Dual model head pose estimation. Fusion of SOTA models. 360° 6D HeadPose detection. All pre-processing and post-processing are fused together, allowing end-to-end processing in a single inference.
MIT License
A collection of GICP-based fast point cloud registration algorithms
Verify that the post-processing merged into FaceMesh works correctly. The object detection model ...
An architecture for LLMs' continual-learning and long-term memories
Pythonic particle-based (super-droplet) warm-rain/aqueous-chemistry cloud microphysics package wi...
Glasses detection, classification and segmentation
Special Presentation Demo at Intel IoT Planet 2021 DeepLearning Day / インテル IoT プラネット 2021 DeepLea...
NumPy实现类PyTorch的动态计算图和神经网络框架(MLP, CNN, RNN, Transformer)
Object detection for video surveillance
Fast Neural Machine Translation in C++ - development repository
Real-time dense visual SLAM system
A high-performance inference system for large language models, designed for production environments.
3D Gaussian Splatting, reimagined: Unleashing unmatched speed with C++ and CUDA from the ground up!
A Rust library integrated with ONNXRuntime, providing a collection of Computer Vison and Vision-L...
Real-time large scale dense visual SLAM system
A PyTorch Library for Accelerating 3D Deep Learning Research