[Feature] Support classwise weight in losses#388
Merged
mzr1996 merged 10 commits intoopen-mmlab:masterfrom Aug 31, 2021
Merged
Conversation
Codecov Report
@@ Coverage Diff @@
## master #388 +/- ##
==========================================
+ Coverage 76.73% 76.77% +0.03%
==========================================
Files 97 97
Lines 5240 5249 +9
Branches 862 865 +3
==========================================
+ Hits 4021 4030 +9
Misses 1098 1098
Partials 121 121
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
Member
|
Wait for open-mmlab/mmdetection#5776 |
mzr1996
requested changes
Aug 30, 2021
|
|
||
| if self.class_weight is not None: | ||
| class_weight = cls_score.new_tensor( | ||
| self.class_weight, device=cls_score.device) |
Member
There was a problem hiding this comment.
Please handle the warning.
UserWarning: To copy construct from a tensor, it is recommended to use
sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True),
rather than tensor.new_tensor(sourceTensor).
Member
There was a problem hiding this comment.
Here I think we can use to function refers to the docs
Comment on lines
+48
to
+49
| cls_score = torch.Tensor([[-1000, 1000], [100, -100]]) | ||
| label = torch.Tensor([0, 1]).long() |
Member
There was a problem hiding this comment.
In this case, weight and class_weight have the same behavior. I think we need a more representative test sample.
tests/test_metrics/test_losses.py
Outdated
Comment on lines
+105
to
+108
| cls_score = torch.Tensor([[100, -100]]) | ||
| label = torch.Tensor([[1, 0], [0, 1]]) | ||
| weight = torch.tensor(0.5) | ||
| class_weight = torch.tensor(0.25) |
Member
There was a problem hiding this comment.
In soft_cross_entropy, cls_score should share the same shape with label, why they're different here.
And according to label, there should be two samples, but weight only has one item.
Ezra-Yu
added a commit
to zhangrui-wolf/mmclassification
that referenced
this pull request
Sep 7, 2021
* Add classwise weight in losses:CE,BCE,softBCE * Update unit test * rm some extra code * rm some extra code * fix broadcast * fix broadcast * update unit tests * use new_tensor * fix lint
mzr1996
added a commit
that referenced
this pull request
Sep 29, 2021
* Add RepVGG code. * Add se_module as plugin. * Add the repvggA0 primitive config * Change repvggA0.py to fit mmcls * Add RepVGG configs * Add repvgg_to_mmcls * Add tools/deployment/convert_repvggblock_param_to_deploy.py * Change configs/repvgg/README.md * Streamlining the number of configuration files. * Fix lints * Delete plugins * Delete code about plugin. * Modify the code for using se module. * Modify config to fit repvgg with se. * Change se_cfg to allow loading of pre-training parameters. * Reduce the complexity of the configuration file. * Finsh unitest for repvgg. * Fix bug about se in repvgg_to_mmcls. * Rename convert_repvggblock_param_to_deploy.py to reparameterize_repvgg.py, and delete setting about device. * test commit * test commit * test commit command * Modify repvgg.py to make the code more readable. * Add value=0 in F.pad() * Add se_cfg to arch_settings. * Fix bug. * modeify some attr name and Update unit tests * rename stage_0 to stem and branch_identity to branch_norm * update unit tests * add m.eval in unit tests * [Enhance] Enhence SE layer to support custom squeeze channels. (#417) * add enhenced SE * Update * rm basechannel * fix docstring * Update se_layer.py fix docstring * [Docs] Add algorithm readme and update meta yml (#418) * Add README.md for models without checkpoints. * Update model-index.yml * Update metafile.yml of seresnet * [Enhance] Add `hparams` argument in `AutoAugment` and `RandAugment` and some other improvement. (#398) * Add hparams argument in `AutoAugment` and `RandAugment`. And `pad_val` supports sequence instead of tuple only. * Add unit tests for `AutoAugment` and `hparams` in `RandAugment`. * Use smaller test image to speed up uni tests. * Use hparams to simplify RandAugment config in swin-transformer. * Rename augment config name from `pipeline` to `pipelines`. * Add some commnet ad docstring. * [Feature] Support classwise weight in losses (#388) * Add classwise weight in losses:CE,BCE,softBCE * Update unit test * rm some extra code * rm some extra code * fix broadcast * fix broadcast * update unit tests * use new_tensor * fix lint * [Enhance] Better result visualization (#419) * Imporve result visualization to support wait time and change the backend to matplotlib. * Add unit test for visualization * Add adaptive dpi function * Rename `imshow_cls_result` to `imshow_infos`. * Support str in `imshow_infos` * Improve docstring. * Bump version to v0.15.0 (#426) * [CI] Add PyTorch 1.9 and Python 3.9 build workflow, and remove some CI. (#422) * Add PyTorch 1.9 build workflow, and remove some CI. * Add Python 3.9 CI * Show Python 3.9 support. * [Enhance] Rename the option `--options` in some tools to `--cfg-options`. (#425) * [Docs] Fix sphinx version (#429) * [Docs] Add `CITATION.cff` (#428) * Add CITATION.cff * Fix typo in setup.py * Change author in setup.py * modeify some attr name and Update unit tests * rename stage_0 to stem and branch_identity to branch_norm * update unit tests * add m.eval in unit tests * Update unit tests * refactor * refactor * Alignment inference accuracy * Update configs, readme and metafile * Update readme * return tuple and fix metafile * fix unit test * rm regnet and classifiers changes * update auto_aug * update metafile & readme * use delattr * rename cfgs * Update checkpoint url * Update readme * Rename config files. * Update readme and metafile * add comment * Update mmcls/models/backbones/repvgg.py Co-authored-by: Ma Zerun <mzr1996@163.com> * Update docstring * Improve docstring. * Update unittest_testblock Co-authored-by: Ezra-Yu <1105212286@qq.com> Co-authored-by: Ma Zerun <mzr1996@163.com>
mzr1996
pushed a commit
to mzr1996/mmpretrain
that referenced
this pull request
Nov 24, 2022
* Add classwise weight in losses:CE,BCE,softBCE * Update unit test * rm some extra code * rm some extra code * fix broadcast * fix broadcast * update unit tests * use new_tensor * fix lint
mzr1996
added a commit
to mzr1996/mmpretrain
that referenced
this pull request
Nov 24, 2022
* Add RepVGG code. * Add se_module as plugin. * Add the repvggA0 primitive config * Change repvggA0.py to fit mmcls * Add RepVGG configs * Add repvgg_to_mmcls * Add tools/deployment/convert_repvggblock_param_to_deploy.py * Change configs/repvgg/README.md * Streamlining the number of configuration files. * Fix lints * Delete plugins * Delete code about plugin. * Modify the code for using se module. * Modify config to fit repvgg with se. * Change se_cfg to allow loading of pre-training parameters. * Reduce the complexity of the configuration file. * Finsh unitest for repvgg. * Fix bug about se in repvgg_to_mmcls. * Rename convert_repvggblock_param_to_deploy.py to reparameterize_repvgg.py, and delete setting about device. * test commit * test commit * test commit command * Modify repvgg.py to make the code more readable. * Add value=0 in F.pad() * Add se_cfg to arch_settings. * Fix bug. * modeify some attr name and Update unit tests * rename stage_0 to stem and branch_identity to branch_norm * update unit tests * add m.eval in unit tests * [Enhance] Enhence SE layer to support custom squeeze channels. (open-mmlab#417) * add enhenced SE * Update * rm basechannel * fix docstring * Update se_layer.py fix docstring * [Docs] Add algorithm readme and update meta yml (open-mmlab#418) * Add README.md for models without checkpoints. * Update model-index.yml * Update metafile.yml of seresnet * [Enhance] Add `hparams` argument in `AutoAugment` and `RandAugment` and some other improvement. (open-mmlab#398) * Add hparams argument in `AutoAugment` and `RandAugment`. And `pad_val` supports sequence instead of tuple only. * Add unit tests for `AutoAugment` and `hparams` in `RandAugment`. * Use smaller test image to speed up uni tests. * Use hparams to simplify RandAugment config in swin-transformer. * Rename augment config name from `pipeline` to `pipelines`. * Add some commnet ad docstring. * [Feature] Support classwise weight in losses (open-mmlab#388) * Add classwise weight in losses:CE,BCE,softBCE * Update unit test * rm some extra code * rm some extra code * fix broadcast * fix broadcast * update unit tests * use new_tensor * fix lint * [Enhance] Better result visualization (open-mmlab#419) * Imporve result visualization to support wait time and change the backend to matplotlib. * Add unit test for visualization * Add adaptive dpi function * Rename `imshow_cls_result` to `imshow_infos`. * Support str in `imshow_infos` * Improve docstring. * Bump version to v0.15.0 (open-mmlab#426) * [CI] Add PyTorch 1.9 and Python 3.9 build workflow, and remove some CI. (open-mmlab#422) * Add PyTorch 1.9 build workflow, and remove some CI. * Add Python 3.9 CI * Show Python 3.9 support. * [Enhance] Rename the option `--options` in some tools to `--cfg-options`. (open-mmlab#425) * [Docs] Fix sphinx version (open-mmlab#429) * [Docs] Add `CITATION.cff` (open-mmlab#428) * Add CITATION.cff * Fix typo in setup.py * Change author in setup.py * modeify some attr name and Update unit tests * rename stage_0 to stem and branch_identity to branch_norm * update unit tests * add m.eval in unit tests * Update unit tests * refactor * refactor * Alignment inference accuracy * Update configs, readme and metafile * Update readme * return tuple and fix metafile * fix unit test * rm regnet and classifiers changes * update auto_aug * update metafile & readme * use delattr * rename cfgs * Update checkpoint url * Update readme * Rename config files. * Update readme and metafile * add comment * Update mmcls/models/backbones/repvgg.py Co-authored-by: Ma Zerun <mzr1996@163.com> * Update docstring * Improve docstring. * Update unittest_testblock Co-authored-by: Ezra-Yu <1105212286@qq.com> Co-authored-by: Ma Zerun <mzr1996@163.com>
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
refer to #379