):
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--weights', nargs='+', type=str, default=models[model], help='model.pt path(s)')
-    parser.add_argument('--source', type=str, default='Inference/', help='source')  # file/folder, 0 for webcam
-    parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
-    parser.add_argument('--conf-thres', type=float, default=0.25, help='object confidence threshold')
-    parser.add_argument('--iou-thres', type=float, default=0.45, help='IOU threshold for NMS')
-    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
-    parser.add_argument('--view-img', action='store_true', help='display results')
-    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
-    parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
-    parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
-    parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --class 0, or --class 0 2 3')
-    parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
-    parser.add_argument('--augment', action='store_true', help='augmented inference')
-    parser.add_argument('--update', action='store_true', help='update all models')
-    parser.add_argument('--project', default='runs/detect', help='save results to project/name')
-    parser.add_argument('--name', default='exp', help='save results to project/name')
-    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
-    parser.add_argument('--trace', action='store_true', help='trace model')
-    opt = parser.parse_args()
-    img.save("Inference/test.jpg")
-    source, weights, view_img, save_txt, imgsz, trace = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size, opt.trace
-    save_img = True  # save inference images
-    webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
-        ('rtsp://', 'rtmp://', 'http://', 'https://'))
-
-    # Directories
-    save_dir = Path(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok))  # increment run
-    (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir
-
-    # Initialize
-    set_logging()
-    device = select_device(opt.device)
-    half = device.type != 'cpu'  # half precision only supported on CUDA
 
-    # Load model
-    model = attempt_load(weights, map_location=device)  # load FP32 model
-    stride = int(model.stride.max())  # model stride
-    imgsz = check_img_size(imgsz, s=stride)  # check img_size
 
-    if trace:
-        model = TracedModel(model, device, opt.img_size)
 
-    if half:
-        model.half()  # to FP16
+def letterbox(im, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleup=True, stride=32):
+    # Resize and pad image while meeting stride-multiple constraints
+    shape = im.shape[:2]  # current shape [height, width]
+    if isinstance(new_shape, int):
+        new_shape = (new_shape, new_shape)
+
+    # Scale ratio (new / old)
+    r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
+    if not scaleup:  # only scale down, do not scale up (for better val mAP)
+        r = min(r, 1.0)
+
+    # Compute padding
+    new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
+    dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1]  # wh padding
+
+    if auto:  # minimum rectangle
+        dw, dh = np.mod(dw, stride), np.mod(dh, stride)  # wh padding
 
-    # Second-stage classifier
-    classify = False
-    if classify:
-        modelc = load_classifier(name='resnet101', n=2)  # initialize
-        modelc.load_state_dict(torch.load('weights/resnet101.pt', map_location=device)['model']).to(device).eval()
+    dw /= 2  # divide padding into 2 sides
+    dh /= 2
 
-    # Set Dataloader
-    vid_path, vid_writer = None, None
-    if webcam:
-        view_img = check_imshow()
-        cudnn.benchmark = True  # set True to speed up constant image size inference
-        dataset = LoadStreams(source, img_size=imgsz, stride=stride)
-    else:
-        dataset = LoadImages(source, img_size=imgsz, stride=stride)
+    if shape[::-1] != new_unpad:  # resize
+        im = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR)
+    top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
+    left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
+    im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color)  # add border
+    return im, r, (dw, dh)
+
+names = ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light', 
+         'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', 
+         'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee', 
+         'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 
+         'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', 
+         'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', 
+         'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 
+         'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 
+         'hair drier', 'toothbrush']
+
+
+colors = [[random.randint(0, 255) for _ in range(3)] for _ in names]
+
+
+def detect(img,model,device,iou_threshold=0.45,confidence_threshold=0.25):   
+    imgsz = 640
+    img = np.array(img)
+    stride = int(model.stride.max())  # model stride
+    imgsz = check_img_size(imgsz, s=stride)  # check img_size
 
     # Get names and colors
     names = model.module.names if hasattr(model, 'module') else model.names
-    colors = [[random.randint(0, 255) for _ in range(3)] for _ in names]
 
