Convolution layer (CONV) The convolution layer (CONV) takes advantage of filters that perform convolution operations as it can be scanning the enter $I$ with respect to its dimensions. Its hyperparameters incorporate the filter size $File$ and stride $S$. The ensuing output $O$ is called feature map or activation map. https://financefeeds.com/desci-reimagining-the-future-of-science-through-decentralization/