[ONNX] Scripting nms on boxes to dynamically export detection/no detection #2052
Conversation
This file contains hidden or 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
fmassa
requested changes
Apr 3, 2020
…of/fixNoDetection # Conflicts: # torchvision/models/detection/transform.py
facebook-github-bot
pushed a commit
to pytorch/pytorch
that referenced
this pull request
Apr 28, 2020
Summary: These two ops are needed for torchvision model export. Since we're scripting a part of the code for dynamic export of models (in pytorch/vision#2052), these two changes are requited. Pull Request resolved: #36501 Reviewed By: hl475 Differential Revision: D21260721 Pulled By: houseroad fbshipit-source-id: 86d9d38665a4a36d22cec741012d976e5bd8d36b
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
The code has two different flows in batched_nms function for images with detection, vs, images with no detection. In order to be able to export a model that supports both, we need to script this function.