刘国友's repositories
amazon-dsstne
Deep Scalable Sparse Tensor Network Engine (DSSTNE) is an Amazon developed library for building Deep Learning (DL) machine learning (ML) models
openai-gemm
Open single and half precision gemm implementations
ternarynet
Implementation for Trained Ternary Network.
fastestpedestriandetectorinthewest
This is my version of the Fastest Pedestrian Detector in the West
cvcsh
OpenCV - Coherent Sensitive Hashing implementation (ongoing port from matlab,C++11) NOT WORKING FOR NOW
twobit_caffe
This is an implementation of "Two-Bit Networks for Deep Learning on Resource-Constrained Embedded Devices"(arxiv 2017) in caffe
tensorpack
Neural Network Toolbox on TensorFlow
boda
Boda: A C++ Framework for Efficient Experiments in Computer Vision
model_compression
Implementation of model compression with knowledge distilling method.
caffepresso
CaffePresso: An Optimized Library for Deep Learning on Embedded Accelerator-based platforms
fast-dnn
A fast deep neural network library.
dest
:panda_face: One Millisecond Deformable Shape Tracking Library (DEST)
mars
Mars is a cross-platform network component developed by WeChat.
BilateralVideoSegmentation
Implementation of Bilateral Space Video Segmentation [Maerki et al CVPR 2016]
daal
Intel® Data Analytics Acceleration Library (Intel® DAAL)
impl-pruning-TF
Implementation of "Iterative pruning" on TensorFlow
hdr-plus
HDR+ Implementation
wincnn
Winograd minimal convolution algorithm generator for convolutional neural networks.
CACU
This is a deep learning framework for cnn which using xnor method to accelerate calculating convolution layer on cpu.
HDR-Fast-Local-Laplacian
HDR recovering and tonemapping using fast local laplacian approach
FaceVFX
Cross-platform face swap application
CNNdroid
Open Source Library for GPU-Accelerated Execution of Trained Deep Convolutional Neural Networks on Android
caffe-moon
This repo is re-implement "MOON: A Mixed Objective Optimization Network for the Recognition of Facial Attributes"
NNPACK
Acceleration package for neural networks on multi-core CPUs
opveclib
The Operator Vectorization Library, or OVL, is a python productivity library for defining high performance custom operators for the TensorFlow platform.
GLFFT
A C++11/OpenGL library for the Fast Fourier Transform
TensorNet-TF
TensorNet (TensorFlow implementation)