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

使用ghostconv代替普通卷积，实例分割任务精度下降问题 #227

Open
xiannsa opened this issue Sep 9, 2023 · 3 comments
Open

使用ghostconv代替普通卷积，实例分割任务精度下降问题 #227

xiannsa opened this issue Sep 9, 2023 · 3 comments

Comments

@xiannsa
Copy link

xiannsa commented Sep 9, 2023

使用ghostconv代替bottelneck里面的普通conv，进行实例分割训练的损失和精度都没有之前的好，难道是还有其他的地方要改进吗？不过参数量和运算量有降低，
@iamhankai
Copy link
Member

正常吧，看精度损失多少

@xiannsa
Copy link
Author

xiannsa commented Sep 12, 2023

白色的是在bottleneck里面用ghost卷积的，黑色是普通卷积，结果都是截取的300轮里面最好的，麻烦看一下是否正常呢。
@13NS@~@3%GE}ETHYC6Y$(W
SU6W@MU2(B(U5BL0`Y@9LA9

@iamhankai
Copy link
Member

看起来正常。把原模型通道数减少，参数量和用ghost卷积的差不多程度，看看谁精度高

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
@iamhankai @xiannsa