# Codeblock 20 Output
features               : torch.Size([1, 576, 768])
captions               : torch.Size([1, 30])
after embedding        : torch.Size([1, 30, 768])
after sin embed        : torch.Size([1, 30, 768])
after decoder block #0 : torch.Size([1, 30, 768])
after decoder block #1 : torch.Size([1, 30, 768])
after decoder block #2 : torch.Size([1, 30, 768])
after decoder block #3 : torch.Size([1, 30, 768])
after linear           : torch.Size([1, 30, 10000])