Breaking changes

• Requires keras>=3.0.0 instead of tf.keras.
• Removed the structured data related tasks by removing the following public
  APIs:
  • CategoricalToNumerical
  • MultiCategoryEncoding
  • StructuredDataInput
  • StructuredDataBlock
  • StructuredDataClassifier
  • StructuredDataRegressor
• Removed the Time series related tasks by removing the following public APIs:
  • TimeseriesInput
  • TimeseriesForecaster
• Reduced search space of Text related tasks by removing the following blocks.
  • Embedding
  • TextToIntSequence
  • TextToNgramVector
  • Transformer

New Contributors

• @nkovela1 made their first contribution in https://github.com/keras-team/autokeras/pull/1851
• @berab made their first contribution in https://github.com/keras-team/autokeras/pull/1883
• @Red54 made their first contribution in https://github.com/keras-team/autokeras/pull/1893

Full Changelog: https://github.com/keras-team/autokeras/compare/1.1.0...2.0.0

Release v1.1.0

Breaking changes

• This only affect you if you use BertTokenizer or BertEncoder in AutoKeras explicity. You are not affected if you only use BertBlock, TextClassifier or TextRegressor. Removed the AutoKeras implementation of BertTokenizer and BertEncoder. Use keras-nlp implementation instead.

Bug fixes

• Now also support numpy>=1.24.

New Contributors

• @Psyrbin made their first contribution in https://github.com/keras-team/autokeras/pull/1779
• @buti1021 made their first contribution in https://github.com/keras-team/autokeras/pull/1782
• @Owaiskhan9654 made their first contribution in https://github.com/keras-team/autokeras/pull/1799

Full Changelog: https://github.com/keras-team/autokeras/compare/1.0.20...1.1.0

Highlights

• Minor bug fixes to prepare for new KerasTuner release.

What's Changed

• update version to 1.0.20dev by @haifeng-jin in https://github.com/keras-team/autokeras/pull/1718
• Fixed #1725 Auto labelling of issues by @Anselmoo in https://github.com/keras-team/autokeras/pull/1726
• Fixed #1738 Linked the Python and TensorFlow to release pages by @Anselmoo in https://github.com/keras-team/autokeras/pull/1739
• Update actions.yml by @haifeng-jin in https://github.com/keras-team/autokeras/pull/1740
• fix tf-nightly broken by @haifeng-jin in https://github.com/keras-team/autokeras/pull/1741
• fix tf-nightly broken by @haifeng-jin in https://github.com/keras-team/autokeras/pull/1742
• Bump black from 22.3.0 to 22.6.0 by @dependabot in https://github.com/keras-team/autokeras/pull/1745
• Fixed: #1756 Replace wrong character by @Anselmoo in https://github.com/keras-team/autokeras/pull/1757
• Update settings.json by @haifeng-jin in https://github.com/keras-team/autokeras/pull/1760
• Update settings.json by @haifeng-jin in https://github.com/keras-team/autokeras/pull/1761
• Update settings.json by @haifeng-jin in https://github.com/keras-team/autokeras/pull/1762
• update readme by @haifeng-jin in https://github.com/keras-team/autokeras/pull/1764
• fix bug serializing block arguments by @haifeng-jin in https://github.com/keras-team/autokeras/pull/1766
• 1.0.20 by @haifeng-jin in https://github.com/keras-team/autokeras/pull/1767

New Contributors

• @dependabot made their first contribution in https://github.com/keras-team/autokeras/pull/1745

Full Changelog: https://github.com/keras-team/autokeras/compare/1.0.19...1.0.20

What's Changed

• Compatible with TF 2.9.0.
• Support more hyperparameters as arguments to blocks.

New Contributors

• @LukeWood made their first contribution in https://github.com/keras-team/autokeras/pull/1702
• @ksohan made their first contribution in https://github.com/keras-team/autokeras/pull/1706
• @kutal10 made their first contribution in https://github.com/keras-team/autokeras/pull/1708
• @NickSmyr made their first contribution in https://github.com/keras-team/autokeras/pull/1710
• @Neproxx made their first contribution in https://github.com/keras-team/autokeras/pull/1715

Full Changelog: https://github.com/keras-team/autokeras/compare/1.0.18...1.0.19

Important Notice!

