Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

fix mosaic and autoaug#8533

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 ourterms of service andprivacy statement. We’ll occasionally send you account related emails.

Already on GitHub?Sign in to your account

Open
GuoQuanhao wants to merge2 commits intoPaddlePaddle:release/2.6
base:release/2.6
Choose a base branch
Loading
fromGuoQuanhao:mosaic-autoaug-fix

Conversation

@GuoQuanhao
Copy link

#8517
本次修改并测试的算子包括operators.py中的Mosaic,RandomDistort,AutoAugment
autoaugment_utils.py中的policy_v3,其中带only的算子例如TranslateY_Only_BBoxes,ShearY_Only_BBoxes并未纳入本次训练进程的测试中

修改完成的数据增强,通过双3090在COCO数据集通过picodet训练10个epoch得到如下精度
截图 2023-08-13 11-55-08
其中数据读取yml文件如下

worker_num: 0eval_height: &eval_height 640eval_width: &eval_width 640eval_size: &eval_size [*eval_height, *eval_width]TrainReader:  sample_transforms:  - Decode: {}  - Mosaic:      prob: 1.0      input_dim: [640, 640]      degrees: [-10, 10]      scale: [0.5, 1.5]      shear: [-0.5, 0.5]      translate: [-0.1, 0.1]      enable_mixup: True  - AutoAugment: {autoaug_type: 'v3'}  - DebugVisibleImage: {output_dir: '../debug'}  batch_transforms:  - BatchRandomResize: {target_size: [576, 608, 640, 672, 704], random_size: True, random_interp: True, keep_ratio: False}  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}  - Permute: {}  - PadGT: {}  batch_size: 32  shuffle: true  mosaic_epoch: 10  drop_last: trueEvalReader:  sample_transforms:  - Decode: {}  - Resize: {interp: 2, target_size: *eval_size, keep_ratio: False}  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}  - Permute: {}  batch_transforms:  - PadBatch: {pad_to_stride: 32}  batch_size: 8  shuffle: falseTestReader:  inputs_def:    image_shape: [1, 3, *eval_height, *eval_width]  sample_transforms:  - Decode: {}  - Resize: {interp: 2, target_size: *eval_size, keep_ratio: False}  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}  - Permute: {}  batch_size: 1

@paddle-bot
Copy link

Thanks for your contribution!

@GuoQuanhao
Copy link
Author

这里给出了一些训练过程中的数据增强,其数据增强方案见上个comment的yml文件
链接:https://pan.baidu.com/s/1LNGuYzobeQdCEkzdjZ_RJQ
提取码:ayb2
--来自百度网盘超级会员V5的分享

@GuoQuanhao
Copy link
Author

hello,这边有测试完成吗,我看这个pr很久啦

@CLAassistant
Copy link

CLAassistant commentedSep 24, 2024
edited
Loading

CLA assistant check
All committers have signed the CLA.

Sign up for freeto join this conversation on GitHub. Already have an account?Sign in to comment

Reviewers

1 more reviewer

@luyao-cvluyao-cvluyao-cv approved these changes

Reviewers whose approvals may not affect merge requirements

At least 1 approving review is required to merge this pull request.

Assignees

@lyuwenyulyuwenyu

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

5 participants

@GuoQuanhao@CLAassistant@luyao-cv@lyuwenyu@Ligoml

[8]ページ先頭

©2009-2025 Movatter.jp