Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

RuntimeError: MiniImagenet integrity check failed #5

Open
lgc-china opened this issue Nov 25, 2024 · 0 comments
Open

RuntimeError: MiniImagenet integrity check failed #5

lgc-china opened this issue Nov 25, 2024 · 0 comments

Comments

@lgc-china
Copy link

Traceback (most recent call last):
File "D:\Code\PycharmCode\CVPR23-GAP-main\main.py", line 50, in
train(args)
File "D:\Code\PycharmCode\CVPR23-GAP-main\train.py", line 18, in train
meta_train_dataset, meta_val_dataset, meta_test_dataset = get_dataset(args.dataset, args.folder, args.N_ways, args.K_shots_for_support, args.K_shots_for_query, args.download, train_transform, test_transform)
File "D:\Code\PycharmCode\CVPR23-GAP-main\dataset.py", line 8, in get_dataset
meta_train_dataset = miniimagenet(folder, shots=K_shots_for_support, ways=N_ways, shuffle=True, test_shots=K_shots_for_query, meta_train=True, download=download, transform=train_transform)
File "D:\Code\PycharmCode\CVPR23-GAP-main\datasets\helpers.py", line 134, in miniimagenet
return helper_with_default(MiniImagenet, folder, shots, ways,
File "D:\Code\PycharmCode\CVPR23-GAP-main\datasets\helpers.py", line 43, in helper_with_default
dataset = klass(folder, num_classes_per_task=ways, **kwargs)
File "C:\Users\LGC\anaconda3\envs\GAP-master\lib\site-packages\torchmeta\datasets\miniimagenet.py", line 87, in init
dataset = MiniImagenetClassDataset(root, meta_train=meta_train,
File "C:\Users\LGC\anaconda3\envs\GAP-master\lib\site-packages\torchmeta\datasets\miniimagenet.py", line 127, in init
raise RuntimeError('MiniImagenet integrity check failed')
RuntimeError: MiniImagenet integrity check failed

The reason for this error is that I am missing the train_data.hdf5 file
then,i try set args.download=True
However, an error message shows that the download link no longer exists.
How should I get train_data.hdf5 files

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant