-
Notifications
You must be signed in to change notification settings - Fork 86
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
DepthWiseConv2dImplicitGEMM has no 'padding' class attribute(actually zero) #48
Comments
I got the same problem, have you solved it yet? |
|
I didn't investigate it further, my exp finds author's Conv2d fails to converge on my mission, while nn.Conv2d is fine, so I just ignore them. |
I also got the same problem. Have you solved it yet? @StarTherlyn |
Thank you for your suggestion :) |
Actually, another modification to convert tuple to int is needed. see #59 |
When I ran directly
replknet.py
with usingDepthWiseConv2dImplicitGEMM
, I got this error:which seems likely a padding issuse with large kernel size. Then I checked
replknet.py
anddepthwise_conv2d_implicit_gemm.py
and found there is no padding parameter.With debugging, I find out that DepthWiseConv2dImplicitGEMM has no attribute of
padding
(actually zero), which leads to when callingmodel.structural_reparam()
andReparamLargeKernelConv.merge_kernel()
, incorrect conv2d class will be created (miss the using condtion of DepthWiseConv2dImplicitGEMM and fallback to create a nn.Conv2d with 0 padding).The text was updated successfully, but these errors were encountered: