search

dqshuai / MetaFormer

A PyTorch implementation of "MetaFormer: A Unified Meta Framework for Fine-Grained Recognition". A reference PyTorch implementation of “CoAtNet: Marrying Convolution and Attention for All Data Sizes”
MIT License
210 stars 36 forks source link

Some errata found on the code #21

Closed seungwoos closed 2 years ago

seungwoos commented 2 years ago

Hi, Thanks for sharing wonderful work :)

While running the code, I found some minor errata building the data augmentation module.

https://github.com/dqshuai/MetaFormer/blob/669bf18c35fdb51e35b0a79fa86224a18cd38ac5/data/build.py#L16

I guess this line should fixed with from timm.data.transforms import str_to_pil_interp since there is no _pil_interp in timm.data.transforms. https://github.com/rwightman/pytorch-image-models/blob/master/timm/data/transforms.py

If there is something I missed, pleased let me know :)

dqshuai commented 2 years ago

@seungwoos Hi, I think it is the difference of version, and i used timm==0.4.5. https://github.com/rwightman/pytorch-image-models/blob/v0.4.5/timm/data/transforms.py#L43

seungwoos commented 2 years ago

Thank you so much for your reply :)

I used the latest version of timm so that this happened. Thank you.