AdaNet is a lightweight and scalable TensorFlow AutoML framework for training and deploying adaptive neural networks using the AdaNet algorithm [Cortes et al. ICML 2017]. AdaNet combines several learned subnetworks in order to mitigate the complexity inherent in designing effective neural networks.
This is not an official Google product.
To get you started:
Requires Python 2.7, 3.4, 3.5, or 3.6.
adanet depends on bug fixes and enhancements not present in TensorFlow releases prior to 1.9. You must install or upgrade your TensorFlow package to at least 1.9:
$ pip install "tensorflow>=1.9.0"
Installing with Pip
$ pip install adanet
Installing from source
To install from source first you'll need to install
bazel following their installation instructions.
cd into its root directory:
$ git clone https://github.com/tensorflow/adanet && cd adanet
adanet root directory run the tests:
$ cd adanet $ bazel test -c opt //...
Once you have verified that everything works well, install
adanet as a pip package .
You are now ready to experiment with
AdaNet is released under the Apache License 2.0.