增加Yolo11模型#3415
Open
yicycyc wants to merge 4 commits into
Open
Conversation
|
Thanks for your contribution! |
| MODEL_URLS = {} | ||
|
|
||
| __all__ = [ | ||
| "YOLO11_cls_n", |
Collaborator
There was a problem hiding this comment.
需要模型权重,发给负责人,负责人提供链接后写到代码中
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
本 PR 在 PaddleClas 中新增
YOLO11-cls分类模型的 Paddle 实现,覆盖n/s/m/l/x五个规格。YOLO11 在上游 Ultralytics 中没有 timm 对应实现,且其官方实现基于 PyTorch。为了满足 PaddleClas 的接入要求,本次迁移未复用 PyTorch 网络代码,而是参考 PaddleClas 现有模型实现方式,完成了纯 Paddle 版本的网络重写、配置接入和文档补充。
在精度验证上,完成了下面的验证:
1. 新增 YOLO11-cls 模型实现
新增 Paddle 版
YOLO11-clsBackbone,实现文件:ppcls/arch/backbone/model_zoo/yolo11.py支持以下模型:
YOLO11_cls_nYOLO11_cls_sYOLO11_cls_mYOLO11_cls_lYOLO11_cls_x并完成注册:
ppcls/arch/backbone/__init__.py2. 新增 ImageNet 配置
新增 YOLO11-cls 的 ImageNet 配置文件:
ppcls/configs/ImageNet/YOLO11/YOLO11_cls_n.yamlppcls/configs/ImageNet/YOLO11/YOLO11_cls_s.yamlppcls/configs/ImageNet/YOLO11/YOLO11_cls_m.yamlppcls/configs/ImageNet/YOLO11/YOLO11_cls_l.yamlppcls/configs/ImageNet/YOLO11/YOLO11_cls_x.yaml说明:
Resize(224) -> CenterCrop(224) -> ToTensorNormalizeImage采用mean=[0,0,0]、std=[1,1,1]3. 新增模型文档
新增中文模型文档:
docs/zh_CN/models/ImageNet1k/YOLO11.md验证结果
1. 前向对齐
基于 Ultralytics 官方
yolo11*-cls.pt权重,对 Paddle 模型与源模型进行前向对齐,比较末级特征feat和分类输出out:结论:
1e-5以内2. ImageNet1k 精度复现
在 ImageNet1k
val集上评估结果如下:结论: