0

I want to build a customized convolutional layer in Keras that does convolution for two kernels and one image, I want it to be implemented in my network so I finally have a fully connected network and can be learning end-to-end.

In other words, I just want a trainable layer that takes two filters and one image as inputs and give one image as output... the output image is equal to the convolution of the 3 inputs ... that is everything I want.

Thanks.

MohQ
  • 11
  • 1
  • Please be specific about your question. You can write a simple scenario as an example so that the readers can easily imagine what you would like to do. – mgokhanbakal Aug 26 '20 at 20:08
  • Ok.... I just want a trainable layer that takes two filters and one image as inputs and give one image as output... the output image is equal to the convolution of the 3 inputs ... that is everything I want .. – MohQ Aug 26 '20 at 20:23
  • @MohQ - do you want to your layer to apply the a convolution using the first kernel on the image, then use the output of that as the input to a second convolution using the second kernel, then finally output that? – Anton Codes Nov 24 '20 at 04:45

0 Answers0