Stars
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Models and examples built with TensorFlow
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
The simplest, fastest repository for training/finetuning medium-sized GPTs.
A toolkit for developing and comparing reinforcement learning algorithms.
OpenMMLab Detection Toolbox and Benchmark
State-of-the-art 2D and 3D Face Analysis Project
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT!🌏 Train a 26M-parameter GPT from scratch in just 2h!
Code to accompany "A Method for Animating Children's Drawings of the Human Figure"
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
🤖 wukong-robot 是一个简单、灵活、优雅的中文语音对话机器人/智能音箱项目,支持ChatGPT多轮对话能力,还可能是首个支持脑机交互的开源智能音箱项目。
Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"
OpenMMLab Pose Estimation Toolbox and Benchmark.
A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
[ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box
WebRTC and ORTC implementation for Python using asyncio
Torchreid: Deep learning person re-identification in PyTorch.
Production First and Production Ready End-to-End Speech Recognition Toolkit
On-device wake word detection powered by deep learning
The easiest tool for fine-tuning LLM models, synthetic data generation, and collaborating on datasets.
Noise supression using deep filtering
PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT
A cross platform Bluetooth Low Energy Client for Python using asyncio