     # Run inference
-    if device.type != 'cpu':
-        model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters())))  # run once
-    t0 = time.time()
-    for path, img, im0s, vid_cap in dataset:
-        img = torch.from_numpy(img).to(device)
-        img = img.half() if half else img.float()  # uint8 to fp16/32
-        img /= 255.0  # 0 - 255 to 0.0 - 1.0
-        if img.ndimension() == 3:
-            img = img.unsqueeze(0)
-
-        # Inference
-        t1 = time_synchronized()
-        pred = model(img, augment=opt.augment)[0]
-
-        # Apply NMS
-        pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)
-        t2 = time_synchronized()
-
-        # Apply Classifier
-        if classify:
-            pred = apply_classifier(pred, modelc, img, im0s)
-
-        # Process detections
-        for i, det in enumerate(pred):  # detections per image
-            if webcam:  # batch_size >= 1
-                p, s, im0, frame = path[i], '%g: ' % i, im0s[i].copy(), dataset.count
-            else:
-                p, s, im0, frame = path, '', im0s, getattr(dataset, 'frame', 0)
-
-            p = Path(p)  # to Path
-            save_path = str(save_dir / p.name)  # img.jpg
-            txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')  # img.txt
-            s += '%gx%g ' % img.shape[2:]  # print string
-            gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwh
-            if len(det):
-                # Rescale boxes from img_size to im0 size
-                det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()
-
-                # Print results
-                for c in det[:, -1].unique():
-                    n = (det[:, -1] == c).sum()  # detections per class
-                    s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string
-
-                # Write results
-                for *xyxy, conf, cls in reversed(det):
-                    if save_txt:  # Write to file
-                        xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
-                        line = (cls, *xywh, conf) if opt.save_conf else (cls, *xywh)  # label format
-                        with open(txt_path + '.txt', 'a') as f:
-                            f.write(('%g ' * len(line)).rstrip() % line + '\n')
-
-                    if save_img or view_img:  # Add bbox to image
-                        label = f'{names[int(cls)]} {conf:.2f}'
-                        plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=3)
-
-            # Print time (inference + NMS)
-            #print(f'{s}Done. ({t2 - t1:.3f}s)')
-
-            # Stream results
-            if view_img:
-                cv2.imshow(str(p), im0)
-                cv2.waitKey(1)  # 1 millisecond
-
-            # Save results (image with detections)
-            if save_img:
-                if dataset.mode == 'image':
-                    cv2.imwrite(save_path, im0)
-                else:  # 'video' or 'stream'
-                    if vid_path != save_path:  # new video
-                        vid_path = save_path
-                        if isinstance(vid_writer, cv2.VideoWriter):
-                            vid_writer.release()  # release previous video writer
-                        if vid_cap:  # video
-                            fps = vid_cap.get(cv2.CAP_PROP_FPS)
-                            w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
-                            h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
-                        else:  # stream
-                            fps, w, h = 30, im0.shape[1], im0.shape[0]
-                            save_path += '.mp4'
-                        vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
-                    vid_writer.write(im0)
-
-    if save_txt or save_img:
-        s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
-        #print(f"Results saved to {save_dir}{s}")
-
-    print(f'Done. ({time.time() - t0:.3f}s)')
-
-    return Image.fromarray(im0[:,:,::-1])
-
-   
-gr.Interface(detect,[gr.Image(type="pil"),gr.Dropdown(choices=model_names)], gr.Image(type="pil"),title="Yolov7",examples=[["horses.jpeg", "yolov7"]],description="demo for <a href='https://github.com/WongKinYiu/yolov7' style='text-decoration: underline' target='_blank'>WongKinYiu/yolov7</a> Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors").launch()
+    imgs = img.copy()  # for NMS
+    
+    image, ratio, dwdh = letterbox(img, auto=False)
+    image = image.transpose((2, 0, 1))
+    img = torch.from_numpy(image).to(device)
+    img = img.float()  # uint8 to fp16/32
+    img /= 255.0  # 0 - 255 to 0.0 - 1.0
+    if img.ndimension() == 3:
+        img = img.unsqueeze(0)
+
+
+    # Inference
