# Codeblock 18 Output
attn_mask             : torch.Size([30, 30])
captions & residual   : torch.Size([1, 30, 768])
after self attention  : torch.Size([1, 30, 768])
self attn weights     : torch.Size([1, 30, 30])    #(1)
after norm            : torch.Size([1, 30, 768])

features              : torch.Size([1, 576, 768])
captions & residual   : torch.Size([1, 30, 768])
after cross attention : torch.Size([1, 30, 768])
cross attn weights    : torch.Size([1, 30, 576])   #(2)
after norm            : torch.Size([1, 30, 768])

captions & residual   : torch.Size([1, 30, 768])
after ffn             : torch.Size([1, 30, 768])
after norm            : torch.Size([1, 30, 768])