{"id":17100349,"url":"https://github.com/eliorc/tavolo","last_synced_at":"2025-06-12T03:13:42.271Z","repository":{"id":34914630,"uuid":"182517601","full_name":"eliorc/tavolo","owner":"eliorc","description":"Collection of deep learning modules and functionality for the TensorFlow-Keras framework","archived":false,"fork":false,"pushed_at":"2023-02-16T06:10:53.000Z","size":198,"stargazers_count":50,"open_issues_count":5,"forks_count":5,"subscribers_count":5,"default_branch":"master","last_synced_at":"2025-04-12T23:53:43.757Z","etag":null,"topics":["deep-learning","tensorflow","tf-keras"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/eliorc.png","metadata":{"files":{"readme":"README.rst","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2019-04-21T10:05:13.000Z","updated_at":"2024-01-04T16:33:07.000Z","dependencies_parsed_at":"2023-01-15T10:30:26.135Z","dependency_job_id":null,"html_url":"https://github.com/eliorc/tavolo","commit_stats":null,"previous_names":[],"tags_count":13,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eliorc%2Ftavolo","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eliorc%2Ftavolo/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eliorc%2Ftavolo/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eliorc%2Ftavolo/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/eliorc","download_url":"https://codeload.github.com/eliorc/tavolo/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248647237,"owners_count":21139083,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","tensorflow","tf-keras"],"created_at":"2024-10-14T15:13:15.049Z","updated_at":"2025-04-12T23:53:49.700Z","avatar_url":"https://github.com/eliorc.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":".. raw:: html\n\n    \u003cdiv align=\"center\"\u003e\n      \u003cimg src=\"docs/source/_static/logo.png\"\u003e\u003cbr\u003e\u003cbr\u003e\n    \u003c/div\u003e\n\n------------\n\n.. image:: https://img.shields.io/badge/python-3.6+-blue.svg\n    :alt: Supported Python versions\n\n.. image:: https://img.shields.io/badge/tensorflow-2.7.2+-orange.svg\n    :alt: Supported TensorFlow versions\n\n.. image:: https://codecov.io/gh/eliorc/tavolo/branch/master/graph/badge.svg\n    :target: https://codecov.io/gh/eliorc/tavolo\n    :alt: Code test coverage\n\nTavolo\n======\n\n| `tavolo`_ aims to package together valuable modules and functionality written for `TensorFlow`_ high-level Keras API for ease of use.\n| You see, the deep learning world is moving fast, and new ideas keep on coming.\n| tavolo gathers implementations of these useful ideas from the community (by contribution, from `Kaggle`_ etc.)\n  and makes them accessible in a single PyPI hosted package that compliments the `tf.keras`_ module.\n\n\nDocumentation\n-------------\n\n| `Tavolo documentation`_\n\n.. _`Tavolo documentation`: https://tavolo.readthedocs.io/\n\nShowcase\n--------\n\n| tavolo's API is straightforward and adopting its modules is as easy as it gets.\n| In tavolo, you'll find implementations for basic like `PositionalEncoding`_ and non-layer implementations that\n  can ease development, like the `LearningRateFinder`_.\n| For example, if we wanted to add head a Yang-style attention mechanism into our model and look for the optimal\n  learning rate, it would look something like:\n\n.. code-block:: python3\n\n    import tensorflow as tf\n    import tavolo as tvl\n\n    model = tf.keras.Sequential([\n        tf.keras.layers.Embedding(input_dim=vocab_size, output_dim=embedding_size, input_length=max_len),\n        tvl.seq2vec.YangAttention(n_units=64),  # \u003c--- Add Yang style attention\n        tf.keras.layers.Dense(n_hidden_units, activation='relu'),\n        tf.keras.layers.Dense(1, activation='sigmoid')])\n\n    model.compile(optimizer=tf.keras.optimizers.SGD(), loss=tf.keras.losses.BinaryCrossentropy())\n\n    # Run learning rate range test\n    lr_finder = tvl.learning.LearningRateFinder(model=model)\n\n    learning_rates, losses = lr_finder.scan(train_data, train_labels, min_lr=0.0001, max_lr=1.0, batch_size=128)\n\n    ### Plot the results to choose your learning rate\n\n.. _`tavolo`: https://github.com/eliorc/tavolo\n.. _`TensorFlow`: https://www.tensorflow.org/\n.. _`Kaggle`: https://www.kaggle.com\n.. _`tf.keras`: https://www.tensorflow.org/guide/keras\n.. _`PositionalEncoding`: https://tavolo.readthedocs.io/en/latest/embeddings.html#module-embeddings.PositionalEncoding\n.. _`MultiHeadedAttention`: https://tavolo.readthedocs.io/en/latest/seq2seq.html#multi-headed-self-attention\n.. _`LearningRateFinder`: https://tavolo.readthedocs.io/en/latest/learning.html#learning-rate-finder\n\n\nContributing\n------------\n\n| Want to contribute? Please read our `Contributing guide`_.\n\n.. _`Contributing guide`: https://tavolo.readthedocs.io/en/latest/contributing.html\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feliorc%2Ftavolo","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Feliorc%2Ftavolo","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feliorc%2Ftavolo/lists"}