Skip to content

README.md

Latest commit

 

History

History
71 lines (51 loc) · 2.57 KB

README.md

File metadata and controls

71 lines (51 loc) · 2.57 KB
Raw

Pretrained Reversible Generation as Unsupervised Visual Representation Learning

Twitter Python 3.10 PyTorch Accelerate arXiv demo

🎉 What I cannot create, I do not understand.

🔥 News

  • We first release the version that depends on the GenerativeRL library.
  • 2025.07.01: We update PRG camera ready version for ICCV 2025 and release project website
  • 2024.11.29: We release PRG on arxiv.

What is PRG

PRG proposes to turn a pretrained continuous time flow diffusion generator upside down running the model backward produces multi level features that after light fine tuning serve as an unsupervised representation extractor.

Requirements

  • Python 3.10 or later
  • Conda (optional, but recommended)
  • GenerativeRL (temporarily required)

Installation

1. Prepare the environment

conda create -n prg-env python=3.10  
conda activate prg-env

2. Install GenerativeRL

git clone https://github.com/opendilab/GenerativeRL.git
cd GenerativeRL
pip install -e .

3. Install PRG

git clone https://github.com/opendilab/PRG.git
cd PRG
pip install -e .

Training

Simply select the desired configuration file for the corresponding training stage from the config directory, and run your training. For example:

cd PRG
accelerate launch example.py
#accelerate launch config/Finetune/train_cifar_10_unet_diff.py

Acknowledgement

The Pretrained Reversible Generation codebase is adapted from the following repositories:

A huge thanks to the authors of these projects for their outstanding contributions! 🎉