def save_model(model, is_best, best_mAP): save_checkpoint( { 'state_dict': model.state_dict(), 'epoch': epoch + 1, 'best_mAP': best_mAP, }, is_best, fpath=osp.join(args.logs_dir, 'checkpoint.pth.tar'))
def save_model(model_ema, is_best, best_mAP, mid): save_checkpoint( { 'state_dict': model_ema.state_dict(), 'epoch': epoch + 1, 'best_mAP': best_mAP, }, is_best, fpath=osp.join(args.logs_dir, 'model' + str(mid) + '_checkpoint.pth.tar'))
def main_worker(args): global start_epoch, best_mAP cudnn.benchmark = True if not args.evaluate: sys.stdout = Logger(osp.join(args.logs_dir, 'log.txt')) else: log_dir = osp.dirname(args.resume) sys.stdout = Logger(osp.join(log_dir, 'log_test.txt')) print("==========\nArgs:{}\n==========".format(args)) # Create data loaders iters = args.iters if (args.iters > 0) else None dataset_source, num_classes, train_loader_source = \ get_data(args.dataset_source, args.data_dir, args.height, args.width, args.batch_size, args.workers, args.num_instances, iters) dataset_target, _, train_loader_target = \ get_data(args.dataset_target, args.data_dir, args.height, args.width, args.batch_size, args.workers, args.num_instances, iters) dataset_validation, test_loader_target = \ get_test_data(args.dataset_validation, args.data_dir, args.height, args.width, args.batch_size, args.workers) # Create model model = models.create(args.arch, dropout=args.dropout, num_classes=num_classes, circle=args.circle) # print(model) print("Model size: {:.3f} M".format(count_num_param(model))) model.cuda() model = nn.DataParallel(model) # 多gpu并行 # Load from checkpoint if args.resume: checkpoint = load_checkpoint(args.resume) copy_state_dict(checkpoint['state_dict'], model) start_epoch = checkpoint['epoch'] best_mAP = checkpoint['best_mAP'] print("=> Start epoch {} best mAP {:.1%}".format( start_epoch, best_mAP)) # Evaluator evaluator = Evaluator(model) if args.evaluate: # print("Test on source domain:") # evaluator.evaluate(test_loader_source, dataset_source.query, dataset_source.gallery, cmc_flag=True, # rerank=args.rerank) print("Test on target domain:") evaluator.evaluate(test_loader_target, dataset_target.query, dataset_target.gallery, cmc_flag=True, rerank=args.rerank) return params = [] for key, value in model.named_parameters(): if not value.requires_grad: continue params += [{ "params": [value], "lr": args.lr, "weight_decay": args.weight_decay }] optimizer = torch.optim.Adam(params) lr_scheduler = WarmupMultiStepLR(optimizer, args.milestones, gamma=0.1, warmup_factor=0.01, warmup_iters=args.warmup_step) # Trainer trainer = PreTrainer(model, num_classes, args, margin=args.margin) # Start training for epoch in range(start_epoch, args.epochs): lr_scheduler.step() train_loader_source.new_epoch() # train_loader_target.new_epoch() trainer.train(epoch, train_loader_source, optimizer, train_iters=len(train_loader_source), print_freq=args.print_freq, balance=args.balance) if (epoch + 1) % args.eval_step == 0 or (epoch == args.epochs - 1): _, mAP = evaluator.evaluate(test_loader_target, dataset_validation.query, dataset_validation.gallery, cmc_flag=True) is_best = mAP > best_mAP best_mAP = max(mAP, best_mAP) save_checkpoint( { 'state_dict': model.state_dict(), 'epoch': epoch + 1, 'best_mAP': best_mAP, }, is_best, fpath=osp.join(args.logs_dir, 'checkpoint.pth.tar')) print( '\n * Finished epoch {:3d} source mAP: {:5.1%} best: {:5.1%}{}\n' .format(epoch, mAP, best_mAP, ' *' if is_best else '')) print("Test on target domain:") evaluator.evaluate(test_loader_target, dataset_validation.query, dataset_validation.gallery, cmc_flag=True, rerank=args.rerank)