New answers tagged convolutional-layers
1
A convolution layer has a Kernel that is matrix smaller that the image (in many papers 3*3), so this Kernel have learnable values.
The kernel is applied pixel by pixel (and dimensions, for color images), by applied I mean take the kernel centered in the pixel and multiply element-wise with the image and sum all results. This is the output for that pixel, a ...
Top 50 recent answers are included