search

mit-han-lab / once-for-all

[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment
https://ofa.mit.edu/
MIT License
1.89k stars 333 forks source link

args.valid_size is wrong? #39

Closed gegeo0 closed 3 years ago

gegeo0 commented 3 years ago

Looks like args.valid_size in train_ofa_net.py is set to 10000. Is that right? Seems to me that target size is much smaller than that (~200)

once-for-all/ofa/imagenet_classification/data_providers/base_provider.py", line 42, in random_sample_valid_set assert train_size > valid_size

gegeo0 commented 3 years ago

nvm, I was using a smaller dataset, that is why I was getting errors