How to write my custom Conv2d layer ?
I want to do some transformations on the convolved part of the image before convolution.
You could use unfold for your custom convolution (which might be slow) as described here.
1 Like
link to the competition solution discussion
can you help me with what the convolution and maxpool with no stride mean
- thanks
I don’t know, what “I removed the stride in the first conv layer and max-pooling layer” means.
Maybe a custom stride was removed and the default one was used?
As it’s the 1st place solution, I assume that the code has to be released (to get the prize). You could also ask the author directly, what she meant by this setup. 
1 Like