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.
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
kernel size in primary convolution of Ghost module #12
Comments
The code is not clean enough. |
So the kernel size of primary convolution in Ghost module is fixed to [1, 1] by default? |
Yes, the kernel size of primary convolution in Ghost module is fixed to [1, 1] by default. |
Have you tried with larger size? |
I have the same question |
@YUHAN666 @dyj1234567890 Not yet. |
@YUHAN666 Have you tried with larger size? |
@dyj1234567890 Not yet, but when applied on my own project, the GhostNet trained with default setting of this code has the best performance among all the backbone I have tried. |
Hi,
It is said in your paper that the primary convolution in Ghost module can have customized kernel
size, which is a major difference from existing efficient convolution schemes. However, it seems that in this code all the kernel size of primary convolution in Ghost module are set to [1, 1], and the kernel set in _CONV_DEFS_0 are only used in blocks of stride=2. Is it set intentionally?
The text was updated successfully, but these errors were encountered: