dalinvip / cnn-lstm-bilstm-deepcnn-clstm-in-pytorch

In PyTorch Learing Neural Networks Likes CNN、BiLSTM

Introduction

• A classification task implement in pytorch, contains some neural networks in models.

• Recenely, I've released the code.
  • old-version-17 release here
  • pytorch version == 0.3.1 release on here

• This is a version of my own architecture --- pytorch-text-classification

• BERT For Text Classification --- PyTorch_Bert_Text_Classification

Requirement

pyorch : 1.0.1
python : 3.6
torchtext: 0.2.1
cuda : 8.0 (support cuda speed up, can chose, default True)

Usage

modify the config file, see the Config directory(here) for detail.

1、python main.py
2、python main.py --config_file ./Config/config.cfg 
3、sh run.sh

Model

Contains some neural networks implement in pytorch, see the models for detail.

Data

SST-1 and SST-2.

Result

I haven't adjusted the hyper-parameters seriously, you can also see train log in here.

The following test set accuracy are based on the best dev set accuracy.

Data/Model	% SST-1	% SST-2
CNN	46.1086	84.2943
Bi-LSTM	47.9186	86.3262
Bi-GRU	47.6923	86.7655

Reference

• 基于pytorch的CNN-LSTM神经网络模型调参小结
• Convolutional Neural Networks for Sentence Classification
• Context-Sensitive Lexicon Features for Neural Sentiment Analysis