This code is an unofficial Python implementation of Denoising Diffusion Probabilistic Models. I trained a simple model with a generated spiral train data. I tested it using uniform distribution on the interval [0, 1).
- Clone the repository.
- Create a virtual environment.
- Install pip packages. If you have trouble with torch, please install it according to PyTorch.
git clone https://github.com/veliglmz/simple-diffusion-model.git
cd simple-diffusion-model
python3.8 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
python main.py
If you want to see the options, you can use this command.
python main.py --help
The result of the spiral sample.