Convolution neural networks can master from a number of characteristics parallelly. In the final phase, we stack each of the output feature maps along with the depth and produce the output. A VGG-block had a lot of 3x3 convolutions padded by 1 to help keep the size of output https://financefeeds.com/best-meme-coin-to-buy-new-copyright-presale-mind-of-pepe-raises-1-5-million-in-48-hours/