Convolution layer (CONV) The convolution layer (CONV) uses filters that perform convolution functions as it can be scanning the enter $I$ with respect to its dimensions. Its hyperparameters include things like the filter size $File$ and stride $S$. The resulting output $O$ is called feature map or activation map. https://financefeeds.com/missing-this-0-14-altcoin-could-be-like-sleeping-on-shiba-inu-before-36400-pump-in-last-cycle/