We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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 our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Describe the bug modulated deform conv算子在模型实际运行时会遇到output tensor的shape与offset tensor、mask tensor的shape不一致情况,无法满足cnnl kernel要求。
暂时无法通过变换,将这三个tensor的shape对齐以满足kernel要求【因为这些NCHW格式的tensor中每一个维度已经有了明确的实际意义】
The text was updated successfully, but these errors were encountered:
上述出错case 中offset,mask shpae应与input相同 因为ho=(hi+2*p-kh)/sh+1。 需要check下这里的offset mask shape为何计算不一致
Sorry, something went wrong.
No branches or pull requests
Describe the bug
modulated deform conv算子在模型实际运行时会遇到output tensor的shape与offset tensor、mask tensor的shape不一致情况,无法满足cnnl kernel要求。
暂时无法通过变换,将这三个tensor的shape对齐以满足kernel要求【因为这些NCHW格式的tensor中每一个维度已经有了明确的实际意义】
The text was updated successfully, but these errors were encountered: