Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add Magvit-v2 (vqvae) #656

Open
wants to merge 12 commits into
base: master
Choose a base branch
from
Open

Add Magvit-v2 (vqvae) #656

wants to merge 12 commits into from

Conversation

hqkate
Copy link
Collaborator

@hqkate hqkate commented Sep 10, 2024

What does this PR do?

Adds Mavgit-v2 VQVAE training scripts, supporting both pynative and graph mode.

Fixes # (issue)

Adds # (feature)

  • Lookup-Free-Quantization(LFQ)
  • VQVAE-3d Training
  • VQGAN Training

Before submitting

  • This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
  • Did you read the contributor guideline?
  • Did you make sure to update the documentation with your changes? E.g. record bug fixes or new features in What's New. Here are the
    documentation guidelines
  • Did you build and run the code without any errors?
  • Did you report the running environment (NPU type/MS version) and performance in the doc? (better record it for data loading, model inference, or training tasks)
  • Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

@xxx

@hqkate hqkate marked this pull request as ready for review September 11, 2024 08:50

For the pretraining of VQVAE-2d, we provide a pretrained model weights as follow:

| Model | Dataset | Image Size | Weights | PSNR | SSIM |
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

what is the weights here?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I was about to upload the pretrained model weights and provide a download link in the readme. But since this PR is not the final version of the code, I probably won't put the model weights now. The "weight" column has been removed, please check, thanks thanks~

@@ -0,0 +1,347 @@
# Copyright 2024 Huawei Technologies Co., Ltd
# Copyright (c) 2022-present, Kakao Brain Corp.
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

remove these copyright

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done.

@@ -0,0 +1,119 @@
# MAGVIT-v2: Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation

This folder contains the Mindspore implementation of [MAGVIT-v2](https://arxiv.org/pdf/2310.05737).
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

add original code repo

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

源碼沒有開源,在Readme加了説明,也列明了一些參考的代碼倉

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants