michaelbbtiger Goto Github PK

2x-playground

Developer Experience experimentation for 2.x

attention-ocr

Visual Attention based OCR

awesome-datascience

:memo: An awesome Data Science repository to learn and apply for real world problems.

awesome-eventstorming

Awesome EventStorming

awesome-scene-text-recognition

A curated list of resources dedicated to scene text localization and recognition

awesomeperfcpp

A curated list of awesome C/C++ performance optimization resources: talks, articles, books, libraries, tools, sites, blogs. Inspired by awesome.

book-reviews

bpl

Bayesian Program Learning model for one-shot learning

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_rtpose

Realtime C++ code for multi-person pose estimation

cann_base

Basic Implementation of a Continuous-attractor Neural Network

cifar10-fast

cljs-flow

Directed graph editor

clojure-ebook-2

clojure-ebook-2

continual-learning

PyTorch implementation of various methods for continual learning (XdG, EWC, online EWC, SI, LwF, DGR, DGR+distill, RtF, iCaRL).

convnet

A GPU implementation of Convolutional Neural Nets in C++

cql

Categorical Query Language IDE

crnn

Convolutional Recurrent Neural Network (CRNN) for image-based sequence recognition.

cub

CUB : a c++ unified base library.

darknet

Windows and Linux version of Darknet Yolo v3 & v2 Neural Networks for object detection (Tensor Cores are used)

datahub

The Metadata Platform for the Modern Data Stack

deep_ocr

make a better chinese character recognition OCR than tesseract

depression-detect-resnet

depression-detect Predicting depression from AVEC2014 using ResNet18.

detect-track

Code release for "Detect to Track and Track to Detect", ICCV 2017

detectron

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

dgd_person_reid

Domain Guided Dropout for Person Re-identification

digit

digital meter numbers detection. :one: :two: :three:

dodaf-digitized

It is widely recognized that there are many advantages to architecture descriptions in the form of structured data. Unstructured data is not readily machine interpretable for the type of queries and analyses required of architecture data. The DoDAF Meta Model (DM2) and the OntologyTools project provide opportunities to achieve this goal.

effect

finalspeed

高速双边加速软件,在高丢包,延迟环境下仍可达到90%物理带宽利用率.