All convolutions inside of a dense block are ReLU-activated and use batch normalization. Channel-sensible concatenation is simply attainable if the peak and width dimensions of the info continue being unchanged, so convolutions in a very dense block are all of stride one. Pooling layers are inserted between dense blocks https://financefeeds.com/solana-and-xrp-etfs-could-bring-in-billions-say-jpmorgan-analysts-rollblock-ecosystem-sees-huge-user-growth/