Single Motion Diffusion Model

PyTorch code and models for the DINOv2 self-supervised learning method.

FID computation in Jax/Flax.

Official implementation for "Blended Latent Diffusion" [SIGGRAPH 2023]

Official implementation for "Blended Diffusion for Text-driven Editing of Natural Images" [CVPR 2022]

Sparsity-aware deep learning inference runtime for CPUs

Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

Azure SignalR Service SDK for .NET

Official Jax Implementation of MaskGIT

Recent Transformer-based CV and related works.

Scenic: A Jax Library for Computer Vision Research and Beyond

Nested Hierarchical Transformer https://arxiv.org/pdf/2105.12723.pdf

Pretrained deep learning models for Jax/Flax: StyleGAN2, GPT2, VGG, ResNet, etc.

Parallel t-SNE implementation with Python and Torch wrappers.

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

Official Implementation for "Pivotal Tuning for Latent-based editing of Real Images" (ACM TOG 2022) https://arxiv.org/abs/2106.05744

Official Implementation of Swapping Autoencoder for Deep Image Manipulation (NeurIPS 2020)

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch