WZMIAOMIAO/deep-learning-for-image-processing · error · FileNotFoundError

not found weights file: {}

Error message

not found weights file: {}

What it means

Same guard as error 22 but in Test9's train.py: if --weights is non-empty and os.path.exists fails, main raises FileNotFoundError naming the path. It exists so training never silently starts without the requested EfficientNet pretrained weights.

Source

Thrown at pytorch_classification/Test9_efficientNet/train.py:83

                                               collate_fn=train_dataset.collate_fn)

    val_loader = torch.utils.data.DataLoader(val_dataset,
                                             batch_size=batch_size,
                                             shuffle=False,
                                             pin_memory=True,
                                             num_workers=nw,
                                             collate_fn=val_dataset.collate_fn)

    # 如果存在预训练权重则载入
    model = create_model(num_classes=args.num_classes).to(device)
    if args.weights != "":
        if os.path.exists(args.weights):
            weights_dict = torch.load(args.weights, map_location=device)
            load_weights_dict = {k: v for k, v in weights_dict.items()
                                 if model.state_dict()[k].numel() == v.numel()}
            print(model.load_state_dict(load_weights_dict, strict=False))
        else:
            raise FileNotFoundError("not found weights file: {}".format(args.weights))

    # 是否冻结权重
    if args.freeze_layers:
        for name, para in model.named_parameters():
            # 除最后一个卷积层和全连接层外，其他权重全部冻结
            if ("features.top" not in name) and ("classifier" not in name):
                para.requires_grad_(False)
            else:
                print("training {}".format(name))

    pg = [p for p in model.parameters() if p.requires_grad]
    optimizer = optim.SGD(pg, lr=args.lr, momentum=0.9, weight_decay=1E-4)
    # Scheduler https://arxiv.org/pdf/1812.01187.pdf
    lf = lambda x: ((1 + math.cos(x * math.pi / args.epochs)) / 2) * (1 - args.lrf) + args.lrf  # cosine
    scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf)

    for epoch in range(args.epochs):
        # train

View on GitHub (pinned to 1ec3fe6f37)

Solutions

1. Generate/download the weights file (run trans_weights_to_pytorch.py) and pass the existing path via --weights
2. Pass --weights "" to train from scratch instead
3. Use an absolute path or cd into the Test9_efficientNet directory before running

Example fix

// before
python train.py --weights ./efficientnetb0.pth   # not in cwd
// after
cd pytorch_classification/Test9_efficientNet
python train.py --weights ./efficientnetb0.pth   # or absolute path

if args.weights and not os.path.exists(args.weights):
    import sys; sys.exit(f'missing weights: {args.weights}')

try:
    main()
except FileNotFoundError as e:
    print('Run trans_weights_to_pytorch.py to generate weights, or pass --weights "":', e)

When it happens

Trigger: python train.py --weights <path> where the EfficientNet .pth (e.g. efficientnetb0.pth converted from TF) was never downloaded, was renamed, or the path is relative to the wrong cwd.

Common situations: Missing the step that runs trans_weights_to_pytorch.py to produce the .pth; running from repo root while weights sit in Test9_efficientNet/; typos in filename.

Related errors

• not found weights file: {}
• not found weights file: {}
• not found weights file: {}
• not found weights file: {}
• not found weights file: {}

AI-assisted analysis of WZMIAOMIAO/deep-learning-for-image-processing@1ec3fe6f37 (2026-08-30). Data as JSON: /api/errors/a7e5986aa7753c78. Report an issue: GitHub.