incompatibility in code and article

[maralzar]

In your article after concatenating Q and output of the transfer attention layer, we see two convolution layers as illustrated in Fig 2 ,however, In code you applied one Conv why do not they match? T=self.conv1[i](T)

[chunmeifeng]

Hi Maral, Thanks for your email. We are sorry that the paper is inconsistent with the code. However, there's no big difference between one convolution layer and two layers.

Maral @.***> 于2022年8月22日周一 23:32写道：

In your article after concatenating Q and output of the transfer attention layer, we see two convolution layers as illustrated in Fig 2 ,however, In code you applied one Conv why do not match? T=self.conv1i

— Reply to this email directly, view it on GitHub https://github.com/chunmeifeng/T2Net/issues/12, or unsubscribe https://github.com/notifications/unsubscribe-auth/AR75XN6RMROCRATB4A3M75LV2PWXRANCNFSM57JFIUOQ . You are receiving this because you are subscribed to this thread.Message ID: @.***>

[maralzar]

Thank you for the quick response and also amazing research. So the results of the articles are based on two convs ? ??

[chunmeifeng]

All the results are obtained from our released code.

Maral @.***> 于2022年8月23日周二 00:36写道：

Thank you for the quick response and also amazing research. So the results of the articles are based on two convs ? ??

— Reply to this email directly, view it on GitHub https://github.com/chunmeifeng/T2Net/issues/12#issuecomment-1223261697, or unsubscribe https://github.com/notifications/unsubscribe-auth/AR75XN3IJKL45K7IJX34GE3V2P6FRANCNFSM57JFIUOQ . You are receiving this because you commented.Message ID: @.***>

[maralzar]

Thank you.