Supporting PyTorch models with the Google AI Edge TFLite runtime.

A project demonstrating Lidar related AI solutions, including three GPU accelerated Lidar/camera DL networks (PointPillars, CenterPoint, BEVFusion) and the related libs (cuPCL, 3D SparseConvolution…

Offline Speech Recognition with OpenAI Whisper and TensorFlow Lite for Android

[ICRA'23] BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.

A stub opecl library that dynamically dlopen/dlsyms opencl implementations at runtime based on environment variables. Will be useful when opencl implementations are installed in non-standard pahs

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

State-of-the-art 2D and 3D Face Analysis Project

你管这破玩意叫操作系统源码 — 像小说一样品读 Linux 0.11 核心代码

Sample projects for TensorFlow Lite in C++ with delegates such as GPU, EdgeTPU, XNNPACK, NNAPI

Scripts, Rootfs and other content for AnLinux

MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.

Install and run GNU/Linux on Android

the formula repository for ndk-pkg

Run pytorch models on GPU Android with Vulkan backend

SL4A brings scripting languages to Android by allowing you to edit and execute scripts and interactive interpreters directly on the Android device.

Helper Class for Deep Learning Inference Frameworks: TensorFlow Lite, TensorRT, OpenCV, ncnn, MNN, SNPE, Arm NN, NNAbla

Enable OpenCL Library in Termux Android application.

TensorFlow for Arm

YOLOv5 in PyTorch > ONNX > CoreML > TFLite

Tensorflow Backend for ONNX

TensorFlow for macOS 11.0+ accelerated using Apple's ML Compute framework.

GPU Accelerated TensorFlow Lite applications on Android NDK. Higher accuracy face detection, Age and gender estimation, Human pose estimation, Artistic style transfer

A repository that shares tuning results of trained models generated by TensorFlow / Keras. Post-training quantization (Weight Quantization, Integer Quantization, Full Integer Quantization, Float16 …

An ncnn implementation of YOLOv5 on ARM devices, capable of using GPU to accelerate inference