-
Notifications
You must be signed in to change notification settings - Fork 1.2k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Refactor] refactor multiview humanpose #1196
Conversation
wusize seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account. You have signed the CLA already but the status is still pending? Let us recheck it. |
Codecov Report
@@ Coverage Diff @@
## master #1196 +/- ##
==========================================
+ Coverage 82.25% 83.01% +0.75%
==========================================
Files 204 204
Lines 16193 16192 -1
Branches 2891 2892 +1
==========================================
+ Hits 13319 13441 +122
+ Misses 2143 2012 -131
- Partials 731 739 +8
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
Need more detailed code comments. |
@@ -115,12 +115,11 @@ | |||
type='V2VNet', input_channels=num_joints, output_channels=1), | |||
center_head=dict( | |||
type='CuboidCenterHead', | |||
cfg=dict( |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The config should be consistent with the model definition, for example, the type
of model here should be DetectAndRegress
instead of VoxelPose
. Check other fields that need to be modified.
* 'multiview_pose' * 'single_pose' * multiview_pose_detect_and_regress * unit test * typo * typo * unit test * del old codes * del old codes * 'fix_test_bug' * 'accuray_test' * fix input_heatmaps * stay consistent with official voxelpose model keys * fix lint * add comments Co-authored-by: wusize <wusize@sensetime.com> Co-authored-by: liqikai <tiger19971215@sjtu.edu.cn>
* 'multiview_pose' * 'single_pose' * multiview_pose_detect_and_regress * unit test * typo * typo * unit test * del old codes * del old codes * 'fix_test_bug' * 'accuray_test' * fix input_heatmaps * stay consistent with official voxelpose model keys * fix lint * add comments Co-authored-by: wusize <wusize@sensetime.com> Co-authored-by: liqikai <tiger19971215@sjtu.edu.cn>
* 'multiview_pose' * 'single_pose' * multiview_pose_detect_and_regress * unit test * typo * typo * unit test * del old codes * del old codes * 'fix_test_bug' * 'accuray_test' * fix input_heatmaps * stay consistent with official voxelpose model keys * fix lint * add comments Co-authored-by: wusize <wusize@sensetime.com> Co-authored-by: liqikai <tiger19971215@sjtu.edu.cn>
Motivation
Re-organize the framework of VoxelPose into a more general detect-and-regress approach.
Modification
mmpose/models/detectors/multiview_pose.py
tests/test_models/test_multiview_pose.py
BC-breaking (Optional)
Use cases (Optional)
Checklist
Before PR:
After PR: