K-FAC: Kronecker-Factored Approximate Curvature
K-FAC in TensorFlow is an implementation of K-FAC, an
approximate second-order optimization method, in TensorFlow. When applied to
feedforward and convolutional neural networks, K-FAC can converge >3.5x
faster in >14x fewer iterations than SGD with Momentum.
Installation
kfac is compatible with Python 2 and 3 and can be installed directly via
pip,
# Assumes tensorflow or tensorflow-gpu installed
$ pip install kfac
# Installs with tensorflow-gpu requirement
$ pip install 'kfac[tensorflow_gpu]'
# Installs with tensorflow (cpu) requirement
$ pip install 'kfac[tensorflow]'KFAC DOCS
Please check KFAC docs for detailed description with examples of how to use KFAC.