text-cnn-tensorflow

by DongjunLee

Convolutional Neural Networks for Sentence Classification(TextCNN) implements by TensorFlow

226 Stars 65 Forks Last release: Not found 19 Commits 0 Releases

Available items

No Items, yet!

The developer of this repository has not created any items for sale yet. Need a bug fixed? Help with integration? A different license? Create a request here:

text-cnn hb-research

This code implements Convolutional Neural Networks for Sentence Classification models.

  • Figure 1: Illustration of a CNN architecture for sentence classification

figure-1

Requirements

Project Structure

init Project by hb-base

.
├── config                  # Config files (.yml, .json) using with hb-config
├── data                    # dataset path
├── notebooks               # Prototyping with numpy or tf.interactivesession
├── scripts                 # download or prepare dataset using shell scripts
├── text-cnn                # text-cnn architecture graphs (from input to logits)
    ├── __init__.py             # Graph logic
├── data_loader.py          # raw_date -> precossed_data -> generate_batch (using Dataset)
├── hook.py                 # training or test hook feature (eg. print_variables)
├── main.py                 # define experiment_fn
├── model.py                # define EstimatorSpec
└── predict.py              # test trained model       

Reference : hb-config, Dataset, experiments_fn, EstimatorSpec

Todo

  • apply embed_type
    • CNN-rand
    • CNN-static
    • CNN-nonstatic
    • CNN-multichannel

Config

example: kaggle_movie_review.yml

data:
  type: 'kaggle_movie_review'
  base_path: 'data/'
  raw_data_path: 'kaggle_movie_reviews/'
  processed_path: 'kaggle_processed_data'
  testset_size: 25000
  num_classes: 5
  PAD_ID: 0

model: batch_size: 64 embed_type: 'rand' #(rand, static, non-static, multichannel) pretrained_embed: "" embed_dim: 300 num_filters: 256 filter_sizes: - 2 - 3 - 4 - 5 dropout: 0.5

train: learning_rate: 0.00005

train_steps: 100000 model_dir: 'logs/kaggle_movie_review'

save_checkpoints_steps: 1000 loss_hook_n_iter: 1000 check_hook_n_iter: 1000 min_eval_frequency: 1000

slack: webhook_url: "" # after training notify you using slack-webhook

Usage

Install requirements.

pip install -r requirements.txt

Then, prepare dataset and train it.

sh prepare_kaggle_movie_reviews.sh
python main.py --config kaggle_movie_review --mode train_and_evaluate

After training, you can try typing the sentences what you want using

predict.py
.

python python predict.py --config rt-polarity

Predict example

python predict.py --config rt-polarity
Setting max_seq_length to Config : 62
load vocab ...
Typing anything :)

> good 1 > bad 0

Experiments modes

:whitecheckmark: : Working
:whitemediumsmall_square: : Not tested yet.

  • :whitecheckmark:
    evaluate
    : Evaluate on the evaluation data.
  • :whitemediumsmallsquare: `extendtrain_hooks` : Extends the hooks for training.
  • :whitemediumsmallsquare: `resetexportstrategies` : Resets the export strategies with the newexport_strategies.
  • :whitemediumsmallsquare: `runstd_server` : Starts a TensorFlow server and joins the serving thread.
  • :whitemediumsmall_square:
    test
    : Tests training, evaluating and exporting the estimator for a single step.
  • :whitecheckmark:
    train
    : Fit the estimator using the training data.
  • :whitecheckmark:
    train_and_evaluate
    : Interleaves training and evaluation.

Tensorboard

tensorboard --logdir logs
  • Category Color

category_image

  • rt-polarity (binary classification)

images

  • kagglemoviereview (multiclass classification)

images

Reference

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.