tensorflow/adanet
A TensorFlow-based AutoML framework that automatically learns neural network architectures and ensembles.
Not currently ranked — collecting fresh signals.
star history
AdaNet is a lightweight framework for automatically learning high-quality models with learning guarantees. It builds neural networks as ensembles of subnetworks, using the AdaNet algorithm presented at ICML 2017. The framework provides Keras and Estimator APIs for training, evaluating, and serving models, and supports distributed training across GPUs and TPUs.
Frequently asked
- What is tensorflow/adanet?
- A TensorFlow-based AutoML framework that automatically learns neural network architectures and ensembles.
- Is adanet open source?
- Yes — tensorflow/adanet is open source, released under the Apache-2.0 license.
- What language is adanet written in?
- tensorflow/adanet is primarily written in Jupyter Notebook.
- How popular is adanet?
- tensorflow/adanet has 3.5k stars on GitHub.
- Where can I find adanet?
- tensorflow/adanet is on GitHub at https://github.com/tensorflow/adanet.