All convolutions in a dense block are ReLU-activated and use batch normalization. Channel-clever concatenation is only attainable if the height and width dimensions of the information continue being unchanged, so convolutions inside a dense block are all of stride 1. Pooling layers are inserted between dense blocks for more https://financefeeds.com/discover-the-4-best-altcoins-to-buy-and-hold-this-month-for-long-term-gains/