I thought I’d be great if for fastai_v1 the pretrained models were trained on the “open images v4” dataset instead of imagenet.
Open images is bigger and has more classes which might make the transfer learning work even better
Imagenet is not very diverse/inclusive, open images is supposed to be better
Tweet from Rachel
I think there is a blog post about that but can’t find it
Open images is very big
Training many models might be expensive
Any thoughts on this?