Please update to TensorFlow 2.8.0 and KerasTuner 1.1.0 to use this AutoKeras version.

What's Changed

• Bug fix for compatibility issue with kt 1.1.0 by @haifeng-jin in https://github.com/keras-team/autokeras/pull/1687

New Contributors

• @reedwm made their first contribution in https://github.com/keras-team/autokeras/pull/1675

Full Changelog: https://github.com/keras-team/autokeras/compare/1.0.17...1.0.18

What's Changed

• Fix broken link in docs by @htbkoo
• Adapt to tf 2.8.0
• Adapt to KerasTuner 1.1.0

New Contributors

• @htbkoo made their first contribution in https://github.com/keras-team/autokeras/pull/1618

Full Changelog: https://github.com/keras-team/autokeras/compare/1.0.16...1.0.17

• Support returning history in .fit() function if validation_data is not provided.
• Pin the TF version to 2.5.0 or lower.
• Pin the KerasTuner version to 1.0.x and less than 1.1.

What's Changed

• Fix broken link in docs by @htbkoo in https://github.com/keras-team/autokeras/pull/1618
• Adapt to tf-nightly by @haifeng-jin in https://github.com/keras-team/autokeras/pull/1634
• Adapt to KerasTuner 1.1.0 by @haifeng-jin in https://github.com/keras-team/autokeras/pull/1640

New Contributors

• @htbkoo made their first contribution in https://github.com/keras-team/autokeras/pull/1618

Full Changelog: https://github.com/keras-team/autokeras/compare/1.0.16...1.0.17rc1

• Temporarily depending on tf-nightly.

What's Changed

• Fix broken link in docs by @htbkoo in https://github.com/keras-team/autokeras/pull/1618
• Adapt to tf-nightly by @haifeng-jin in https://github.com/keras-team/autokeras/pull/1634

New Contributors

• @htbkoo made their first contribution in https://github.com/keras-team/autokeras/pull/1618

Full Changelog: https://github.com/keras-team/autokeras/compare/1.0.16...1.0.17rc0

• Support returning history in .fit() function if validation_data is not provided.
• Pin the TF version to 2.5.0 or lower.

• Adapt to KerasTuner 1.0.3.
• Raise the minimum version requirement for KerasTuner to 1.0.3.

• Support TensorFlow 2.5.0.
• Beta release of Timeseries Forecasting. Tutorial
• More blocks support passing hyperparameters to arguments. Including BertBlock, RNNBlock, Transformer, and Embedding. Code Example
• Support verbose argument for AutoModel.fit, AutoModel.predict, and AutoModel.evaluate.
• Move the download of weights of pretrained BERT to GitHub assets.

• Support TensorFlow 2.5.0.
• Beta release of Timeseries Forecasting. Tutorial
• More blocks support passing hyperparameters to arguments. Including BertBlock, RNNBlock, Transformer, and Embedding. Code Example
• Support verbose argument for AutoModel.fit, AutoModel.predict, and AutoModel.evaluate.

• Compatible with TensorFlow 2.4.
• Support specify search space for num_units, num_layers, and dropout of DenseBlock. Code Example
• Support specify search space for filters, num_blocks, and num_layers of ConvBlock.
• Add Keras Tuner to dependency to be installed automatically.
• Bug fix for multi-model data AutoModel.predict(...).

• Compatible with TensorFlow 2.4.
• Support specify search space for num_units, num_layers, and dropout of DenseBlock. Code Example

• Reduces batch_size by 2 when running out of memory.
• Add pretrained EfficientNet to the search space.
• Support load data from disk. For more details, read our tutorials on the official website.
• Put data type casting and reshaping into the exported Keras Model.
• Fixed the bug of breaking when validation_data is a tf.data.Dataset instance.

• Improved text data performance by adding pretrained BERT model to the search space.
• Added Adam optimizer with weight decay to the search space.

• Performance improvements for structured data classification and regression tasks.
• Bug fix for not using the best number of epochs for the final model training when validation data is not provided.

• Bug fix for using multiple GPUs.
• Bug fix for KeyError when searching for large number of trials.
• Grammar fixes for error messages.

• Reduced GPU memory consumption.
• Optimized greedy tuning algorithm.
• Support using multiple GPUs.