YOLOv5代码详解 (第二部分）

2. test.py2.1 设置超参数2.2 设置任务（验证，测试，学习）2.3 测试函数2.3.1 初始化模型2.3.2 判断设备类型并仅使用一张GPU进行测试2.3.3 获取配置文件路径和文件参数2.3.4 数据获取2.3.5 计算map数据2.3.5 打印结果（图片，速度），保存结果至json，并返回结果

2. test.py

该部分主要用于运行train.py时，计算每个epoch的mAP。 PS，与train.py相似的部分就不再阐述。

2.1 设置超参数

权重，数据，batch size，图像尺寸，使用哪张显卡，数据增强，计算mAP。

if __name__ == '__main__': parser = argparse.ArgumentParser(prog='test.py') parser.add_argument('--weights', type=str, default='weights/best.pt', help='model.pt path') parser.add_argument('--data', type=str, default='data/coco.yaml', help='*.data path') parser.add_argument('--batch-size', type=int, default=16, help='size of each image batch') parser.add_argument('--img-size', type=int, default=608, help='inference size (pixels)') parser.add_argument('--conf-thres', type=float, default=0.001, help='object confidence threshold') parser.add_argument('--iou-thres', type=float, default=0.65, help='IOU threshold for NMS') parser.add_argument('--save-json', action='store_true', help='save a cocoapi-compatible JSON results file') parser.add_argument('--task', default='', help="'val', 'test', 'study'") parser.add_argument('--device', default='1', help='cuda device, i.e. 0 or 0,1,2,3 or cpu') parser.add_argument('--single-cls', action='store_true', help='treat as single-class dataset') parser.add_argument('--augment', action='store_true', help='augmented inference') parser.add_argument('--verbose', action='store_true', help='report mAP by class') opt = parser.parse_args() opt.img_size = check_img_size(opt.img_size) opt.save_json = opt.save_json or opt.data.endswith('coco.yaml') opt.data = check_file(opt.data) # check file print(opt)

2.2 设置任务（验证，测试，学习）

# task = 'val', 'test', 'study' if opt.task in ['val','test']: # (default) run normally test(opt.data, opt.weights, opt.batch_size, opt.img_size, opt.conf_thres, opt.iou_thres, opt.save_json, opt.single_cls, opt.augment, opt.verbose) elif opt.task == 'study': # run over a range of settings and save/plot for weights in ['yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt']: f = 'study_%s_%s.txt' % (Path(opt.data).stem, Path(weights).stem) # filename to save to x = list(range(288, 896, 64)) # x axis y = [] # y axis for i in x: # img-size print('\nRunning %s point %s...' % (f, i)) r, _, t = test(opt.data, weights, opt.batch_size, i, opt.conf_thres, opt.iou_thres, opt.save_json) y.append(r + t) # results and times np.savetxt(f, y, fmt='.4g') # save os.system('zip -r study.zip study_*.txt') # plot_study_txt(f, x) # plot

“study”应该是可以修改预训练权重的操作。

2.3 测试函数

2.3.1 初始化模型

判断模型是否存在，若不存在则训练为假，移除之前的测试结果，下载模型。

# Initialize/load model and set device if model is None: training = False device = torch_utils.select_device(opt.device, batch_size=batch_size) half = device.type != 'cpu' # half precision only supported on CUDA # Remove previous for f in glob.glob('test_batch*.jpg'): os.remove(f) # Load model google_utils.attempt_download(weights) model = torch.load(weights, map_location=device)['model'].float() # load to FP32 torch_utils.model_info(model) model.fuse() model.to(device) if half: model.half() # to FP16 # Multi-GPU disabled, incompatible with .half() # if device.type != 'cpu' and torch.cuda.device_count() > 1: # model = nn.DataParallel(model) else: # called by train.py training = True device = next(model.parameters()).device # get model device # half disabled https://github.com/ultralytics/yolov5/issues/99 half = False # device.type != 'cpu' and torch.cuda.device_count() == 1 if half: model.half() # to FP16

2.3.2 判断设备类型并仅使用一张GPU进行测试

判断设备类型并仅仅单GPU支持一半的精度。

# Half half = device.type != 'cpu' and torch.cuda.device_count() == 1 # half precision only supported on single-GPU if half: model.half() # to FP16

2.3.3 获取配置文件路径和文件参数

获取配置文件yaml中的nc参数。

# Configure model.eval() with open(data) as f: data = yaml.load(f, Loader=yaml.FullLoader) # model dict nc = 1 if single_cls else int(data['nc']) # number of classes iouv = torch.linspace(0.5, 0.95, 10).to(device) # iou vector for mAP@0.5:0.95 niou = iouv.numel()

2.3.4 数据获取

测试数据的获取使用NMS初始化图片大小获取测试或验证图片路径用梯度下降运行模型、计算损失和运行NMS计算每张测试图片的数据并保存到json文件中画出某几张batch图片（包括GT和预测） # Dataloader if dataloader is None: # not training merge = opt.merge # use Merge NMS 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 path = data['test'] if opt.task == 'test' else data['val'] # path to val/test images dataloader = create_dataloader(path, imgsz, batch_size, int(max(model.stride)), opt, hyp=None, augment=False, cache=False, pad=0.5, rect=True)[0] seen = 0 names = model.names if hasattr(model, 'names') else model.module.names coco91class = coco80_to_coco91_class() s = (' s' + 's' * 6) % ('Class', 'Images', 'Targets', 'P', 'R', 'mAP@.5', 'mAP@.5:.95') p, r, f1, mp, mr, map50, map, t0, t1 = 0., 0., 0., 0., 0., 0., 0., 0., 0. loss = torch.zeros(3, device=device) jdict, stats, ap, ap_class = [], [], [], [] for batch_i, (img, targets, paths, shapes) in enumerate(tqdm(dataloader, desc=s)): img = 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 targets = targets.to(device) nb, _, height, width = img.shape # batch size, channels, height, width whwh = torch.Tensor([width, height, width, height]).to(device) # Disable gradients with torch.no_grad(): # Run model t = torch_utils.time_synchronized() inf_out, train_out = model(img, augment=augment) # inference and training outputs t0 += torch_utils.time_synchronized() - t # Compute loss if training: # if model has loss hyperparameters loss += compute_loss([x.float() for x in train_out], targets, model)[1][:3] # GIoU, obj, cls # Run NMS t = torch_utils.time_synchronized() output = non_max_suppression(inf_out, conf_thres=conf_thres, iou_thres=iou_thres, merge=merge) t1 += torch_utils.time_synchronized() - t # Statistics per image for si, pred in enumerate(output): labels = targets[targets[:, 0] == si, 1:] nl = len(labels) tcls = labels[:, 0].tolist() if nl else [] # target class seen += 1 if pred is None: if nl: stats.append((torch.zeros(0, niou, dtype=torch.bool), torch.Tensor(), torch.Tensor(), tcls)) continue # Append to text file # with open('test.txt', 'a') as file: # [file.write('.5g' * 7 % tuple(x) + '\n') for x in pred] # Clip boxes to image bounds clip_coords(pred, (height, width)) # Append to pycocotools JSON dictionary if save_json: # [{"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236}, ... image_id = int(Path(paths[si]).stem.split('_')[-1]) box = pred[:, :4].clone() # xyxy scale_coords(img[si].shape[1:], box, shapes[si][0], shapes[si][1]) # to original shape box = xyxy2xywh(box) # xywh box[:, :2] -= box[:, 2:] / 2 # xy center to top-left corner for p, b in zip(pred.tolist(), box.tolist()): jdict.append({'image_id': image_id, 'category_id': coco91class[int(p[5])], 'bbox': [round(x, 3) for x in b], 'score': round(p[4], 5)}) # Assign all predictions as incorrect correct = torch.zeros(pred.shape[0], niou, dtype=torch.bool, device=device) if nl: detected = [] # target indices tcls_tensor = labels[:, 0] # target boxes tbox = xywh2xyxy(labels[:, 1:5]) * whwh # Per target class for cls in torch.unique(tcls_tensor): ti = (cls == tcls_tensor).nonzero().view(-1) # prediction indices pi = (cls == pred[:, 5]).nonzero().view(-1) # target indices # Search for detections if pi.shape[0]: # Prediction to target ious ious, i = box_iou(pred[pi, :4], tbox[ti]).max(1) # best ious, indices # Append detections for j in (ious > iouv[0]).nonzero(): d = ti[i[j]] # detected target if d not in detected: detected.append(d) correct[pi[j]] = ious[j] > iouv # iou_thres is 1xn if len(detected) == nl: # all targets already located in image break # Append statistics (correct, conf, pcls, tcls) stats.append((correct.cpu(), pred[:, 4].cpu(), pred[:, 5].cpu(), tcls)) # Plot images if batch_i < 1: f = 'test_batch%g_gt.jpg' % batch_i # filename plot_images(img, targets, paths, f, names) # ground truth f = 'test_batch%g_pred.jpg' % batch_i plot_images(img, output_to_target(output, width, height), paths, f, names) # predictions

