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

how to use the model to eval the imagenet1K #74

Open
neverstoplearn opened this issue Apr 20, 2023 · 0 comments
Open

how to use the model to eval the imagenet1K #74

neverstoplearn opened this issue Apr 20, 2023 · 0 comments

Comments

@neverstoplearn
Copy link

2023-04-20 11:41:29 - LOGS - Random seeds are set to 0
2023-04-20 11:41:29 - LOGS - Using PyTorch version 1.12.0+cu102
2023-04-20 11:41:29 - LOGS - Available GPUs: 1
2023-04-20 11:41:29 - LOGS - CUDNN is enabled
2023-04-20 11:41:29 - LOGS - Directory created at: classification_results/train
Traceback (most recent call last):
File "/data/xxx/miniconda3/envs/torch112/bin/cvnets-eval", line 33, in
sys.exit(load_entry_point('cvnets', 'console_scripts', 'cvnets-eval')())
File "/data/xxx/ml-cvnets/main_eval.py", line 143, in main_worker
main(opts=opts, **kwargs)
File "/data/xxx/ml-cvnets/main_eval.py", line 27, in main
val_loader = create_eval_loader(opts)
File "/data/xxx/ml-cvnets/data/data_loaders.py", line 20, in create_eval_loader
eval_dataset = evaluation_datasets(opts)
File "/data/xxx/ml-cvnets/data/datasets/init.py", line 67, in evaluation_datasets
eval_dataset = DATASET_REGISTRY[name_dataset_task](
File "/data/xxx/ml-cvnets/data/datasets/classification/imagenet.py", line 47, in init
ImageFolder.init(
File "/data/xxx/miniconda3/envs/torch112/lib/python3.8/site-packages/torchvision/datasets/folder.py", line 310, in init
super().init(
File "/data/xxx/miniconda3/envs/torch112/lib/python3.8/site-packages/torchvision/datasets/folder.py", line 145, in init
classes, class_to_idx = self.find_classes(self.root)
File "/data/xxx/miniconda3/envs/torch112/lib/python3.8/site-packages/torchvision/datasets/folder.py", line 219, in find_classes
return find_classes(directory)
File "/data/xxx/miniconda3/envs/torch112/lib/python3.8/site-packages/torchvision/datasets/folder.py", line 43, in find_classes
raise FileNotFoundError(f"Couldn't find any class folder in {directory}.")
FileNotFoundError: Couldn't find any class folder in /data/xxx/ml-cvnets/dataset/ImageNet-1K/val.

I download the ImageNet1K datasets, after unzip the dataset, there are train/val/test folder, but only the train folder have class folder, how can i eval the val/test dataset? look forward your help,thanks.

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