[Fix] Fix reppoints TensorRT support. #1060
Merged
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
added 2 commits
September 16, 2022 19:23
There was a problem hiding this comment.
In my env:
torch 1.10.0 + cu113
tensorrt 8.4.2.4
This conversion will failed on onnx2tensorrt.
[TRT] [W] Skipping tactic 0x0000000000000000 due to Myelin error: autotuning: CUDA error 3 allocating 0-byte buffer:
[09/27/2022-11:10:30] [TRT] [E] 4: [optimizer.cpp::computeCosts::3624] Error Code 4: Internal Error (Could not find any implementation for node {ForeignNode[Transpose_600 + Reshape_603...Gather_1063]} due to insufficient workspace. See verbose log for requested sizes.)
|
LGTM. |
hanrui1sensetime
approved these changes
Oct 18, 2022
tpoisonooo
approved these changes
Oct 27, 2022
| # TODO: figure out why we can't reshape after permute deirectly | ||
| bbox_pred = bbox_pred.permute(0, 2, 3, 1) | ||
| bbox_pred = bbox_pred.reshape(batch_size, -1) | ||
| bbox_pred = (bbox_pred + 0).reshape(batch_size, -1, 4) |
| @@ -115,7 +118,11 @@ def reppoints_head__get_bboxes(ctx, | |||
| scores = scores.sigmoid() | |||
| else: | |||
| scores = scores.softmax(-1) | |||
| bbox_pred = bbox_pred.permute(0, 2, 3, 1).reshape(batch_size, -1, 4) | |||
|
|
|||
| # TODO: figure out why we can't reshape after permute deirectly | |||
There was a problem hiding this comment.
deirectly --> directly
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## master #1060 +/- ##
=======================================
Coverage 47.71% 47.72%
=======================================
Files 323 323
Lines 11312 11314 +2
Branches 1619 1619
=======================================
+ Hits 5398 5400 +2
Misses 5526 5526
Partials 388 388
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. |
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.
Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily receiving feedbacks. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.
Motivation
Reppoint give wrong result on latest TensorRT.
Modification
Reshape twice.
BC-breaking (Optional)
Does the modification introduce changes that break the backward-compatibility of the downstream repositories?
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