Build and train Lipschitz constrained networks: TensorFlow implementation of k-Lipschitz layers

Deepfakes with an adversarial twist.

Code for Spectral Norm of Convolutional Layers with Circular and Zero Paddings and Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration

PyTorch Implementation of the CLIP Algorithm

A Wasserstein Generative Adversarial Network that learns the distribution of a Mixture of Gaussian, using weight clipping or spectral normalization

implementation of novel Segformer neural network variants dubbed "LRSegformer" which includes Lipschitz-regularized MLP decoder layers to improve training stability and prevent overfitting