A PyTorch implementation of normalizing flows. Many popular flow architectures are implemented including GLOW, NICE, Real NVP, Masked Autoregressive Flow, Planar Flow, Radial Flow and others. The package can be easily installed via pip. It includes several sample use cases in the example folder, including Glow, a VAE, and a Residual Flow.
Keywords: normalising flows, GLOW, NICE, Real NVP, Neural Spline Flow, generative model, probabilistic programming, Python, PyTorch