-
Notifications
You must be signed in to change notification settings - Fork 1
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
Re-Identification Model #141
base: main
Are you sure you want to change the base?
Conversation
…earning (loss). Added custom reID/embedding metrics. Implemented a test to verify trainability, exportability and inference. Removed GhostFaceNetsV2 from the backbone tests as it only generates embeddings instead of the usual features.
Codecov ReportAttention: Patch coverage is
✅ All tests successful. No failed tests found.
Additional details and impacted files@@ Coverage Diff @@
## main #141 +/- ##
==========================================
- Coverage 96.31% 95.31% -1.01%
==========================================
Files 147 178 +31
Lines 6304 7956 +1652
==========================================
+ Hits 6072 7583 +1511
- Misses 232 373 +141 ☔ View full report in Codecov by Sentry. |
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.
Thanks, left some comments
…locks and variants. Added tests for all supported pytorch metric learning losses.
Thanks very much everyone for the review and suggestions. Incorporated everything in, except for the new luxonis-ml nested label changes, as that should probably be done in a different PR. Thoughts? |
Locally, I'm getting
Could it be that I have a wrong version of mdformat? |
…s-train into feat/reid-support
…s-train into feat/reid-support
Original CU Task
Added the GFNv2 backbone for use in re-ID tasks. Added integration with pytorch-metric-learning for ~30 loss functions (customizable) and two custom reID/embedding metrics. Implemented a test to verify trainability, exportability and inference.