This new release repositioned AutoKeras as a convenient library for quick experiments on small datasets with simple deep learning models, rather than a large-scale training library for distributed settings.
What's Changed
- AutoKeras works on PyTorch, JAX, and TensorFlow. PyTorch is the recommended backend.
- Added back
StructuredDataClassifier,StructuredDataRegressor,StructuredInput,StructuredDataBlock,Embedding. - Website updated with new documentation.
Breaking Changes
- Removed
BertBlock. - Removed support for using
tensorflow.data.Dataset,pandas.DataFrame, strings for file path and column name for training/validation/prediction dataset. Now, only supportsnumpy.ndarray.
New Contributors
- @fcolecumberri made their first contribution in #1929
- @mwtoews made their first contribution in #1930
Full Changelog: 2.0.0...3.0.0