Fix device place error in fcn mask head #6374
Merged
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Outdated suggestions cannot be applied.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.
Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.
Motivation
The following error was raised when using
mmdet.apis.inference_detector
run HTC model on CUDA device :Go deeper in the code of
mmdet/models/roi_heads/mask_heads/fcn_mask_head.py
, I found thatscale_factor
is created bytorch.Tensor
in line 248 and compute with boxes in line 252. If the model is on a CUDA device,bboxes
will be also put on the CUDA device. Butscale_factor
created bytorch.Tensor
is on the CPU device. So, a runtime error will be raised when running inference.Modification
Move
scale_factor
to the device ofbboxes
and also cast its dtype.BC-breaking (Optional)
Does the modification introduce changes that break the backward-compatibility of the downstream repos?
If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.
Use cases (Optional)
If this PR introduces a new feature, it is better to list some use cases here, and update the documentation.
Checklist