lucidrains / lucidrains/bit-diffusion

Performance of this code in image generation task

Open
#3 0 comments 8 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
356
Forks
20
PR merge metrics
No merged PRs in 30d

Description

Dear @lucidrains, thank you very much for providing the code. It's really helpful for my own research on diffusion model.

I am wondering if you have reached the reported performance in Analog Bits paper for the image generation task?

I am trying to reproduce the image captioning task in the paper, but unfortunately I couldn't reach the reported performance. So I am checking the code of the image generation task in this repo, to see if I did anything wrong in my own code.

Also, if you've tried reproducing the image captioning task, I would love to hear your suggestions.

Thank you very much!

Contributor guide

No contributing guide indexed for this repository

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

The issue does not name a file, test, or entry point. Start by locating the Python/PyTorch image-generation implementation and comparing its setup with the Analog Bits paper and the reported image-captioning results. Done would mean reproducing the reported performance or documenting a concrete discrepancy and its cause.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.