+    t1 = time_synchronized()
+    with torch.no_grad():   # Calculating gradients would cause a GPU memory leak
+        pred = model(img,augment=True)[0]
+    t2 = time_synchronized()
+
+    # Apply NMS
+    pred = non_max_suppression(pred, confidence_threshold, iou_threshold, classes=None, agnostic=True)
+    t3 = time_synchronized()
+
+    for i, det in enumerate(pred):  # detections per image
+        if len(det):
+            # Rescale boxes from img_size to im0 size
+            det[:, :4] = scale_coords(img.shape[2:], det[:, :4], imgs.shape).round()
+
+
+            # Write results
+            for *xyxy, conf, cls in reversed(det):
+                label = f'{names[int(cls)]} {conf:.2f}'
+                plot_one_box(xyxy, imgs, label=label, color=colors[int(cls)], line_thickness=2)
+
+    return imgs 
+
+def inference(img,model_link,iou_threshold,confidence_threshold):
+    print(model_link)
+    device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
+    # Load model
+    model_path = hf_hub_download("shriarul5273/yolov7", str(model_link)+'.pt')
+    model = attempt_load(model_path, map_location=device) 
+    return detect(img,model,device,iou_threshold,confidence_threshold)
+
+
+def inference2(video,model_link,iou_threshold,confidence_threshold):
+    print(model_link)
+    device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
+    # Load model
+    model_path = hf_hub_download("shriarul5273/yolov7",  str(model_link)+'.pt')
+    model = attempt_load(model_path, map_location=device) 
+    frames = cv2.VideoCapture(video)
+    fps = frames.get(cv2.CAP_PROP_FPS)
+    image_size = (int(frames.get(cv2.CAP_PROP_FRAME_WIDTH)),int(frames.get(cv2.CAP_PROP_FRAME_HEIGHT)))
+    finalVideo = cv2.VideoWriter('output.mp4',cv2.VideoWriter_fourcc(*'VP90'), fps, image_size)
+    p = 1
+    while frames.isOpened():
+        ret,frame = frames.read()
+        if not ret:
+            break
+        frame = detect(frame,model,device,iou_threshold,confidence_threshold)
+        finalVideo.write(frame)
+    frames.release()
+    finalVideo.release()
+    return 'output.mp4'
+
+
+
+examples_images = ['inference/images/horses.jpg',
+            'inference/images/bus.jpg',
+            'inference/images/zidane.jpg']
+examples_videos = ['input_0.mp4','input_1.mp4'] 
+
+models = ['yolov7','yolov7x','yolov7-w6','yolov7-d6','yolov7-e6e']
+
+with gr.Blocks() as demo:
+    gr.Markdown("## YOLOv7 Inference")
+    with gr.Tab("Image"):
+        gr.Markdown("## YOLOv7 Inference on Image")
+        with gr.Row():
+            image_input = gr.Image(type='pil', label="Input Image", source="upload")
+            image_output = gr.Image(type='pil', label="Output Image", source="upload")
+        image_drop = gr.Dropdown(choices=models,value=models[0])
+        image_iou_threshold = gr.Slider(label="IOU Threshold",interactive=True, minimum=0.0, maximum=1.0, value=0.45)
+        image_conf_threshold = gr.Slider(label="Confidence Threshold",interactive=True, minimum=0.0, maximum=1.0, value=0.25)
+        gr.Examples(examples=examples_images,inputs=image_input,outputs=image_output)
+        text_button = gr.Button("Detect")
+    with gr.Tab("Video"):
+        gr.Markdown("## YOLOv7 Inference on Video")
+        with gr.Row():
+            video_input = gr.Video(type='pil', label="Input Image", source="upload")
+            video_output = gr.Video(type="pil", label="Output Image",format="mp4")
+        video_drop = gr.Dropdown(choices=models,value=models[0])
+        video_iou_threshold = gr.Slider(label="IOU Threshold",interactive=True, minimum=0.0, maximum=1.0, value=0.45)
+        video_conf_threshold = gr.Slider(label="Confidence Threshold",interactive=True, minimum=0.0, maximum=1.0, value=0.25)
+        gr.Examples(examples=examples_videos,inputs=video_input,outputs=video_output)
+        video_button = gr.Button("Detect")
+    
+    with gr.Tab("Webcam Video"):
+        gr.Markdown("## YOLOv7 Inference on Webcam Video")
+        gr.Markdown("Coming Soon")
+
+    text_button.click(inference, inputs=[image_input,image_drop,
+                                         image_iou_threshold,image_conf_threshold],
+                                        outputs=image_output)
+    video_button.click(inference2, inputs=[video_input,video_drop,
+                                           video_iou_threshold,video_conf_threshold],            
+                                        outputs=video_output)
+
+demo.launch()

input_0.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0305b8ba574b0b26c8d21b70dbd80aacbba13e813a99f5c4675982063ebd18a3
+size 1103987

input_1.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:103c54e60a7abf381741b4bcc5e696f5d200fc2a4ff259cc779bbd511dc2dae1
+size 1792081