Stars
Models and examples built with TensorFlow
The world's simplest facial recognition api for Python and the command line
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
Streamlit — A faster way to build and share data apps.
🥧 HTTPie CLI — modern, user-friendly command-line HTTP client for the API era. JSON support, colors, sessions, downloads, plugins & more.
The fundamental package for scientific computing with Python.
ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型
Benchmarks of approximate nearest neighbor libraries in Python
Efficient 3D human pose estimation in video using 2D keypoint trajectories
Use your Raspberry Pi as a browser-based KVM.
An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.
Retrying is an Apache 2.0 licensed general-purpose retrying library, written in Python, to simplify the task of adding retry behavior to just about anything.
Deep Clustering for Unsupervised Learning of Visual Features
📊 Benchmark multiple object trackers (MOT) in Python
Official PyTorch implementation of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image", ICCV 2019
Autonomous mobile robots (2WD, 4WD, Mecanum Drive)
Learning to Cluster Faces (CVPR 2019, CVPR 2020)
[CVPR 2021 Best Paper Award Candidate] PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation, (Oral, Best Paper Award Finalist)
Official project website for the CVPR 2020 paper (Oral Presentation) "Cascaded deep monocular 3D human pose estimation wth evolutionary training data"
Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localization
We create D3D-HOI a dataset of monocular videos with ground truth annotations of 3D object pose and part motion during human-object interaction.