Awesome Open Source
Awesome Open Source

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

✅ : Working
◽️ : Not tested yet.

  • evaluate : Evaluate on the evaluation data.
  • ◽️ extend_train_hooks : Extends the hooks for training.
  • ◽️ reset_export_strategies : Resets the export strategies with the new_export_strategies.
  • ◽️ run_std_server : Starts a TensorFlow server and joins the serving thread.
  • ◽️ test : Tests training, evaluating and exporting the estimator for a single step.
  • train : Fit the estimator using the training data.
  • train_and_evaluate : Interleaves training and evaluation.

Tensorboard

tensorboard --logdir logs

  • Category Color

category_image

  • rt-polarity (binary classification)

images

  • kaggle_movie_review (multiclass classification)

images

Reference


Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
Python (1,126,520
Deep Learning (22,383
Tensorflow (12,575
Nlp (7,908
Classification (3,033
Sentiment Analysis (2,006
Tensorflow Models (276
Related Projects