I thought I’d be great if for fastai_v1 the pretrained models were trained on the “open images v4” dataset instead of imagenet.
Reasons:
-
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
Drawbacks:
Open images is very big
Training many models might be expensive
Any thoughts on this?