Release v1.0.16

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

v1.0.15

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

v1.0.14

• 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.

v1.0.13 Release

• 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.

v1.0.12 Release

• 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(...).

v1.0.11 Release

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

v1.0.10 Release

• 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.

v1.0.9 Release

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

v1.0.8 Release

• 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.

v1.0.7 Release

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