tianxingyzxq Goto Github PK

2019-ccf-bdci-ocr-mczj-ocr-identificationidelement

2019CCF-BDCI大赛 最佳创新探索奖获得者 基于OCR身份证要素提取赛题冠军 天晨破晓团队 赛题源码

acurustrack

A multi-object tracking component. Works in the conditions where identification and classical object trackers don't (e.g. shaky/unstable camera footage, occlusions, motion blur, covered faces, etc.). Works on any object despite their nature.

albumentations

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

algorithm

alphatree-graphic-deep-neural-network

将深度神经网络中的一些模型 进行统一的图示，便于大家对模型的理解

angular-penalty-softmax-losses-pytorch

Angular penalty loss functions in Pytorch (ArcFace, SphereFace, Additive Margin, CosFace)

angular-triplet-loss

ATL(Angular Triplet Loss):A new loss function based on sphereface & triplet loss

awesome-leetcode

Leetcode 题解 (跟随思路一步一步撸出代码) 及经典算法实现

awesome-ocr

papers about ocr

caffe

Caffe: a fast framework for deep learning. For the most recent version checkout the dev branch. For the latest stable release checkout the master branch.

caffe-1

Caffe fork with unpool layers, deconvolution layers, locally connected layers, and a custom layer called TweakFeaturesLayer.

caffe-mt

This is a fork of caffe added some useful layers, the original caffe site is https://github.com/BVLC/caffe.

caffe-video_triplet

Unsupervised Learning using Videos (ICCV 2015)

caffe-yolo

YOLO (Real-Time Object Detection) in caffe

caffe_code_analysis

Caffe_Code_Analysis

cmake_examples

Practical, Easy-to-copy CMake examples

compilerspj2

cpp-cheatsheet

Modern C++ Cheatsheet

cpp-primer

C++ Primer 5 answers

cpp_crash_course

C++ files from the "C++ Crash Course" YouTube series by CoffeeBeforeArch

cuda-convnet

Automatically exported from code.google.com/p/cuda-convnet

cuda-convnet2

Automatically exported from code.google.com/p/cuda-convnet2

cuda_freshman

cuda_programming

Code from the "CUDA Crash Course" YouTube series by CoffeeBeforeArch

deep-residual-networks

Deep Residual Learning for Image Recognition

deeplearing

deepLearing

deeplearning

deeplearning-1

detectandtrack

The implementation of an algorithm presented in the CVPR18 paper: "Detect-and-Track: Efficient Pose Estimation in Videos"

devilyuan

DevilYuan股票量化系统