Visualizing_Understanding_CNN_Implementation
Visualizing_Understanding_CNN_Implementation copied to clipboard
Transposed filters
I was wondering if the deconv filters are trainable, or they are just transpose of the (pretrained) conv filters? If the latter, are we assuming the filters are unitary?
I have the same question with you ,in image segmetation ,the deconv is trainable, but here,the code shows that it directly uses the transpose of the conv filters