2.3.5 计算map数据

# Compute statistics stats = [np.concatenate(x, 0) for x in zip(*stats)] # to numpy if len(stats): p, r, ap, f1, ap_class = ap_per_class(*stats) p, r, ap50, ap = p[:, 0], r[:, 0], ap[:, 0], ap.mean(1) # [P, R, AP@0.5, AP@0.5:0.95] mp, mr, map50, map = p.mean(), r.mean(), ap50.mean(), ap.mean() nt = np.bincount(stats[3].astype(np.int64), minlength=nc) # number of targets per class else: nt = torch.zeros(1)

2.3.5 打印结果（图片，速度），保存结果至json，并返回结果

# Print results pf = ' s' + '.3g' * 6 # print format print(pf % ('all', seen, nt.sum(), mp, mr, map50, map)) # Print results per class if verbose and nc > 1 and len(stats): for i, c in enumerate(ap_class): print(pf % (names[c], seen, nt[c], p[i], r[i], ap50[i], ap[i])) # Print speeds t = tuple(x / seen * 1E3 for x in (t0, t1, t0 + t1)) + (imgsz, imgsz, batch_size) # tuple if not training: print('Speed: %.1f/%.1f/%.1f ms inference/NMS/total per %gx%g image at batch-size %g' % t) # Save JSON if save_json and map50 and len(jdict): imgIds = [int(Path(x).stem.split('_')[-1]) for x in dataloader.dataset.img_files] f = 'detections_val2017_%s_results.json' % \ (weights.split(os.sep)[-1].replace('.pt', '') if weights else '') # filename print('\nCOCO mAP with pycocotools... saving %s...' % f) with open(f, 'w') as file: json.dump(jdict, file) try: from pycocotools.coco import COCO from pycocotools.cocoeval import COCOeval # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb cocoGt = COCO(glob.glob('../coco/annotations/instances_val*.json')[0]) # initialize COCO ground truth api cocoDt = cocoGt.loadRes(f) # initialize COCO pred api cocoEval = COCOeval(cocoGt, cocoDt, 'bbox') cocoEval.params.imgIds = imgIds # image IDs to evaluate cocoEval.evaluate() cocoEval.accumulate() cocoEval.summarize() map, map50 = cocoEval.stats[:2] # update results (mAP@0.5:0.95, mAP@0.5) except: print('WARNING: pycocotools must be installed with numpy==1.17 to run correctly. ' 'See https://github.com/cocodataset/cocoapi/issues/356') # Return results model.float() # for training maps = np.zeros(nc) + map for i, c in enumerate(ap_class): maps[c] = ap[i] return (mp, mr, map50, map, *(loss.cpu() / len(dataloader)).tolist()), maps, t