devandong Goto Github PK

abseil-cpp

Abseil Common Libraries (C++)

awesome-machine-learning-in-compilers

Must read research papers and links to tools and datasets that are related to using machine learning for compilers and systems optimisation

bolt

Bolt is a deep learning library with high performance and heterogeneous flexibility.

caffe

Caffe: a fast open framework for deep learning.

chineseocr_lite

超轻量级中文ocr，支持竖排文字识别, 支持ncnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M

cinn

a Compiler Infrastructure for Neural Networks

clang-llvm-tutorial

clang & llvm examples, e.g. AST Interpreter, Function Pointer Analysis, Value Range Analysis, Data-Flow Analysis, Andersen Pointer Analysis, LLVM Backend...

coremltools

Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.

cpu-cache

cutlass

CUDA Templates for Linear Algebra Subroutines

deep-learning-operator

implementation, benchmark, optimization

embedded-ai.bench

benchmark for embededded-ai deep learning inference engines, such as NCNN / TNN / MNN etc.

flexible-gemm

flexible-gemm conv of deepcore

forge

A neural network toolkit for Metal

gpuexample

GPUExample

learnmetal

Metal 入门教程

mediapipe

MediaPipe is the simplest way for researchers and developers to build world-class ML solutions and applications for mobile, edge, cloud and the web.

megengine

MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架

metal

mnn

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

opencl-101

Learn OpenCL step by step.

openmp-101

Learn OpenMP examples step by step

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

pytorch_block_sparse

Fast Block Sparse Matrices for Pytorch

sample-code

skia

Skia is a complete 2D graphic library for drawing Text, Geometries, and Images.

tensorflow

An Open Source Machine Learning Framework for Everyone

tnn

TNN：由腾讯优图实验室打造，移动端高性能、轻量级推理框架，同时拥有跨平台、高性能、模型压缩、代码裁剪等众多突出优势。TNN框架在原有Rapidnet、ncnn框架的基础上进一步加强了移动端设备的支持以及性能优化，同时也借鉴了业界主流开源框架高性能和良好拓展性的优点。目前TNN已经在手Q、微视、P图等应用中落地，欢迎大家参与协同共建，促进TNN推理框架进一步完善。

yolov5

YOLOv5 in PyTorch > ONNX > CoreML > iOS