一、detect文件
def detect(save_img=False):
source, weights, view_img, save_txt, imgsz = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size
save_img = not opt.nosave and not source.endswith('.txt') # save inference images 是否以”.txt"结尾判断是否保存推理结果的图像
webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
('rtsp://', 'rtmp://', 'http://', 'https://'))
# 输入源是否为摄像头源(isnumeric(0),则为摄像头源),是否以txt结尾,转化为小写是否为网址
# Directories,添加文件
save_dir = Path(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok))
# 添加路径runs/detect并与exp拼接
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir
# 若save_txt为真则在exp下添加labels路径,否则继续添加exp路径
# Initialize,判断设备
set_logging()
device = select_device(opt.device) # 判断运用的设备是cpu还是gpu
half = device.type != 'cpu' # half precision only supported on CUDA,设备不是cpu,是gpu为true,则采用半精度计算
# Load model
model = attempt_load(weights, map_location=device) # load FP32 model,32为步幅
stride = int(model.stride.max()) # model stride,计算模型的最大步幅。模型的步幅表示输入图像经过模型后,在特征图上产生的像素步幅
imgsz = check_img_size(imgsz, s=stride)
# 使用 check_img_size 函数来检查输入图像的尺寸是否满足模型的要求(640*640)。imgsz 是命令行参数中指定的图像尺寸,s 参数是模型的步幅。
# 如果不符合,则返回new_size
if half:
model.half() # to FP16 半精度格式(FP16)
# Second-stage classifier
classify = False # 是否使用二次分类器
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()
# Set Dataloader
vid_path, vid_writer = None, None # 这两个变量分别用于保存视频路径和视频写入器的引用
if webcam: # 输入jpg等图片形式时webcam为false,输入为摄像头、txt、网址时为true
view_img = check_imshow() # 检查是否需要显示图像,如果需要则返回 True,否则返回 False
cudnn.benchmark = True # set True to speed up constant image size inference,加速
dataset = LoadStreams(source, img_size=imgsz, stride=stride)
else:
dataset = LoadImages(source, img_size=imgsz, stride=stride)
# Get names and colors
names = model.module.names if hasattr(model, 'module') else model.names # 获取类别名称
colors = [[random.randint(0, 255) for _ in range(3)] for _ in names] # 随机RGB通道
# Run inference
if device.type != 'cpu':
'''初始化模型的参数,1个样本,3个通道,模型尺寸Imagsz*Imgaz,记录时间'''
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) # 将图片转换为Pytorch支持的格式并且在cpu或者gpu运行([3,640,480])
img = img.half() if half else img.float() # uint8 to fp16/32
img /= 255.0 # 0 - 255 to 0.0 - 1.0 归一化
if img.ndimension() == 3: # 扩张一维,([1,3,640,480])
img = img.unsqueeze(0)
# Inference
t1 = time_synchronized() # 记录时间
pred = model(img, augment=opt.augment)[0] # 数据增强,可能会降低计算机运行速度
# Apply NMS 过滤
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 遍历每个图片(【5,6】)
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 ,保存路径
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,保存新图的尺寸
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh,保存原图尺寸
if len(det):
# Rescale boxes from img_size to im0 size
det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round() # 坐标映射,方便在原图画框
# 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}' # 输出类别和置信度
plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=3) # 绘制检测框
# Print time (inference + NMS)
print(f'{s}Done. ({t2 - t1:.3f}s)')
# Stream results
if view_img:
cv2.imshow(str(p), im0) # 是否显示图片
cv2.waitKey(1) # 1 millisecond
# Save results (image with detections)
if save_img:
if dataset.mode == 'image':
cv2.imwrite(save_path, im0) # 保存最终的结果文件
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)') # 耗时
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--weights', nargs='+', type=str, default='yolov5s.pt', help='model.pt path(s)')
parser.add_argument('--source', type=str, default='data/images', 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')
opt = parser.parse_args()
print(opt) # 显示解析后的参数值
check_requirements(exclude=('pycocotools', 'thop')) # 检查依赖是否安装
with torch.no_grad():
if opt.update: # update all models (to fix SourceChangeWarning)
for opt.weights in ['yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt']:
detect()
strip_optimizer(opt.weights)
else:
detect()