competition-centernetv2 #5861
Closed
competition-centernetv2 #5861
Conversation
This file contains hidden or 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
|
|
Results the repetition
|
@huimlight So you don't multiply rpn score with rcnn score when training? |
no, I multiply. This code in cascade_roi_head.py |
|
很棒的工作，什么时候可以合入啊？ |
It's not multiplied in training based on what I see. In fact, the rpn score is not used to calculate rcnn loss in the official implemenation either. |
| def _init_predictor(self): | ||
| """Initialize predictor layers of the head.""" | ||
| self.conv_reg = nn.Conv2d(self.feat_channels, 4, 3, padding=1) | ||
| self.agn_hm = nn.Conv2d(self.in_channels, 1, 3, stride=1, padding=1) |
There was a problem hiding this comment.
Seems did not use num_classes? should we set num_classes=1 in config file?
| num_points * 4. | ||
| agn_hms (list[Tensor]): Box scores for each scale level, \ | ||
| each is a 4D-tensor, the channel number is \ | ||
| num_points * num_classes. |
There was a problem hiding this comment.
Please check the output shape, is num_points * num_classes or num_points * 1?
|
closed as it has been continued in #9566 |
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Outdated suggestions cannot be applied.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.
Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.
Motivation
Learn Centernetv2, learn MMDET.
Modification
Code: we add detector in mmdet/models/detectors/centernetv2.py.
Code: we add config in configs/centernetv2/centernet2.py.
Code: we add centernet_head in mmdet/dense_heads/centernet_headv2.py.
Code: we add hm_binary_focal_loss in mmdet/losses/hm_binary_focal_loss.py.
Code: we modify mmdet/roi_heads/cascade_roi_head.py, add the super parameter add_agnostic_score to Control whether the first stage score.This hyperparameter does not affect the use of other configuration files
Code: we modify mmdet/bbox_head/bbox_head.py, add the super parameter add_agnostic_score to Control Whether to use softmax.This hyperparameter does not affect the use of other configuration files
BC-breaking (Optional)
Does the modification introduce changes that break the backward-compatibility of the downstream repos?
No
Use cases (Optional)
If this PR introduces a new feature, it is better to list some use cases here, and update the documentation.
Checklist