-
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
add temporal head and MPJPELoss #522
Conversation
cherryjm
commented
Mar 16, 2021
•
edited
Loading
edited
- add temporal head
- add MPJPELoss for 3D pose estimation
Codecov Report
@@ Coverage Diff @@
## master #522 +/- ##
==========================================
+ Coverage 81.16% 81.23% +0.07%
==========================================
Files 139 140 +1
Lines 9572 9647 +75
Branches 1530 1537 +7
==========================================
+ Hits 7769 7837 +68
- Misses 1458 1464 +6
- Partials 345 346 +1
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
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.
It looks good to me.
The code is clean. An important thing is to make sure that the flip op correctly changes all affected coordinates. |
- "target_image_path": path to the image file | ||
output (np.ndarray[N, K, 3]): predicted regression vector. | ||
""" | ||
target_image_paths = [] |
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.
Save a few lines by
target_image_paths = [m['target_image_path'] for m in metas]
* resolve comments * update changelog * patch for Issue open-mmlab#522 * fix bug * fix bug