Code Release of ECCV 2020 Spotlight paper for Side-Aware Boundary Localization for More Precise Object Detection #3603
Conversation
This file contains 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
|
Unit tests are missing. |
ZwwWayne
reviewed
Aug 23, 2020
ZwwWayne
reviewed
Aug 23, 2020
ZwwWayne
reviewed
Aug 23, 2020
ZwwWayne
reviewed
Aug 23, 2020
ZwwWayne
reviewed
Aug 23, 2020
hellock
reviewed
Aug 23, 2020
| return decoded_bboxes | ||
|
|
||
|
|
||
| def generat_buckets(proposals, bucket_num, scale_factor=1.0): |
There was a problem hiding this comment.
Follow the naming conventions: bucket_num -> num_buckets
| scale_factor (float): Scale factor to rescale proposals. | ||
| offset_topk (int): Topk buckets are used to generate \ | ||
| bucket fine regression targets. Defaults to 2. | ||
| offset_allow (float): Offset allowance to generate \ |
There was a problem hiding this comment.
We may consider a more comprehensive variable name.
| # generate bucket labels and weight | ||
| side_num = int(np.ceil(bucket_num / 2.0)) | ||
| labels = torch.cat([ | ||
| l_label[:, 0][:, None], r_label[:, 0][:, None], t_label[:, 0][:, None], |
There was a problem hiding this comment.
labels = torch.stack([l_label[:, 0], r_label[:, 0], t_label[:, 0], d_label[:, 0]], dim=-1)| self.reg_pos_conv_xs[i].init_weights() | ||
| self.reg_pos_conv_ys[i].init_weights() | ||
| nn.init.normal_(self.reg_conv_att_x.weight, 0, 0.01) | ||
| nn.init.constant_(self.reg_conv_att_x.bias, 0) |
There was a problem hiding this comment.
Use the init methods in mmcv.cnn
| self.reg_pre_convs[i].init_weights() | ||
| for i in range(self.reg_pos_num): | ||
| self.reg_pos_conv_xs[i].init_weights() | ||
| self.reg_pos_conv_ys[i].init_weights() |
There was a problem hiding this comment.
ConvModules are initialized during construction by default.
| reg_fy = (reg_fy * reg_fy_att).sum(dim=3) | ||
| return reg_fx, reg_fy | ||
|
|
||
| def direction_feature_extractor(self, reg_x): |
There was a problem hiding this comment.
Use terms that are consistent with the paper.
| reg_fy = torch.transpose(reg_fy, 1, 2) | ||
| return reg_fx.contiguous(), reg_fy.contiguous() | ||
|
|
||
| def reg_pred(self, x, offfset_fcs, cls_fcs): |
| bucket_offset_targets, bucket_offset_weights) | ||
|
|
||
| def _bucket_target_single(self, pos_proposals, neg_proposals, | ||
| pos_gt_bboxes, pos_gt_labels, cfg): |
Codecov Report
@@ Coverage Diff @@
## master #3603 +/- ##
==========================================
- Coverage 61.31% 61.14% -0.18%
==========================================
Files 213 216 +3
Lines 14531 15187 +656
Branches 2441 2520 +79
==========================================
+ Hits 8910 9286 +376
- Misses 5177 5442 +265
- Partials 444 459 +15
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
ZwwWayne
reviewed
Aug 30, 2020
| Args: | ||
| num_buckets (int): Number of buckets. | ||
| scale_factor (int): Scale factor of proposals to generate buckets. | ||
| offset_topk (int): Topk buckets are used to generate \ |
There was a problem hiding this comment.
'\' is unnecessary here in arguments, we can remove them for simplicity.
ZwwWayne
reviewed
Aug 30, 2020
| self.cls_ignore_neighbor = cls_ignore_neighbor | ||
|
|
||
| def encode(self, bboxes, gt_bboxes): | ||
| """Get bucketing estimation and fine regression targets during |
There was a problem hiding this comment.
It would be better to use standard docstrings here rather than a simple line.
ZwwWayne
reviewed
Aug 30, 2020
hellock
reviewed
Aug 30, 2020
| return bucket_w, bucket_h, l_buckets, r_buckets, t_buckets, d_buckets | ||
|
|
||
|
|
||
| def label2onehot(labels, num_labels): |
hellock
reviewed
Aug 30, 2020
| reg_post_kernel=3, | ||
| reg_pre_num=2, | ||
| reg_post_num=1, | ||
| num_classes=80, |
hellock
approved these changes
Sep 1, 2020
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.
No description provided.