silasxue Goto Github PK

visionbase

Visionbase is a clean C implementation of lots image processing and recognition algorithms.

visual-qa

Keras-based LSTM/CNN models for Visual Question Answering

visual7w-qa-models

Visual7W visual question answering models

visual_search

A visual search engine based on Elasticsearch and Tensorflow

visualsearchappswift

iOS Swift app using OpenCV & Parse

visualsearchserver

A simple implementation of Visual Search using features extracted from Tensor Flow inception model

viton

Code and dataset for paper "VITON: An Image-based Virtual Try-on Network"

vlfeat_wrapper

Python vlfeat wrapper with Cython

vlstm

Vectorized multimodal LSTM using Matlab and GPU

vocabtree2

Vocabulary Tree Code

voxelhashing

vqa-mcb

vqabaseline

Simple Baseline for Visual Question Answering

vstabilization

Stabilization scripts for video

waifu2x

Image Super-Resolution for Anime-Style Art

watts

Word Spotting and Recognition with Embedded Attributes

weatherspider

天气爬虫（全国城镇天气自动定时抓取更新，并开放RESTful查询接口），附带代理IP池定时更新并检测其可用性

webdnn

The Fastest DNN Running Framework on Web Browser

webmagic

A scalable web crawler framework.

webmagic-csdnblog

基于WebMagic写的一个csdn博客小爬虫

webporter

基于 webmagic 的 Java 爬虫应用

webservice

detection service android cbir

wekan

The open-source Trello-like kanban (build with Meteor)

wende

Wende Chinese QA system (experimental)

whats-the-point1

Weakly-supervised semantic image segmentation with CNNs using point supervision

whatsthis-ios

MXNet WhatThis Example for iOS

wide-residual-networks

95.8% and 80% on CIFAR-10 and CIFAR-100

wikiqa

Question Answer System using Chinese Wikipedia Data

word-render

word render for text recognition, ocr, generate sample

word2vec

对 ansj 编写的 Word2VEC_java 的进一步包装，同时实现了常用的词语相似度和句子相似度计算。