Fix Errors; Now runnable with PyTorch LTS 1.8.2 with Ubuntu 20.04, CUDA 11.1, and CUDNN 8.0.5 (NOTE BELOW) #22
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…r bpl; change groupnorm to layernorm; use apex;
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
NOTE that apply_nms is replaced with the torchvision nms function. This is incomplete because nms doesn't come with the pre- and post-top_k filtering in the original apply_nms. The eval_predcls constrained mR@50 I have reproduced after training is 18.88 (a little less than 19.3) but I suspect the pre-k and post-k could be one reason. If I have time down the road I will try to replicate that function exactly.