search

MILVLG / bottom-up-attention.pytorch

A PyTorch reimplementation of bottom-up-attention models
Apache License 2.0
294 stars 76 forks source link

Can I just delete the caffe folder in bua? #91

Open ElegantLin opened 2 years ago

ElegantLin commented 2 years ago

Hi authors, thanks for your great work first. It seems that there is not necessary to keep the caffe folder since it only depends on an older GPU. Can I just delete the caffe folder in bua?

Thanks!

ElegantLin commented 2 years ago

I think I cannot cuz there are some Caffe dependencies in d2.

1219521375 commented 2 years ago

There are some caffe references in train_net.py and extract_features.py, you can delete or comment out it manually.