-
Notifications
You must be signed in to change notification settings - Fork 1.6k
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 mg_head #49
Add mg_head #49
Conversation
Codecov Report
@@ Coverage Diff @@
## master #49 +/- ##
==========================================
- Coverage 51.53% 51.08% -0.45%
==========================================
Files 140 144 +4
Lines 8521 8958 +437
Branches 1323 1388 +65
==========================================
+ Hits 4391 4576 +185
- Misses 3850 4091 +241
- Partials 280 291 +11
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
@@ -733,14 +729,8 @@ def get_task_detections(self, num_class_with_bg, batch_cls_preds, | |||
box_preds = box_preds.float() |
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.
Are 729 -730 necessary?
# encode background as first element in one-hot vector | ||
total_scores = torch.sigmoid(cls_preds)[..., 1:] | ||
# total_scores = torch.sigmoid(cls_preds) | ||
total_scores = cls_preds |
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.
If they are the same, we may skip this assignment and only use cls_preds
in the following code
* first * fix0 * fix1 * dirty work * wip * add allocator * finally done! * lint * fix lint * better gather * better onnx2ncnn * fix expand * [Fix] NCNN TensorSlice op bugs (open-mmlab#42) * fix custom ops support, fix multiple mark bug, add name mapping * check if the value_info need to be added * remove unnecessary print * add nms implement * two stage split wip * add two stage split * add split retinanet visualize * add two stage split (wip) * finish two stage split * fix lint * move parse string to mmdeploy.utils * add calib data generator * create calib dataset * finish end2end int8 * add split two stage tensorrt visualize * fix tensorslice bugs * fix lint * fix clang-format * remove comments * int param * fix lint Co-authored-by: grimoire <[email protected]> * add two stage ncnn support * remove unused ops * git unused config * remove no_grad, should add in refactor * add ncnn wrapper * fix lint * size return tuple * Resolve grammar error * Fix lint * Trim Trailing Whitespace * fix trim * update wrapper * remove logs * remove * csrc optimize Co-authored-by: hanrui1sensetime <[email protected]>
Add CenterHead and related module.