lucidrains/vector-quantize-pytorch
A PyTorch library providing vector and scalar quantization modules for deep learning, with support for VQ-VAE and residual quantization.
Not currently ranked — collecting fresh signals.
star history
This library implements vector and scalar quantization as PyTorch modules, originally transcribed from Deepmind’s TensorFlow implementation. It uses exponential moving averages to update codebook dictionaries and provides both standard VectorQuantize and ResidualVQ classes for recursive quantization of residuals. The library enables high-quality image generation (VQ-VAE-2) and music generation (Jukebox) by compressing latent representations into discrete codebook entries.
Frequently asked
- What is lucidrains/vector-quantize-pytorch?
- A PyTorch library providing vector and scalar quantization modules for deep learning, with support for VQ-VAE and residual quantization.
- Is vector-quantize-pytorch open source?
- Yes — lucidrains/vector-quantize-pytorch is open source, released under the MIT license.
- What language is vector-quantize-pytorch written in?
- lucidrains/vector-quantize-pytorch is primarily written in Python.
- How popular is vector-quantize-pytorch?
- lucidrains/vector-quantize-pytorch has 4k stars on GitHub.
- Where can I find vector-quantize-pytorch?
- lucidrains/vector-quantize-pytorch is on GitHub at https://github.com/lucidrains/vector-quantize-pytorch.