[Feature] Release new fp16-dcn models ( mask-rcnn DCN/DCNv2) #5201
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Outdated suggestions cannot be applied.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.
Motivation
Release mask_rcnn_r50_fpn_fp16_dconv_c3-c5_1x_coco and mask_rcnn_r50_fpn_fp16_mdconv_c3-c5_1x_coco,
including config files, models and log files.
it is based on open-mmlab/mmcv#1029.
Modification
Add two config files.
Release models.
Modify the readme file.
BC-breaking (Optional)
If pytorch >= 1.6.0 with that the mmcv version is larger than 1.3.2 and before open-mmlab/mmcv#1029 merged, there will be a type mismatch bug in fp16 training.