Metadata-Version: 1.1
Name: caver
Version: 0.0.6
Summary: Multi-label Text Classification Toolkit
Home-page: https://github.com/guokr/Caver
Author: Guokr Inc.
Author-email: jinyang.zhou@guokr.com
License: UNKNOWN
Description: # Caver: a toolkit for multilabel text classification.
        
        [中文版](./README_zh.md)
        
        ---
        
        Rising a torch in the cave to see the words on the wall. This is the `Caver`.
        
        [Documents](https://guokr.github.io/Caver)
        
        ## Requirements
        
        * PyTorch
        * tqdm
        * torchtext
        * scipy
        * numpy
        * Python3
        
        ## How to train on your onw dataset
        
        ```python
        
        python3 train.py --input_data_dir {path to your origin dataset} --output_data_dir {path to store the preprocessed dataset} --train_filename train.tsv --valid_filename valid.tsv --checkpoint_dir {path to save the checkpoints} --model {fastText/CNN/LSTM} --batch_size {16, you can modify this for you own} --epoch {10}
        
        ```
        
        ## Did you guys have some pre-trained models
        
        Yes 
        
        ## How to setup the models for inference
        
        Basicly just setup the model and target labels, you can check examples in server.py and ensemble.py
        
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Topic :: Text Processing
Classifier: Topic :: Text Processing :: Indexing
Classifier: Topic :: Text Processing :: Linguistic
