will thumbs up if correct and fast

Assume that an RGB image input enters a ConvNet: For the convolution layer, a single vertical edge filter (shown below) with the padding size of 2 and the stride of 2 with ReLU activation and no bias was used. For the pooling layer, max pooling with with S=2 and f=2 was used. The output of the pooling layer flatens and enters the fully connected network. The output of the pooling layer is 22 size. (xij represents the element in the output of the pooling layer in the i-th row and j-th column)