rmcavoy

Yes, only the BiFPN and the RetinaHead. The backbone EfficientNet remains unchanged versus what is there currently.

@dkoguciuk Yep I discovered that as well but forgot to update this post.

The clamp function probably improves stability in some cases but is very much unnecessary as you can switch to using the "with logits" version of the focal loss as is...

Yes unfortunately but it can be used to correct the numerous problems with all the public PyTorch implementations. Like for example, the original tensorflow code has three convolution layers per...

The tensorflow code also confirmed my assumption that every convolution in the fpn+box network is either 1x1 or depthwise separable

Unfortunately my ability to directly contribute code to open source repos is limited by my work (pretty sure I would need to do various kinds of paperwork for approval of...

@turner-rovco That is a separate issue yes but it is one of the other things that needs to be fixed along with switching to depthwise separable convolutions and ensuring there...

@tadbeer Did you remove the problem where the maker of this repo accidentally randomized all the weights in the backbone after loading the pretrained weights? This error makes it nearly...

Any plans to update this merge?