刘国友's repositories
gpu.js
GPU Accelerated JavaScript
splitbrainauto
Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction. CVPR 2017.
plug-and-play-priors
An algorithmic framework to experiment with different image priors via denoising algorithms for inverse problems.
mx-lsoftmax
mxnet version of Large-Margin Softmax Loss for Convolutional Neural Networks.
bnn-fpga
Binarized Convolutional Neural Networks on Software-Programmable FPGAs
caffe2
Caffe2 is a cross-platform framework made with expression, speed, and modularity in mind.
cglm
Optimized OpenGL/Graphics Math (glm) for C
OpenBLAS
OpenBLAS is an optimized BLAS library based on GotoBLAS2 1.13 BSD version.
blis
BLAS-like Library Instantiation Software Framework
Lua-5.1.4-codedump
Lua 5.1.4版本代码注释
caffe-mobile
iOS/Android Caffe lib with demo APP (CPU_ONLY, NO_BACKWARD, NO_BOOST, NO_HDF5, NO_LEVELDB)
Demitasse
Demitasse is a fast Deep Neural Network Library for mobile devices(non GPGPU).
Stochastic_Depth
Code for "Deep Networks with Stochastic Depth"
Face_Parsing_2016
Faster model for Multi-Objective Convolutional Learning for Face Labeling
Embedded-Neural-Network
collection of works on neural network based embedded applications
convShader
Convolution in the Mobile GPU with OpenGL ES 2.0 Shading Language
clSPARSE
a software library containing Sparse functions written in OpenCL
XNOR-Net-1
XNOR-Net, CUDNN5 supported version of XNOR-Net-caffe: https://github.com/loswensiana/BWN-XNOR-caffe
adaptive-softmax
Implements an efficient softmax approximation as described in the paper "Efficient softmax approximation for GPUs" (http://arxiv.org/abs/1609.04309)
Ne10
An open optimized software library project for the ARM® Architecture
face_verification_experiment
A Light CNN for Deep Face Representation with Noisy Labels
tf-faster-rcnn
A tensorflow implementation of faster RCNN
mkl-dnn
Intel(R) Math Kernel Library for Deep Neural Networks (Intel(R) MKL-DNN)
libxsmm
Library targeting Intel Architecture for small, dense or sparse matrix multiplications, and small convolutions.
cub
CUB is a flexible library of cooperative threadblock primitives and other utilities for CUDA kernel programming.
Simd
C++ image processing library with using of SIMD: SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, AVX, AVX2, VMX(Altivec) and VSX(Power7), NEON for ARM.