Tengine is a lite, high performance, modular inference engine for embedded device

PNG encoder and decoder in C and C++.

AVX2-vectorized box filter

Machine Learning Compiler Road Map

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

The fastest JSON library in C

Display and control your Android device

Dear ImGui: Bloat-free Graphical User interface for C++ with minimal dependencies

Quantized Neural Network PACKage - mobile-optimized implementation of quantized neural network operators

Datasets, Transforms and Models specific to Computer Vision

FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/

Practical, Easy-to-copy CMake examples

Visual comparison for YUV and JPG/PNG images.

Image processing library for learning purpose

A complete computer science study plan to become a software engineer.

stb single-file public domain libraries for C/C++

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba

lib, demo, model, data

Examples and tools for deep learning deployment

在Android使用深度学习模型实现图像识别，本项目提供了多种使用方式，使用到的框架如下：Tensorflow Lite、Paddle Lite、MNN、TNN

Android face detection 30+ FPS, pretrained weight 1MB.

MNN applications by MNN, JNI exec, RK3399. Support tflite\tensorflow\caffe\onnx models.

🥭 移动端MNN部署学习笔记。支持Android与iOS。

Semantic Segmentation on PyTorch (include FCN, PSPNet, Deeplabv3, Deeplabv3+, DANet, DenseASPP, BiSeNet, EncNet, DUNet, ICNet, ENet, OCNet, CCNet, PSANet, CGNet, ESPNet, LEDNet, DFANet)

😎 A Collection of Awesome NCNN-based Projects

The minimal opencv for Android, iOS, ARM Linux, Windows, Linux, MacOS, HarmonyOS, WebAssembly, watchOS, tvOS, visionOS

PyTorch Neural Network eXchange