YOLOV5——输出 json 格式预测文件（修改detect.py）
YOLOV5的预测只输出在测试文件中预测标记的数据，如下图。如果想要将预测的 json 格式文件输出该怎么办呢
json 标注数据文件内容包含：
name：图片文件名
category：类别id
bbox：目标框信息xyrb格式，分别指[左上角x坐标，左上角y坐标，右下角x坐标，右下角y坐标]
score：预测的分数
[ { "name": "226_46_t20201125133518273_CAM1.jpg", "category": 4, "bbox": [ 5662, 2489, 5671, 2497 ], "score": 0.130577 } ]
写入标记数据信息
content_json = [] # windows下使用 file_name = save_path.split('\\') # Linux下使用 # file_name = save_path.split('/') content_dic = { "name": file_name[len(file_name)-1], "category": (names[int(cls)]), "bbox": torch.tensor(xyxy).view(1, 4).view(-1).tolist(), "score": conf.tolist() } content_json.append(content_dic) # 将 json 数据写入文件 with open(os.path.join(Path(out), 'result.json'), 'w') as f: json.dump(content_json, f)
完整的detect.py文件
import argparse import os import shutil import time from pathlib import Path import json import cv2 import torch import torch.backends.cudnn as cudnn from numpy import random 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, plot_one_box, strip_optimizer, set_logging) from utils.torch_utils import select_device, load_classifier, time_synchronized def detect(save_img=False): # 获取设置的参数数据 out, source, weights, view_img, save_txt, imgsz = \ opt.save_dir, opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size webcam = source.isnumeric() or source.startswith(('rtsp://', 'rtmp://', 'http://')) or source.endswith('.txt') # Initialize set_logging() device = select_device(opt.device) if os.path.exists(out): # output dir shutil.rmtree(out) # delete dir os.makedirs(out) # make new dir # 如果设备为GPU时， 使用Float16 half = device.type != 'cpu' # half precision only supported on CUDA # Load model 确保用户设定的输入图片分辨率能整除32(如不能则调整为能整除并返回) model = attempt_load(weights, map_location=device) # load FP32 model imgsz = check_img_size(imgsz, s=model.stride.max()) # check img_size if half: model.half() # to FP16 # Second-stage classifier 设置第二次分类，默认不使用 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']) # load weights modelc.to(device).eval() # Set Dataloader 通过不同的输入源来设置不同的数据加载方式 vid_path, vid_writer = None, None if webcam: view_img = True cudnn.benchmark = True # set True to speed up constant image size inference dataset = LoadStreams(source, img_size=imgsz) else: save_img = True dataset = LoadImages(source, img_size=imgsz) # Get names and colors # 获取类别名字 names = model.module.names if hasattr(model, 'module') else model.names # 设置画框的颜色 colors = [[random.randint(0, 255) for _ in range(3)] for _ in range(len(names))] # Run inference t0 = time.time() # 进行一次前向推理,测试程序是否正常 img = torch.zeros((1, 3, imgsz, imgsz), device=device) # init img _ = model(img.half() if half else img) if device.type != 'cpu' else None # run once # 输出json文件 save_json = True content_json = [] # path 图片/视频路径 # img 进行resize+pad之后的图片 # img0 原size图片 # cap 当读取图片时为None，读取视频时为视频源 for path, img, im0s, vid_cap in dataset: img = torch.from_numpy(img).to(device) # 图片也设置为Float16 img = img.half() if half else img.float() # uint8 to fp16/32 img /= 255.0 # 0 - 255 to 0.0 - 1.0 # 没有batch_size的话则在最前面添加一个轴 if img.ndimension() == 3: img = img.unsqueeze(0) # Inference t1 = time_synchronized() """ 前向传播 返回pred的shape是(1, num_boxes, 5+num_class) h,w为传入网络图片的长和宽，注意dataset在检测时使用了矩形推理，所以这里h不一定等于w num_boxes = h/32 * w/32 + h/16 * w/16 + h/8 * w/8 pred[..., 0:4]为预测框坐标 预测框坐标为xywh(中心点+宽长)格式 pred[..., 4]为objectness置信度 pred[..., 5:-1]为分类结果 """ pred = model(img, augment=opt.augment)[0] # Apply NMS """ pred:前向传播的输出 conf_thres:置信度阈值 iou_thres:iou阈值 classes:是否只保留特定的类别 agnostic:进行nms是否也去除不同类别之间的框 经过nms之后，预测框格式：xywh-->xyxy(左上角右下角) pred是一个列表list[torch.tensor]，长度为batch_size 每一个torch.tensor的shape为(num_boxes, 6),内容为box+conf+cls """ pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms) t2 = time_synchronized() # Apply Classifier # 添加二次分类，默认不使用 if classify: pred = apply_classifier(pred, modelc, img, im0s) # Process detections # 对每一张图片作处理 for i, det in enumerate(pred): # detections per image # 如果输入源是webcam，则batch_size不为1，取出dataset中的一张图片 if webcam: # batch_size >= 1 p, s, im0 = path[i], '%g: ' % i, im0s[i].copy() else: p, s, im0 = path, '', im0s # 设置保存图片/视频的路径 save_path = str(Path(out) / Path(p).name) # 设置保存框坐标txt文件的路径 txt_path = str(Path(out) / Path(p).stem) + ('_%g' % dataset.frame if dataset.mode == 'video' else '') # 设置打印信息（图片长宽） s += '%gx%g ' % img.shape[2:] # print string 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 # 调整预测框的坐标：基于resize+pad的图片的坐标-->基于原size图片的坐标 # 此时坐标格式为xyxy det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round() # Print results # 打印检测到的类别数量 for c in det[:, -1].unique(): n = (det[:, -1] == c).sum() # detections per class s += '%g %ss, ' % (n, names[int(c)]) # add to string # Write results for *xyxy, conf, cls in reversed(det): if save_txt: # Write to file # 将xyxy(左上角+右下角)格式转为xywh(中心点+宽长)格式，并除上w，h做归一化，转化为列表再保存 xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh line = (cls, conf, *xywh) if opt.save_conf else (cls, *xywh) # label format with open(txt_path + '.txt', 'a') as f: # 在原图上画框 f.write(('%g ' * len(line) + '\n') % line) if save_img or view_img: # Add bbox to image label = '%s %.2f' % (names[int(cls)], conf) plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=3) # 输出 json 文件 if save_json: # windows下使用 file_name = save_path.split('\\') # Linux下使用 # file_name = save_path.split('/') content_dic = { "name": file_name[len(file_name)-1], "category": (names[int(cls)]), "bbox": torch.tensor(xyxy).view(1, 4).view(-1).tolist(), "score": conf.tolist() } content_json.append(content_dic) # Print time (inference + NMS) # 打印前向传播时间 print('%sDone. (%.3fs)' % (s, t2 - t1)) # Stream results # 如果设置展示，则show图片/视频 if view_img: cv2.imshow(p, im0) if cv2.waitKey(1) == ord('q'): # q to quit raise StopIteration # Save results (image with detections) # 设置保存图片/视频 # if save_img: # if dataset.mode == 'images': # cv2.imwrite(save_path, im0) # else: # if vid_path != save_path: # new video # vid_path = save_path # if isinstance(vid_writer, cv2.VideoWriter): # vid_writer.release() # release previous video writer # # fourcc = 'mp4v' # output video codec # 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)) # vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*fourcc), fps, (w, h)) # vid_writer.write(im0) if save_txt or save_img or save_json: print('Results saved to %s' % Path(out)) # 将 json 数据写入文件 with open(os.path.join(Path(out), 'result.json'), 'w') as f: json.dump(content_json, f) # 打印总时间 print('Done. (%.3fs)' % (time.time() - t0)) if __name__ == '__main__': """ weights:训练的权重 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:设置设备 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 """ parser = argparse.ArgumentParser() parser.add_argument('--weights', nargs='+', type=str, default='best.pt', help='model.pt path(s)') parser.add_argument('--source', type=str, default='../tile/testA_imgs', help='source') # file/folder, 0 for webcam parser.add_argument('--img-size', type=int, default=1600, help='inference size (pixels)') parser.add_argument('--conf-thres', type=float, default=0.1, 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('--save-dir', type=str, default='detect_img/output', help='directory to save results') 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') opt = parser.parse_args() print(opt) 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() # 去除pt文件中的优化器等信息 strip_optimizer(opt.weights) else: detect()
代码注释参考：https://blog.csdn.net/weixin_44152895/article/details/110009680
