Yolov5代码详解——detect.py
首先执行扩展包的导入:
import argparse import os import platform import sys from pathlib import Path import torch FILE = Path(__file__).resolve() #获取detect.py在电脑中的绝对路径 ROOT = FILE.parents[0] # 获取detect.py的父目录(绝对路径) if str(ROOT) not in sys.path: # 判断detect.py的父目录是否存在于模块的查询路径列表 sys.path.append(str(ROOT)) # add ROOT to PATH ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # 将绝对路径转换为相对路径 from models.common import DetectMultiBackend from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadScreenshots, LoadStreams from utils.general import (LOGGER, Profile, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2, increment_path, non_max_suppression, print_args, scale_boxes, strip_optimizer, xyxy2xywh) from utils.plots import Annotator, colors, save_one_box from utils.torch_utils import select_device, smart_inference_mode
包导入完成之后,执行最下面的这段代码:
if __name__ == '__main__': opt = parse_opt() #解析参数 main(opt)
这段代码用到了parse_opt()这个函数,它的功能主要是解析参数,主要参数解析如下:
""" --weights:权重的路径地址 --source:测试数据,可以是图片/视频路径,也可以是'0'(电脑自带摄像头),也可以是rtsp等视频流 --output:网络预测之后的图片/视频的保存路径 --img-size:网络输入图片大小 --conf-thres:置信度阈值 --iou-thres:做nms的iou阈值 --device:是用GPU还是CPU做推理 --view-img:是否展示预测之后的图片/视频,默认False --save-txt:是否将预测的框坐标以txt文件形式保存,默认False --classes:设置只保留某一部分类别,形如0或者0 2 3 --agnostic-nms:进行nms是否也去除不同类别之间的框,默认False --augment:推理的时候进行多尺度,翻转等操作(TTA)推理 --update:如果为True,则对所有模型进行strip_optimizer操作,去除pt文件中的优化器等信息,默认为False --project:推理的结果保存在runs/detect目录下 --name:结果保存的文件夹名称 """ 该部分来源于博主“炮哥带你学”——‘目标检测---教你利用yolov5训练自己的目标检测模型’一文, 原文地址:https://blog.csdn.net/didiaopao/article/details/119954291?spm=1001.2014.3001.5502
在parse_opt()执行完成之后,会将opt传给函数main():
def main(opt): check_requirements(exclude=('tensorboard', 'thop')) #检测中的扩展包是否安装 run(**vars(opt))
main()函数中调用了函数run(),run()主要代码解析如下:
run()主要分为了六个部分:
-
处理预测路径
#处理预测路径 source = str(source) #将路径转为字符串类型(data\\images\\bus.jpg) save_img = not nosave and not source.endswith('.txt') # 保存预测结果 #suffix函数表示文件类型,suffix[1:]表示从.jpg中截取jpg,然后判断jpg是否位于(IMG_FORMATS + VID_FORMATS)中 is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS) #判断路径是否为网络流的格式(lower()作用是将字母全部转换为小写) is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://')) #判断路径是否为‘0’(如果为‘0’会打开电脑摄像头),是否是.streams文件格式,是否是网络流地址 webcam = source.isnumeric() or source.endswith('.streams') or (is_url and not is_file) screenshot = source.lower().startswith('screen') if is_url and is_file: source = check_file(source) # download,下载图片或视频
-
新建保存结果的文件夹
# Directories,新建保存结果的文件夹 #增量式地产生文件夹(exp,exp1,exp2...) save_dir = increment_path(Path(project) / name, exist_ok=exist_ok) # increment run #在exp文件夹下新建labels文件夹 (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir
-
加载模型的权重
# Load model,加载模型的权重 device = select_device(device) #选择加载模型的设备 #加载模型并从模型中读取一些信息 model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half) stride, names, pt = model.stride, model.names, model.pt imgsz = check_img_size(imgsz, s=stride) # check image size
-
加载待预测的图片
# Dataloader,加载待预测的图片 bs = 1 # batch_size if webcam: #根据‘处理预测路径’代码部分得webcam一般为false view_img = check_imshow(warn=True) dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride) bs = len(dataset) elif screenshot: #根据‘处理预测路径’代码部分得screenshot一般为false dataset = LoadScreenshots(source, img_size=imgsz, stride=stride, auto=pt) else: #加载图片 dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride) vid_path, vid_writer = [None] * bs, [None] * bs
-
执行模型的推理过程
# Run inference,执行模型的推理过程 #warmup初始化一张空白图片并传入到模型当中,让模型执行一次前向传播 model.warmup(imgsz=(1 if pt or model.triton else bs, 3, *imgsz)) # warmup seen, windows, dt = 0, [], (Profile(), Profile(), Profile()) #定义变量存储中间结果信息 #path:路径 im:处理后的图片 im0s:原图 vid_cap:none s:图片的打印信息 for path, im, im0s, vid_cap, s in dataset: with dt[0]: im = torch.from_numpy(im).to(model.device) #将im转化为pytorch支持的格式并放到设备中 im = im.half() if model.fp16 else im.float() # uint8 to fp16/32 im /= 255 # 0 - 255 to 0.0 - 1.0 #归一化 if len(im.shape) == 3: im = im[None] # expand for batch dim # Inference,对上面整理好的图片进行预测 with dt[1]: visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False pred = model(im, augment=augment, visualize=visualize) # NMS,进行非极大值过滤 with dt[2]: pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det) # Second-stage classifier (optional) # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s) # Process predictions for i, det in enumerate(pred): # 遍历每张图片 seen += 1 if webcam: # batch_size >= 1 p, im0, frame = path[i], im0s[i].copy(), dataset.count s += f'{i}: ' else: p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0) p = Path(p) # to Path save_path = str(save_dir / p.name) # im.jpg txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # im.txt s += '%gx%g ' % im.shape[2:] # print string gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] #获取原图宽和高 imc = im0.copy() if save_crop else im0 #判断是否将检测框部分裁剪下来 annotator = Annotator(im0, line_width=line_thickness, example=str(names)) #定义绘图工具 if len(det): #坐标映射,方便在原图上画检测框 det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round() # 遍历det for c in det[:, 5].unique(): n = (det[:, 5] == c).sum() # detections per class s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string # 是否保存预测结果 for *xyxy, conf, cls in reversed(det): if save_txt: # 保存为txt 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(f'{txt_path}.txt', 'a') as f: f.write(('%g ' * len(line)).rstrip() % line + '\n') if save_img or save_crop or view_img: # 只在图片上添加检测框 c = int(cls) # integer class label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}') annotator.box_label(xyxy, label, color=colors(c, True)) if save_crop: #是否保存截下来的目标框 save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True) # Stream results im0 = annotator.result() if view_img: if platform.system() == 'Linux' and p not in windows: windows.append(p) cv2.namedWindow(str(p), cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO) # allow window resize (Linux) cv2.resizeWindow(str(p), im0.shape[1], im0.shape[0]) 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[i] != save_path: # new video vid_path[i] = save_path if isinstance(vid_writer[i], cv2.VideoWriter): vid_writer[i].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 = str(Path(save_path).with_suffix('.mp4')) # force *.mp4 suffix on results videos vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h)) vid_writer[i].write(im0) # Print time (inference-only) LOGGER.info(f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1E3:.1f}ms")
-
打印输出信息
# Print results,打印输出信息 t = tuple(x.t / seen * 1E3 for x in dt) # 统计每张图片的平均时间 LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t) 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 '' LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}") if update: strip_optimizer(weights[0]) # update model (to fix SourceChangeWarning)