alohali Goto Github PK

alohali.github.io

benchmark-models

benchmark models for TNN, ncnn, MNN

benchmarks

A benchmark framework for Tensorflow

bladedisc

clbenchmark

clpeak

A tool which profiles OpenCL devices to find their peak capacities

coding

computelibrary

The Compute Library is a set of computer vision and machine learning functions optimised for both Arm CPUs and GPUs using SIMD technologies.

cpufp

A CPU tool for benchmarking the peak of floating points

cs231nhomework

cudnnnet

deep-residual-networks

Deep Residual Learning for Image Recognition

deeprec

DeepRec is a recommendation engine based on TensorFlow.

distiller

Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://nervanasystems.github.io/distiller

git

Git Source Code Mirror - This is a publish-only repository and all pull requests are ignored. Please follow Documentation/SubmittingPatches procedure for any of your improvements.

mipscpu

A Mips I CPU simulation written in C++ that is completely programmable and can run most instructions.

mnn

MNN is a lightweight deep neural network inference engine.

mobilenet-caffe

Caffe Implementation of Google's MobileNets (v1 and v2)

ncnn

ncnn is a high-performance neural network inference framework optimized for the mobile platform

neonbenchmark

neongemm

onednn

oneAPI Deep Neural Network Library (oneDNN)

ppl.cv

ppl.cv is a high-performance image processing library of openPPL supporting x86 and cuda platforms.

ppl.nn

A primitive library for neural network

product-nets-distributed

distributed version of product-nets

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

squeezenet

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters

tensorflow

An Open Source Machine Learning Framework for Everyone

tensorflow-1

tnn

TNN：移动端高性能、轻量级推断框架，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推断框架进一步完善。