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

请问，训练时候评测评测远远高于eval时的评测结果？ 在自有数据上测试了v3.0版本的6s，相比较v7-tiny效果差很多，并且6s计算量大很多 #8

Open
STEVENQY opened this issue Mar 18, 2023 · 1 comment
Open

请问，训练时候评测评测远远高于eval时的评测结果？ 在自有数据上测试了v3.0版本的6s，相比较v7-tiny效果差很多，并且6s计算量大很多 #8

STEVENQY opened this issue Mar 18, 2023 · 1 comment

Comments

@STEVENQY
Copy link

No description provided.

@yang-0201
Copy link
Owner

抱歉，请问你用的是v0.3.0 分支中的v3.0版本的6s还是yolov6官方版本的6s，如果是我这边版本的文件，v3版本应该还有错误，因为时间精力问题，没有与官方对齐精度，实现可能有问题，目前只对齐了v2版本的。
关于，训练时候评测评测远远高于eval时的评测结果，是不存在这种问题的，用训练生成的best_ckpt.pt来验证，精度是一模一样的

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
2 participants
@STEVENQY @yang-0201