kevenlee Goto Github PK

albumentations

fast image augmentation library and easy to use wrapper around other libraries

angel

A Flexible and Powerful Parameter Server for large-scale machine learning

arm_neon_2_x86_sse

autoaugment

Unofficial implementation of the ImageNet, CIFAR 10 and SVHN Augmentation Policies learned by AutoAugment using pillow

breeze

一个C++的轻量级的分布式服务器引擎, 架构**为一切皆service.

ceres-solver

goolge ceres-solver for non-linear least squares problems with bounds constraints. More details http://ceres-solver.org/

chineseocr_lite

超轻量级中文ocr，支持竖排文字识别, 支持ncnn推理 , dbnet(1.7M) + crnn(6.3M) + anglenet(1.5M) 总模型仅10M

cutmix-pytorch

Official Pytorch implementation of CutMix regularizer

deformable-convolution-v2-pytorch

Deformable ConvNets V2 (DCNv2) in PyTorch

easypusher

免费组件：简单、高效、稳定、免费的一款标准RTSP/RTP协议直播推送库，支持将H.264/H.265/G.711/G.726/AAC等音视频数据推送到RTSP流媒体服务器（例如EasyDarwin）进行低延时直播或者视频通信，支持Windows、Linux、ARM、Android、iOS等平台，EasyPusher配套EasyDarwin流媒体服务器、EasyPlayer RTSP播放器适用于特殊行业的低延时应急指挥需求！ Android迁移到了https://github.com/EasyDarwin/EasyPusher-Android , iOS迁移到了https://github.com/EasyDarwin/EasyPusher-iOS

efficientnet-pytorch

A PyTorch implementation of EfficientNet

fast-autoaugment

Official Implementation of 'Fast AutoAugment' in PyTorch.

faster_rcnn_for_dota

Code used for training Faster R-CNN on DOTA

gpu_notice

image-comparer

image comparer - powered by Electron

lapjv-algorithm-c

Jonker-Volgenant / LAPJV algorithm for the linear assignment problem, in C language

ml-tutorial-experiment

Coding the Machine Learning Tutorial for Learning to Learn

mmdetection

Open MMLab Detection Toolbox and Benchmark

model-compression

model compression based on pytorch (1、quantization: 16/8/4/2 bits(dorefa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、ternary/binary value(twn/bnn/xnor-net)；2、 pruning: normal、regular and group convolutional channel pruning；3、 group convolution structure；4、batch-normalization folding for quantization)

munkres-cpp

Kuhn-Munkres (Hungarian) Algorithm in C++

netron

Visualizer for neural network, deep learning and machine learning models

ngx_healthcheck_module

nginx module for upstream servers health check. support stream and http upstream. 该模块可以为Nginx提供主动式后端服务器健康检查的功能（同时支持四层和七层后端服务器的健康检测）

openpose

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

powerperfgui

for ARM perf.

pytorch-image-models

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

qualityscaler

Image/video deeplearning upscaler app for Windows - BRSGAN & RealSR_JPEG

roitransformer_dota

shineframe

高性能超轻量级C++开发库及服务器编程框架

sidewindow-fast-guidedfilter

Implementation for paper SideWindowFilter

sylar

C++高性能分布式服务器框架,webserver,websocket server,自定义tcp_server（包含日志模块，配置模块，线程模块，协程模块，协程调度模块，io协程调度模块，hook模块，socket模块，bytearray序列化，http模块，TcpServer模块，Websocket模块，Https模块等, Smtp邮件模块, MySQL, SQLite3, ORM,Redis,Zookeeper)