brjathu
Follow
Stars
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…
Utilities for efficient fine-tuning, inference and evaluation of code generation models
Schedule-Free Optimization in PyTorch
CUDA accelerated rasterization of gaussian splatting
Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.
Official inference library for Mistral models
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation" and [TPAMI'23] "ViTPose : Vision Transformer for Generic Body Pose Estimation"
Pytorch Implementation for Neural Point Characters (NPC)
Flax is a neural network library for JAX that is designed for flexibility.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
SeanNaren / minGPT
Forked from williamFalcon/minGPTA minimal PyTorch Lightning OpenAI GPT w DeepSpeed Training!
Generative Agents: Interactive Simulacra of Human Behavior
Code repository for the paper "On the Benefits of 3D Pose and Tracking for Human Action Recognition", (CVPR 2023)
Easily create large video dataset from video urls
An official code release of the paper RGB no more: Minimally Decoded JPEG Vision Transformers
Our model BUDDI learns the joint distribution of interacting people
Dropbox Uploader is a BASH script which can be used to upload, download, list or delete files from Dropbox, an online file sharing, synchronization and backup service.
Code repository for the paper "Tracking People by Predicting 3D Appearance, Location & Pose". (CVPR 2022 Oral)
[CVPR'23, Highlight] ECON: Explicit Clothed humans Optimized via Normal integration
Official PyTorch code for the paper "Improving Fractal Pre-training"
Hiera: A fast, powerful, and simple hierarchical vision transformer.
4DHumans: Reconstructing and Tracking Humans with Transformers
Internet Explorer explores the web in a self-supervised manner to progressively find relevant examples that improve performance on a desired target dataset.
20 high-performance LLMs with recipes to pretrain, finetune and deploy at scale.