Release for Improved Denoising Diffusion Probabilistic Models

[CVPR‘20] SpixelFCN: Superpixel Segmentation with Fully Convolutional Network

Dense Unsupervised Learning for Video Segmentation (NeurIPS*2021)

StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.

Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement

MEAN.JS - Full-Stack JavaScript Using MongoDB, Express, AngularJS, and Node.js -

A bash script used to install the requied stack for running Jesse.

Code and models for the paper Shape-Texture Debiased Neural Network Training

Tensors and Dynamic neural networks in Python with strong GPU acceleration

PyTorch implementation of the U-Net for image semantic segmentation with high quality images

Datasets, Transforms and Models specific to Computer Vision

This is an extended torch.nn.Linear module which mask connection.

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

Voice Operated Character Animation

Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision

Simple PyTorch implementations of U-Net/FullyConvNet (FCN) for image segmentation

Protocol Buffers - Google's data interchange format

The author's officially unofficial PyTorch BigGAN implementation.

Superpixel segmentation using SLIC with Python.

Supporting notebooks and data from hypertools paper

A python implementation of the spherical k-means clustering algorithm

Bayesian nonparametric small-variance asymptotic clustering algorithms