Closed Clayne2027 closed 8 months ago
We used the hdf5
file formate as our machine had a very slow disk-cpu communication speed. If that's not the case for you, you can simply use PyTorch's ImageFolder to load your ImageNet dataset as in this link. Let me know if you still have issues with data loading.
Best, Sang
thanks a lot, i have solved this problem by using the ImageFolder class
Glad that you solved the issue. Let me know if you have other questions. I am closing the issue for now.
the code of create_hdf5.py can not be ran successfully, assert len(fnames) == num_ex, how can i fix this problem?