EugenHotaj/pytorch-generative
PyTorch library providing reference implementations of state-of-the-art generative models with training utilities.
Not currently ranked — collecting fresh signals.
star history
This repository is a Python library that makes generative modeling easier in PyTorch by providing high-quality implementations of generative models including autoregressive models (PixelCNN, PixelSNAIL, ImageGPT), variational autoencoders (VAE, VQ-VAE, VD-VAE, Beta-VAE), and normalizing flows. It offers reusable building blocks, training utilities, debugging tools, and TensorBoard integration for visualizing metrics.
Frequently asked
- What is EugenHotaj/pytorch-generative?
- PyTorch library providing reference implementations of state-of-the-art generative models with training utilities.
- Is pytorch-generative open source?
- Yes — EugenHotaj/pytorch-generative is open source, released under the MIT license.
- What language is pytorch-generative written in?
- EugenHotaj/pytorch-generative is primarily written in Python.
- How popular is pytorch-generative?
- EugenHotaj/pytorch-generative has 437 stars on GitHub.
- Where can I find pytorch-generative?
- EugenHotaj/pytorch-generative is on GitHub at https://github.com/EugenHotaj/pytorch-generative.