Stars
Build resilient language agents as graphs.
Extract clean data from anywhere, powered by vision-language models ⚡
[CVPR 2023] Official implementation of the paper "Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation"
Automatic Scale Factor Estimation of 3D Reconstruction in COLMAP Utilizing Aruco Marker
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptatio…
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2
The simplest, fastest repository for training/finetuning medium-sized GPTs.
An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries
Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.
TensorFlow Lite (tflite) C++ Series
BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models
A simple C++ library for reading and writing audio files.
Dataset, streaming, and file system extensions maintained by TensorFlow SIG-IO
Learn OpenCV : C++ and Python Examples
Fuse network engine; Contains instructions to connect as a node
PyTorch package for the discrete VAE used for DALL·E.
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
The repository for CVPR 2022 Paper "Neural 3D Video Synthesis"
An office suite that combines text, spreadsheet and presentation editors allowing to create, view and edit local documents
Python Script to download hundreds of images from 'Google Images'. It is a ready-to-run code!
python DroneCAN code generation, interface and utilities
3D mesh stylization driven by a text input in PyTorch
Multiple Object Tracker, Based on Hungarian algorithm + Kalman filter.
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite