All convolutions within a dense block are ReLU-activated and use batch normalization. Channel-intelligent concatenation is only attainable if the height and width dimensions of the info stay unchanged, so convolutions inside of a dense block are all of stride 1. Pooling layers are inserted between dense blocks for further https://financefeeds.com/ethereum-eth-may-be-altcoin-king-but-watch-out-for-these-3-king-killers/