onnx / onnx/models

StyleGAN2 onnx model

Open
#462 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

model-request
Dominant language
Jupyter Notebook
Stars
9.8k
Forks
1.6k
PR merge metrics
No merged PRs in 30d

Description

Model Request

Which model would you like to see in the model zoo?

StyleGAN2 generator on faces (CelebA, FFHQ, ...)
Paper: "Analyzing and Improving the Image Quality of StyleGAN", https://arxiv.org/abs/1912.04958

Describe why this model is relevant

The environment to make inferences on this model is complicated to set up. Moreover, it works only on old Cuda versions and old GPUs.

Model information

Source repository: https://github.com/NVlabs/stylegan2.git
Model Zoo category: Vision
Model Zoo sub-category: Image Generation

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

Start by reviewing the linked NVlabs/stylegan2 source repository and the ONNX models repository conventions for Vision models. Determine the supported conversion path for the StyleGAN2 generator and add it under the Image Generation category, with a usable model artifact and documentation matching the model-zoo requirements.

Written by the indexing model from the issue text.

Assessment

Domain
computer-vision, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.