Skip to content
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.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

加载yolov8预训练模型，做训练，权重网络不匹配 #344

Open
Salary-only-17k opened this issue Aug 23, 2024 · 5 comments
Open

加载yolov8预训练模型，做训练，权重网络不匹配 #344

Salary-only-17k opened this issue Aug 23, 2024 · 5 comments

Comments

@Salary-only-17k
Copy link

RuntimeError: For 'load_param_into_net', model.model.22.cv3.0.2.weight in the argument 'net' should have the same shape as model.model.22.cv3.0.2.weight in the argument 'parameter_dict'. But got its shape (10, 128, 1, 1) in the argument 'net' and shape (80, 128, 1, 1) in the argument 'parameter_dict'.
@Salary-only-17k
Copy link
Author

我测试了yolov8s yolov7tiny yolov5n都不能加载？？？？

@WongGawa
Copy link
Collaborator

感谢反馈。请提供一下详细信息。
执行命令是什么，并且权重从哪里获取得到的呢？

@YYCYcc
Copy link

YYCYcc commented Dec 2, 2024

您好权重是从https://gitee.com/sundaelite/insect_detect_mindyolo/blob/main/MODEL_ZOO.md，获得的，请问这个权重文件是有问题吗

@WongGawa
Copy link
Collaborator

WongGawa commented Dec 2, 2024

可以提供一下训练的所使用的数据集是否是coco数据集？如果是要使用其他数据集微调的话，可以参考exampl编写所使用的yaml配置文件；或者可以使用--strict_load False，能否解决您的问题。

@WongGawa
Copy link
Collaborator

@YYCYcc 建议优先从以下链接获取，由https://github.com/mindspore-lab/mindyolo/tree/master/configs/内的各模型提供的权重文件。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@Salary-only-17k @YYCYcc @WongGawa
pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy