[Feature] Add detection distill algorithm LAD #436
Conversation
pppppM
changed the title
|
|
||
| | Teacher | Student | Training schedule | AP (val) | Config | Download | | ||
| | :-----: | :-----: | :---------------: | :------: | :----------: | :----------------------: | | ||
| | -- | R-50 | 1x | 40.4 | [config](<>) | [model](<>) \| [log](<>) | |
There was a problem hiding this comment.
Maybe can add the paths of config, model and log for the two baselines from MMClassification.
| | -- | R-50 | 1x | 40.4 | [config](<>) | [model](<>) \| [log](<>) | | ||
| | -- | R-101 | 1x | 42.6 | [config](<>) | [model](<>) \| [log](<>) | | ||
| | R-101 | R-50 | 1x | 41.4 | [config](<>) | [model](<>) \| [log](<>) | | ||
| | R-50 | R-101 | 1x | 43.2 | [config](<>) | [model](<>) \| [log](<>) | |
There was a problem hiding this comment.
Please add the config of this distillation (lad_ppa_r50_ppa_r101_1x_coco.py).
And contact with @pppppM to upload the files (model and log) after training.
| @@ -0,0 +1,30 @@ | |||
| _base_ = ['mmdet::paa/paa_r101_fpn_1x_coco.py'] | |||
There was a problem hiding this comment.
Backbone of the student model should be r50.
* refactor(onnx2ncnn.cpp): split it to shape_inference, pass and utils * refactor(onnx2ncnn.cpp): split it to shape_inference, pass and utils * refactor(onnx2ncnn.cpp): split code * refactor(net_module.cpp): fix build error * ci(test_onnx2ncnn.py): add generate model adn run * ci(onnx2ncnn): add ncnn backend * ci(test_onnx2ncnn): add converted onnx model` * ci(onnx2ncnn): fix ncnn tar * ci(backed-ncnn): simplify dependency install * ci(onnx2ncnn): fix apt install * Update backend-ncnn.yml * Update backend-ncnn.yml * Update backend-ncnn.yml * Update backend-ncnn.yml * Update backend-ncnn.yml * Update backend-ncnn.yml * Update backend-ncnn.yml * Update backend-ncnn.yml * Update backend-ncnn.yml * Update backend-ncnn.yml * Update backend-ncnn.yml * fix(ci): add include algorithm * Update build.yml * parent aa85760 author q.yao <[email protected]> 1651287879 +0800 committer tpoisonooo <[email protected]> 1652169959 +0800 [Fix] Fix ci (open-mmlab#426) * fix ci * add nvidia key * remote torch * recover pytorch refactor(onnx2ncnn.cpp): split it to shape_inference, pass and utils * fix(onnx2ncnn): review * fix(onnx2ncnn): build error Co-authored-by: q.yao <[email protected]>
|
Hi @LiuQQQQQQQ ！We are grateful for your efforts in helping improve this open-source project during your personal time. Welcome to join OpenMMLab Special Interest Group (SIG) private channel on Discord, where you can share your experiences, ideas, and build connections with like-minded peers. To join the SIG channel, simply message moderator— OpenMMLab on Discord or briefly share your open-source contributions in the #introductions channel and we will assist you. Look forward to seeing you there! Join us ：https://discord.gg/UjgXkPWNqA Thank you again for your contribution❤ |
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
Please describe the motivation of this PR and the goal you want to achieve through this PR.
Modification
Please briefly describe what modification is made in this PR.
BC-breaking (Optional)
Does the modification introduce changes that break the backward compatibility of the downstream repositories?
If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.
Use cases (Optional)
If this PR introduces a new feature, it is better to list some use cases here and update the documentation.
Checklist
Before PR:
After PR: