sefira

word2vec

This is a word2vec for Chinese douban movie reviews 在豆瓣电影影评上进行word2vec, 一个中文语料word2vec

question-classification-cnn-rnn-attention

针对百度知道电影问答数据的问题分类 question classification for zhidao.baidu.com in movie domain

texture-classification-hand-crafted-feature

bing_query_title_match

Bing search log, query and title pairwise loss match

GoogleImageSearchAPISimulation

a Google Image Search API Simulation while Google‘s is no longer available.

PreciseRoIPooling

Precise RoI Pooling with coordinate gradient support, proposed in the paper "Acquisition of Localization Confidence for Accurate Object Detection" (https://arxiv.org/abs/1807.11590).

ai-deadlines

:alarm_clock: AI conference deadline countdowns

c2board

Tensorboard for Caffe2

CNTK

Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit

conditional-convolutional-neural-network

Implement of conditional convolutional neural network ICCV15. A source code of paper: Attention Estimation for Input Switch in Scalable Multi-display Environments

Detectron

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

Detectron-Cascade-RCNN

Cascade R-CNN in Detectron

DistantSupervision

Zhidao Movie

DLHeadPose

DL for head pose estimation, will be used in MultiScreen_UniMouse

jmc

jmc - a new macOS media organizer

Kpooling

LLC

models

Model configurations

MultiScreen_UniMouse

switch our single mouse and keyboard contrl rights between multisScreen in multi computer by gaze( just face pose)

neural-style

Torch implementation of neural style algorithm

NeuralMovieQAQ

NeuralMovieQAQAzure

Paddle

PArallel Distributed Deep LEarning

PANet

PANet for Instance Segmentation and Object Detection

pytorch-semseg

Semantic Segmentation Architectures Implemented in PyTorch

semantic-segmentation-pytorch

Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

SensorToMotion

recognize the Motion class for hongqi tech. sensor

serving

A flexible, high-performance serving system for machine learning models

siggraph2016_colorization

Code for the paper 'Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic Image Colorization with Simultaneous Classification'.

ToyDL_MNIST

Toy project for quick experiment in Deep learning