Create YOLOv5.py

.ai/deep_learning/YOLOv5.py

@@ -0,0 +1,75 @@
+import torch
+from models.experimental import attempt_load
+from utils.datasets import LoadStreams, LoadImages
+from utils.general import check_img_size, non_max_suppression, apply_classifier, scale_coords, xyxy2xywh, strip_optimizer, set_logging
+from utils.torch_utils import select_device, load_classifier, time_synchronized
+from utils.plots import plot_one_box
+import argparse
+import time
+import cv2
+
+def detect(save_img=False, save_txt=False, imgsz=(640, 640), conf_thres=0.4, iou_thres=0.5, max_det=1000):
+    # Initialize
+    device = select_device('')
+    half = device.type != 'cpu' # half precision only supported on CUDA
+
+    # Load model
+    model = attempt_load('yolov5s.pt', map_location=device)  # load FP32 model
+    stride = int(model.stride.max())  # model stride
+    imgsz = check_img_size(imgsz, s=stride)  # check image size
+
+    # Get names and colors
+    names = model.module.names if hasattr(model, 'odule') 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()
+    img = torch.zeros((1, 3, imgsz, imgsz), device=device)  # init img
+    _ = model(img) if device.type!= 'cpu' else None  # run once
+
+    # Set Dataloader
+    vid_path, vid_writer = None, None
+    dataset = LoadStreams('https://www.youtube.com/watch?v=dQw4w9WgXcQ', img_size=imgsz, stride=stride)
+
+    # Run inference
+    t = time_synchronized()
+    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=False)[0]
+
+        # Apply NMS
+        pred = non_max_suppression(pred, conf_thres, iou_thres, max_det=max_det)
+
+        # Process detections
+        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], im0s.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 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, im0s, label=label, color=colors[int(cls)], line_thickness=3)
+
+    print(f'Done. ({time.time() - t0:.3f}s)')