如果您想提取 YOLOv5 6.0 版本的 detect.py 中关于摄像头的代码，可以按照以下步骤进行：
1. 打开 detect.py 文件，找到以下代码：
```python
# Camera inference
elif source.isnumeric():
source = int(source)
# Start streaming
cap = cv2.VideoCapture(source)
assert cap.isOpened(), f'Failed to open {source}'
cap.set(cv2.CAP_PROP_FRAME_WIDTH, width)
cap.set(cv2.CAP_PROP_FRAME_HEIGHT, height)
fps = cap.get(cv2.CAP_PROP_FPS)
print(f'Using {source} with FPS {fps:.3f} [OK]')
for path, img, im0s, vid_cap in dataset:
if vid_path != path:
vid_path, frames = path, []
if isinstance(vid_cap, cv2.VideoCapture):
frames = vid_cap.get(cv2.CAP_PROP_FRAME_COUNT)
elif isinstance(vid_cap, int):
frames = vid_cap
else:
assert False, f'Invalid video {path}'
t1 = time_synchronized()
# Get frames
ret, frame = cap.read()
if not ret:
break
assert frame is not None, 'Image Not Found '
# Padded resize
frame = letterbox(frame, new_shape=inp_shape)[0]
# Normalize RGB
frame = frame[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to 3x416x416
frame = np.ascontiguousarray(frame)
# Inference
img = torch.from_numpy(frame).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
t2 = 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)
t3 = time_synchronized()
# Process detections
for i, det in enumerate(pred): # detections per image
p, s, im0 = path, '', im0s.copy()
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh
if det is not None and 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, ' # add to string
# Write results
for *xyxy, conf, cls in det:
if save_txt: # Write to file
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
with open(txt_path + '.txt', 'a') as f:
f.write(('%g ' * 5 + '\n') % (cls, *xywh)) # label format
if save_img or save_crop or save_patch: # Add bbox to image
c = int(cls) # integer class
label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
plot_one_box(xyxy, im0, label=label, color=colors(c, True), line_thickness=3, **plot_kwargs)
if save_crop or save_patch: # Save crop
#crop = im0[int(xyxy[1]):int(xyxy[3]), int(xyxy[0]):int(xyxy[2])]
save_file = str(Path(save_dir) / Path(p).stem) + f'_{i}_{names[c]}.jpg'
cv2.imwrite(save_file, crop)
# Print results
print(f'{s}Done. ({t3 - t1:.3f}s)')
# Stream results
if view_img:
cv2.imshow(p, im0)
if cv2.waitKey(1) == ord('q'): # q to quit
raise StopIteration
if save_txt or save_img:
print(f"Results saved to {save_dir}")
if platform == 'darwin': # MacOS
os.system(f'open {save_dir}')
cap.release()
```
2. 将以上代码复制到一个新文件中
3. 删除以下代码：
```python
elif source.isnumeric():
source = int(source)
# Start streaming
cap = cv2.VideoCapture(source)
assert cap.isOpened(), f'Failed to open {source}'
cap.set(cv2.CAP_PROP_FRAME_WIDTH, width)
cap.set(cv2.CAP_PROP_FRAME_HEIGHT, height)
fps = cap.get(cv2.CAP_PROP_FPS)
print(f'Using {source} with FPS {fps:.3f} [OK]')
```
4. 将下面的代码留下来：
```python
for path, img, im0s, vid_cap in dataset:
if vid_path != path:
vid_path, frames = path, []
if isinstance(vid_cap, cv2.VideoCapture):
frames = vid_cap.get(cv2.CAP_PROP_FRAME_COUNT)
elif isinstance(vid_cap, int):
frames = vid_cap
else:
assert False, f'Invalid video {path}'
t1 = time_synchronized()
# Get frames
ret, frame = cap.read()
if not ret:
break
assert frame is not None, 'Image Not Found '
# Padded resize
frame = letterbox(frame, new_shape=inp_shape)[0]
# Normalize RGB
frame = frame[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to 3x416x416
frame = np.ascontiguousarray(frame)
# Inference
img = torch.from_numpy(frame).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
t2 = 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)
t3 = time_synchronized()
# Process detections
for i, det in enumerate(pred): # detections per image
p, s, im0 = path, '', im0s.copy()
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh
if det is not None and 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, ' # add to string
# Write results
for *xyxy, conf, cls in det:
if save_txt: # Write to file
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
with open(txt_path + '.txt', 'a') as f:
f.write(('%g ' * 5 + '\n') % (cls, *xywh)) # label format
if save_img or save_crop or save_patch: # Add bbox to image
c = int(cls) # integer class
label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
plot_one_box(xyxy, im0, label=label, color=colors(c, True), line_thickness=3, **plot_kwargs)
if save_crop or save_patch: # Save crop
#crop = im0[int(xyxy[1]):int(xyxy[3]), int(xyxy[0]):int(xyxy[2])]
save_file = str(Path(save_dir) / Path(p).stem) + f'_{i}_{names[c]}.jpg'
cv2.imwrite(save_file, crop)
# Print results
print(f'{s}Done. ({t3 - t1:.3f}s)')
# Stream results
if view_img:
cv2.imshow(p, im0)
if cv2.waitKey(1) == ord('q'): # q to quit
raise StopIteration
```
这部分代码处理摄像头输入并进行推理。
5. 将提取出的代码保存到一个新文件中，例如 camera_detect.py。
现在您可以使用 camera_detect.py 进行摄像头推理。请确保在运行代码之前正确设置 YOLOv5 模型、类别和权重路径。
扫一扫
8355
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
