[Enhancement] Accelerate Associative Embedding inference #1102
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
* use offical markdownlint hook * add lint.yml * add circleci config * Updated config.yml * Updated config.yml * Updated config.yml * Updated config.yml
* update fap (#1070) * fix a bug in post_dark_udp * fix a bug in post_dark_udp * Modified a bad comment * add unit test for udp * add unit test for udp * use numpy instead math for math ops * fix lint Co-authored-by: Jas <jinsheng@sensetime.com> Co-authored-by: quyang <quyang@qiyi.com> Co-authored-by: ly015 <liyining0712@gmail.com>
* [Enhancement] inference speed and flops tools. (#986) * add the function to test the dummy forward speed of models. * add tools to test the flops and inference speed of multiple models. * [Feature] Add ViPNAS models for wholebody keypoint detection (#1009) * add configs * add dark configs * add checkpoint and readme * update webcam demo * fix model path in webcam demo * fix unittest * update model metafiles (#1001) * [Feature] Add ViPNAS mbv3 (#1025) * add vipnas mbv3 * test other variants * submission for mmpose * add unittest * add readme * update .yml * fix lint * rebase * fix pytest Co-authored-by: jin-s13 <jinsheng13@foxmail.com> * add cfg file for flops and speed test, change the bulid_posenet to init_pose_model and fix some typo in cfg (#1028) * Skip CI when some specific files were changed (#1041) * add voxelpose * unit test * unit test * unit test * add docs/ckpts * del unnecessary comments * correct typos in comments and docs * Add or modify docs * change variable names * reduce memory cost in test * get person_id * rebase * resolve comments * rebase master * rename cfg files * fix typos in comments Co-authored-by: zengwang430521 <zengwang430521@gmail.com> Co-authored-by: Yining Li <liyining0712@gmail.com> Co-authored-by: Lumin <30328525+luminxu@users.noreply.github.com> Co-authored-by: jin-s13 <jinsheng13@foxmail.com> Co-authored-by: Qikai Li <87690686+liqikai9@users.noreply.github.com> Co-authored-by: QwQ2000 <396707050@qq.com>
* support soft_wing_loss * add unittest for soft wing loss * update model md * update doc
* add adaptive wingloss * move adaptive wingloss to heatmap_loss * match shape in wingloss * rename loss * mean for loss * add configs * fix unittest * rename mse_loss to heatmap_loss * add docs * fix lint Co-authored-by: ly015 <liyining0712@gmail.com>
* fix doc patch1 * fix docstring * fix docstring * fix dataset * fix dataset * fix docstring * resolve warnings * fix multilines
Codecov Report
@@ Coverage Diff @@
## dev-0.22 #1102 +/- ##
===========================================
Coverage ? 82.46%
===========================================
Files ? 203
Lines ? 16069
Branches ? 2862
===========================================
Hits ? 13252
Misses ? 2095
Partials ? 722
Flags with carried forward coverage won't be shown. Click here to find out more. Continue to review full report at Codecov.
|
|
This PR did not show a significant effect on the inference speed in tests. |
HAOCHENYE
added a commit
to HAOCHENYE/mmpose
that referenced
this pull request
Jun 27, 2023
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.
Motivation
Improve the inference speed of bottom-up human pose estimators.
Modification
Re-implement
AssociativeEmbedding.refinewith torch instead of numpy. Accelerate tensor operations and avoid moving large tensors from GPU to CPU.AssociativeEmbedding.parseis also adjusted to fit the changes inAssociativeEmbedding.refine.BC-breaking (Optional)
Use cases (Optional)
Checklist
Before PR:
After PR: