title

Confusing about the dimension of Seq2Seq model - #2 by vdw - nlp - PyTorch Forums

charset

utf-8

description

I am new to Seq2Seq and hope to find a proper guildances, advices. I am doing a Project from an online course so I can not give the material but I got my Project notebook on Github I want to ask about my understandin…

generator

Discourse 3.5.0.beta9-dev - https://github.com/discourse/discourse version eecb0729f2a8c0acae887fa2c86457aaeedd3d44

theme-color

#fff

og:site_name

PyTorch Forums

og:type

website

og:image

https://discuss.pytorch.org/uploads/default/original/2X/1/15a7e2573aeb9e6ba8995f824d3b63171a433041.png

og:url

https://discuss.pytorch.org/t/confusing-about-the-dimension-of-seq2seq-model/185235/2

og:title

Confusing about the dimension of Seq2Seq model

twitter:card

summary

twitter:image

https://discuss.pytorch.org/uploads/default/original/2X/1/15a7e2573aeb9e6ba8995f824d3b63171a433041.png

twitter:url

https://discuss.pytorch.org/t/confusing-about-the-dimension-of-seq2seq-model/185235/2

twitter:title

Confusing about the dimension of Seq2Seq model

twitter:description

Yes, the input for the encoder is (batch_size, seq_len). Each sequence in a batch is a list/array of integers reflecting the indices of the tokens in the vocabulary. For example, a match might look like this: [ [12, 40, 8, 105, 86, 6], [35, 105, 86, 35, 40, 6] ] Representing the 2 sentences “i like to watch movies .” and “you watch movies you like .” This means your vocabulary provides a mapping like {6: ".", 8: "to", 12: "i", 35: "you", 40: "like", ...} There is no need to convert ...

position

1

headline

Confusing about the dimension of Seq2Seq model

datePublished

2023-07-28T07:15:03Z

articleSection

nlp

keywords

alternate nofollow

https://discuss.pytorch.org/t/confusing-about-the-dimension-of-seq2seq-model/185235.rss

apple-touch-icon

https://discuss.pytorch.org/uploads/default/optimized/2X/3/38d28fd067a1a8f263e14507942b2e38e49b771a_2_180x180.png

canonical

https://discuss.pytorch.org/t/confusing-about-the-dimension-of-seq2seq-model/185235

icon

https://discuss.pytorch.org/uploads/default/optimized/2X/b/bb2eeaba4e9f7e4a5944a0d83f52c4f2bf1b6a85_2_32x32.png

url

https://discuss.pytorch.org/u/QUANG_HUY_CHU