AutoML library for deep learning
APACHE-2.0 License
Bot releases are visible (Hide)
Published by haifeng-jin about 4 years ago
Published by haifeng-jin about 4 years ago
Bug Fixes:
New Features:
API Changes:
pooling
argument removed.overwrite=False
by default.dropout_rate
arguments to dropout
.Published by haifeng-jin over 4 years ago
Bump dependency TensorFlow version to 2.2.0.
User now can use custom metrics and loss.
User now can specify the tuner to use for Task APIs like ImageClassifier.
Use Keras preprocessing layers for ImageAugmentation.
If not epochs is not specified, and validation_data is not provided,
it will use the best models best number of epochs for retraining the best model with the entire training set.
Bug fixes:
All bugs in the tutorials are fixed.
All the tutorials can run smoothly.
Breaking changes:
ImageAugmentation args updated.
Published by haifeng-jin over 4 years ago
Fixed the bug for low performance in the final model training.
Fixed the bug for does not support tf.data.Dataset for TextClassifier.
Improved performance for ImageClassifier and TextClassifier.
Issues:
It cannot save the preprocessing layers' weights.
The exported model has to be adapted manually if contains any preprocessing layer.
It should be fixed with TF 2.2.
We will have another release afterward.
Published by haifeng-jin over 4 years ago
Supporting Tensorflow Keras preprocessing layers.
The preprocessors are now exportable to Keras Model, too,
i.e., the entire model is exportable to Keras Model.
The exported model should have exactly the sample performances as the searched model.
Published by haifeng-jin almost 5 years ago
Redesigned the API and system architecture based on KerasTuner 1.0 and TensorFlow 2.0.
Refer to the official website for more information. https://autokeras.com/
Published by haifeng-jin almost 5 years ago
Published by haifeng-jin over 5 years ago
Use BERT to do the natural language tasks.
Pretrained models separated out to autokeras-pretrained.
Tabular module separated out to autokaggle.
Published by haifeng-jin over 5 years ago
Published by haifeng-jin almost 6 years ago
Fixed some bugs.
Code refactored.
Added Predefined API.
Added pretrained models of face detection, object detection, voice generation.
Published by haifeng-jin almost 6 years ago
Fixed the CUDA: out of memory bug.
Refined the interface for net_module.
Published by haifeng-jin almost 6 years ago
Published by haifeng-jin almost 6 years ago
Published by haifeng-jin almost 6 years ago
Improved neural architecture search performance.
Published by haifeng-jin almost 6 years ago
Fixed the bug in dependencies of setup.py
Published by haifeng-jin almost 6 years ago
A comparatively stable version.
Published by haifeng-jin almost 6 years ago
Fixed the memory limit bug.
Published by haifeng-jin about 6 years ago
Refined the output information on screen.
Published by haifeng-jin about 6 years ago
Updated output information.
Published by haifeng-jin about 6 years ago
Fixing the bugs caused by floating point.