Di Jin's repositories
SQuAD-QA-System
QA system for Stanford Question Answering Dataset
sentence-classification
Implementation of sentence classification using CNN, CNN-RNN, fasttext, etc.
Weighted_Softmax_Loss_for_Caffe
This is a weighted Softmax Loss Layer for Caffe.
ANN_CNN_fromScratch
This is the code for full connected and convolutional neural network for deep learning from scratch
1-billion-word-language-modeling-benchmark
Formerly known as code.google.com/p/1-billion-word-language-modeling-benchmark
Deep-Learning-Phase-Segmentation
This code implements cell segmentation for quantitative phase images based on CNN deep learning.
pubmed-rct
PubMed 200k RCT dataset: a large dataset for sequential sentence classification.
pytorch-playground
Base pretrained models and datasets in pytorch (MNIST, SVHN, CIFAR10, CIFAR100, STL10, AlexNet, VGG16, VGG19, ResNet, Inception, SqueezeNet)
readability
a collection of functions that measure the readability of a given body of text
RNN-for-image-captioning
This code is to build RNN and LSTM model for image captioning from scratch
sent-conv-torch
Text classification using a convolutional neural network.
sentence_classification
sentence classification using CNN/LSTM/GRU
Structured-Self-Attentive-Sentence-Embedding
An open-source implementation of the paper ``A Structured Self-Attentive Sentence Embedding'' published by IBM and MILA.
wiki2vec
Generating Vectors for DBpedia Entities via Word2Vec and Wikipedia Dumps. Questions? https://gitter.im/idio-opensource/Lobby