pytorch / pytorch/tutorials

Relu after embedding in seq2seq tutorial

Open
#555 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
9.3k
Forks
4.4k
Avg merge
1d 21h
Merged PRs (30d)
4

Description

In seq2seq tutorial in the "Simple decoder" scheme and code there is relu block after word embedding. It looks like a bug due to no reason to put relu after a constant. It must be dropout I hope like in Attention Decoder structure.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Open the linked seq2seq translation tutorial at the “Simple decoder” section and compare its embedding block with the “Attention Decoder” structure. Confirm whether the activation is intentional or should match the reported dropout behavior, then update the tutorial code and wording if needed and verify the rendered example.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
documentation, machine-learning
Issue type
Bug
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
42/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.