Evaluation / Testing data

I want to evaluate a basic imagenet data, although i have downloaded config files and pretrained models from the github site provided, i get following error. I tried to use ImageNet-1K data, i could not find the imagenet_full_size/061417/ data. Can you please provide more infrmation about how to test / evaluate data using welknown imagenet dataset. Or can your provide any support file / info for imagenet_full_size/061417/

File "/home/ayhan/jepa/evals/image_classification_frozen/eval.py", line 363, in load_pretrained
pretrained_dict = checkpoint['encoder']
KeyError: 'encoder'

Thank you.

Start with evals/image_classification_frozen/eval.py, especially load_pretrained at line 363, and inspect the expected checkpoint structure around the access to checkpoint['encoder']. Compare that expectation with the downloaded pretrained model and the ImageNet-1K data layout, including the missing imagenet_full_size/061417/ path. Done means the evaluation procedure and required files are identified well enough to run the ImageNet evaluation.

Written by the indexing model from the issue text.