tensorflow / tensorflow/models

Logits and log_probs set to 0 when using cross_entropy

Open
#8,398 0 comments 0 reactions 1 assignee View on GitHub

@a-dai is already working on this.

Since Apr 26, 2020.

models:research type:support
Dominant language
Python
Stars
77.7k
Forks
44.8k
PR merge metrics
No merged PRs in 30d

Description

In MaskGan, seq2seq_vd, if the training strategy is cross_entropy, all the logits, ,log_probs output of the generator's decoder are set to 0. Why is this the case?
https://github.com/tensorflow/models/blob/0672bdcf4c06768155e30632dd0763c1f9a3d002/research/maskgan/models/seq2seq_vd.py#L354

@a-dai

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.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.