CementMaker / Cnn_lstm_for_text_classify
CNN, LSTM, NBOW, fasttext 中文文本分类
Stars: ✭ 90
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Cnn lstm for text classify
Pytorch Learners Tutorial
PyTorch tutorial for learners
Stars: ✭ 97 (+7.78%)
Mutual labels: cnn, lstm, rnn, lstm-neural-networks
Personality Detection
Implementation of a hierarchical CNN based model to detect Big Five personality traits
Stars: ✭ 338 (+275.56%)
Mutual labels: cnn, lstm, lstm-neural-networks
Bitcoin Price Prediction Using Lstm
Bitcoin price Prediction ( Time Series ) using LSTM Recurrent neural network
Stars: ✭ 67 (-25.56%)
Mutual labels: lstm, rnn, lstm-neural-networks
Machine Learning
My Attempt(s) In The World Of ML/DL....
Stars: ✭ 78 (-13.33%)
Mutual labels: lstm, rnn, attention
Base-On-Relation-Method-Extract-News-DA-RNN-Model-For-Stock-Prediction--Pytorch
基於關聯式新聞提取方法之雙階段注意力機制模型用於股票預測
Stars: ✭ 33 (-63.33%)
Mutual labels: lstm, rnn, attention
Unet Zoo
A collection of UNet and hybrid architectures in PyTorch for 2D and 3D Biomedical Image segmentation
Stars: ✭ 302 (+235.56%)
Mutual labels: cnn, lstm, rnn
Multi Class Text Classification Cnn Rnn
Classify Kaggle San Francisco Crime Description into 39 classes. Build the model with CNN, RNN (GRU and LSTM) and Word Embeddings on Tensorflow.
Stars: ✭ 570 (+533.33%)
Mutual labels: cnn, lstm, rnn
DrowsyDriverDetection
This is a project implementing Computer Vision and Deep Learning concepts to detect drowsiness of a driver and sound an alarm if drowsy.
Stars: ✭ 82 (-8.89%)
Mutual labels: lstm, rnn, lstm-neural-networks
Stockpriceprediction
Stock Price Prediction using Machine Learning Techniques
Stars: ✭ 700 (+677.78%)
Mutual labels: lstm, rnn, lstm-neural-networks
Deep Music Genre Classification
🎵 Using Deep Learning to Categorize Music as Time Progresses Through Spectrogram Analysis
Stars: ✭ 23 (-74.44%)
Mutual labels: cnn, lstm, rnn
Rnn Theano
使用Theano实现的一些RNN代码，包括最基本的RNN，LSTM，以及部分Attention模型，如论文MLSTM等
Stars: ✭ 31 (-65.56%)
Mutual labels: cnn, lstm, rnn
automatic-personality-prediction
[AAAI 2020] Modeling Personality with Attentive Networks and Contextual Embeddings
Stars: ✭ 43 (-52.22%)
Mutual labels: lstm, rnn, attention
lstm-electric-load-forecast
Electric load forecast using Long-Short-Term-Memory (LSTM) recurrent neural network
Stars: ✭ 56 (-37.78%)
Mutual labels: lstm, rnn, lstm-neural-networks
Basicocr
BasicOCR是一个致力于解决自然场景文字识别算法研究的项目。该项目由长城数字大数据应用技术研究院佟派AI团队发起和维护。
Stars: ✭ 336 (+273.33%)
Mutual labels: cnn, lstm, rnn
EBIM-NLI
Enhanced BiLSTM Inference Model for Natural Language Inference
Stars: ✭ 24 (-73.33%)
Mutual labels: lstm, rnn, attention
Video Classification
Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101
Stars: ✭ 543 (+503.33%)
Mutual labels: cnn, lstm, rnn
Deepseqslam
The Official Deep Learning Framework for Route-based Place Recognition
Stars: ✭ 49 (-45.56%)
Mutual labels: cnn, lstm, rnn
Lightnet
Efficient, transparent deep learning in hundreds of lines of code.
Stars: ✭ 243 (+170%)
Mutual labels: cnn, lstm, rnn
Automatic speech recognition
End-to-end Automatic Speech Recognition for Madarian and English in Tensorflow
Stars: ✭ 2,751 (+2956.67%)
Mutual labels: cnn, lstm, rnn
Text Classification
Implementation of papers for text classification task on DBpedia
Stars: ✭ 682 (+657.78%)
Mutual labels: cnn, lstm, attention
DNN for text classify
中文文本分类
├── Model 模型文件夹
│ ├── FastText.py fastText算法，调用好接口
│ ├── NeuralBOW.py NBOW算法，可以作为base
│ ├── __init__.py __init__
│ ├── textCnn.py textCNN
│ └── textLstm.py textRnn，这里使用lstm
│ └── textDynamicRNN.py DynaicRnn，这里使用lstm
├── README.md
├── __init__.py
├── data
│ ├── fastTextData fastText对应的数据
│ │ ├── train_data 训练集
│ │ └── valid_data 测试集
│ └── pkl DNN对应的处理好的数据
│ ├── test.pkl DNN对应的测试集
│ └── train.pkl DNN对应的训练集
├── data.tar 源数据
├── preprocess.py 预处理数据，将源文本数据处理成NN和fastText所需要的特征
NNfeature NNfeature
fastTextfeature fastText特征
DynamicRnnfeature DynamicRnn特征
└── train.py 训练模型，将每个NN模型对应训练测试过程封装成类
NeuralBowTrain 训练NeuralBow
textCnnTrain 训练textCnn
textRnnTrain 训练textRnn
train_step 函数化的train过程
dev_step 函数化的dev过程
└── dynamicRnnTrain.py 训练DynamicRNN，将每个NN模型对应训练测试过程封装成类
'''
文本采用压缩包里面的文档，运行代码之前需要解压文件夹
解压之后的文件夹名称: data/context
执行过程：
先执行PreProcess.py
再执行train.py
代码中的参数为不走心设置，可以自行进行调参
包括epoches，mini batch大小，学习率和每个模型对应的模型参数等
后续工作：
加入多层LSTM，dynamic_rnn，attention机制
加入项目：
neural machine translate
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].