CNN-LSTM-Text-Classification
Apply CNN-LSTM model on multi-class text classification task.
After setting the model configerations in train.py run the following commands in terminal.
train.py
$ python train.py
and view the result in tensorboard (you could replace the path after --logdir by yours).
--logdir
$ tensorboard --logdir='1536427044/runs/summaries'
still faced with the problem of overfitting. I have tried l2 regularization and dropout, cannot see a good improvement. If you guys who view this repo and has alternatives, leave comments here.
上一篇:Text_Classification_Using_CNN
下一篇:text-classification-by-cnn
还没有评论,说两句吧!
热门资源
seetafaceJNI
项目介绍 基于中科院seetaface2进行封装的JAVA...
spark-corenlp
This package wraps Stanford CoreNLP annotators ...
Keras-ResNeXt
Keras ResNeXt Implementation of ResNeXt models...
capsnet-with-caps...
CapsNet with capsule-wise convolution Project ...
inferno-boilerplate
This is a very basic boilerplate example for pe...
智能在线
400-630-6780
聆听.建议反馈
E-mail: support@tusaishared.com