This repository contains an implementation of RealNVP (Real-valued Non-Volume Preserving) normalizing flow for the MNIST dataset. RealNVP is a type of normalizing flow model used in deep learning and generative modeling to model complex distributions and generate new samples.
The RealNVP normalizing flow is implemented using Python and Pytorch. The model is trained on the MNIST dataset, which consists of 28x28 grayscale images of handwritten digits.
The notebook includes the following components:
- RealNVP model implementation with coupling layer
- Training script
- Evaluation script
This project is licensed under the MIT License - see the LICENSE file for details.
We hope this implementation of RealNVP normalizing flow for the MNIST dataset will be useful for researchers and practitioners in the field of generative modeling and deep learning.