New answers tagged

2

The first formula you quote is for an image with one input channel and one output channel, it just focuses on height and width. In this case, if we consider a 5x5 convolution, the Kernel will just have size 5x5, $m$ and $n$ and going from -2 to +2. Now if our input has 3 channels (RGB, but could be feature maps). we need to use each channel as an input, and ...


0

Indeed I was able to prove that this method works, confirmed by my Matlab golden model. The problem was that in order to read the output activations of an intermediate layer in Keras, you have to create a separate model with the specified output. This separate model in my case did not have the same weights as the original model, leading to incorrect outputs. ...


1

No, you don't average across all feature maps. When the input has multiple channels, you need your convolution filter to have the same number of channels. Therefore, the filter "covers" the full depth of the input. Then, you simply perform the element-wise multiplication of the filter with the overlapping region in the input and add all the ...


Top 50 recent answers are included