https://github.com/eliorc/tavolo

Collection of deep learning modules and functionality for the TensorFlow-Keras framework
https://github.com/eliorc/tavolo

deep-learning tensorflow tf-keras

Last synced: about 1 month ago
JSON representation

Collection of deep learning modules and functionality for the TensorFlow-Keras framework

• Host: GitHub
• URL: https://github.com/eliorc/tavolo
• Owner: eliorc
• License: mit
• Created: 2019-04-21T10:05:13.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2023-02-16T06:10:53.000Z (over 1 year ago)
• Last Synced: 2023-03-02T21:15:27.670Z (over 1 year ago)
• Topics: deep-learning, tensorflow, tf-keras
• Language: Python
• Homepage:
• Size: 193 KB
• Stars: 51
• Watchers: 6
• Forks: 5
• Open Issues: 5
• Metadata Files:
  • Readme: README.rst
  • License: LICENSE

Awesome Lists containing this project

README

        
.. raw:: html

    


      



    


------------

.. image:: https://img.shields.io/badge/python-3.6+-blue.svg

    :alt: Supported Python versions

.. image:: https://img.shields.io/badge/tensorflow-2.7.2+-orange.svg

    :alt: Supported TensorFlow versions

.. image:: https://codecov.io/gh/eliorc/tavolo/branch/master/graph/badge.svg

    :target: https://codecov.io/gh/eliorc/tavolo

    :alt: Code test coverage

Tavolo

======

| `tavolo`_ aims to package together valuable modules and functionality written for `TensorFlow`_ high-level Keras API for ease of use.

| You see, the deep learning world is moving fast, and new ideas keep on coming.

| tavolo gathers implementations of these useful ideas from the community (by contribution, from `Kaggle`_ etc.)

  and makes them accessible in a single PyPI hosted package that compliments the `tf.keras`_ module.

Documentation

-------------

| `Tavolo documentation`_

.. _`Tavolo documentation`: https://tavolo.readthedocs.io/

Showcase

--------

| tavolo's API is straightforward and adopting its modules is as easy as it gets.

| In tavolo, you'll find implementations for basic like `PositionalEncoding`_ and non-layer implementations that

  can ease development, like the `LearningRateFinder`_.

| For example, if we wanted to add head a Yang-style attention mechanism into our model and look for the optimal

  learning rate, it would look something like:

.. code-block:: python3

    import tensorflow as tf

    import tavolo as tvl

    model = tf.keras.Sequential([

        tf.keras.layers.Embedding(input_dim=vocab_size, output_dim=embedding_size, input_length=max_len),

        tvl.seq2vec.YangAttention(n_units=64),  # <--- Add Yang style attention

        tf.keras.layers.Dense(n_hidden_units, activation='relu'),

        tf.keras.layers.Dense(1, activation='sigmoid')])

    model.compile(optimizer=tf.keras.optimizers.SGD(), loss=tf.keras.losses.BinaryCrossentropy())

    # Run learning rate range test

    lr_finder = tvl.learning.LearningRateFinder(model=model)

    learning_rates, losses = lr_finder.scan(train_data, train_labels, min_lr=0.0001, max_lr=1.0, batch_size=128)

    ### Plot the results to choose your learning rate

.. _`tavolo`: https://github.com/eliorc/tavolo

.. _`TensorFlow`: https://www.tensorflow.org/

.. _`Kaggle`: https://www.kaggle.com

.. _`tf.keras`: https://www.tensorflow.org/guide/keras

.. _`PositionalEncoding`: https://tavolo.readthedocs.io/en/latest/embeddings.html#module-embeddings.PositionalEncoding

.. _`MultiHeadedAttention`: https://tavolo.readthedocs.io/en/latest/seq2seq.html#multi-headed-self-attention

.. _`LearningRateFinder`: https://tavolo.readthedocs.io/en/latest/learning.html#learning-rate-finder

Contributing

------------

| Want to contribute? Please read our `Contributing guide`_.

.. _`Contributing guide`: https://tavolo.readthedocs.io/en/latest/contributing.html