Sitemap

Transformer’s Encoder-Decoder

11 min readDec 12, 2021

--

Press enter or click to view image in full size
Press enter or click to view image in full size
Figure 1 of the paper
Press enter or click to view image in full size
Press enter or click to view image in full size
Press enter or click to view image in full size
Press enter or click to view image in full size
Press enter or click to view image in full size
Press enter or click to view image in full size

(‘Hello’, ‘world’, ‘!’, <pad>, <pad>, …, <pad>)

(8667, 1362, 106, 0, 0, …, 0)

Press enter or click to view image in full size
Press enter or click to view image in full size
Press enter or click to view image in full size
Press enter or click to view image in full size
Press enter or click to view image in full size
Press enter or click to view image in full size
Press enter or click to view image in full size
Press enter or click to view image in full size
Press enter or click to view image in full size
Press enter or click to view image in full size

While the linear transformations are the same across different positions, they use different parameters from layer to layer. Another way of describing this is as two convolutions with kernel size 1.

Press enter or click to view image in full size
Press enter or click to view image in full size
Press enter or click to view image in full size
Press enter or click to view image in full size
Press enter or click to view image in full size
Press enter or click to view image in full size
Press enter or click to view image in full size
Press enter or click to view image in full size

--

--