BackPACK Logo
master

Getting started

  • How to use BackPACK
  • Example using all extensions

Backpack

  • Supported models
  • Available Extensions
  • Good to know
  • Code examples and use cases
BackPACK
  • BackPACK
  • Edit on GitHub

BackPACK

BackPACK is a library built on top of PyTorch to extract more information from a backward pass.

pip install backpack-for-pytorch

For a quick overview of the features, check backpack.pt. The code lives on Github.

Getting started

  • How to use BackPACK
    • Extending the model and loss function
    • Calling the extension
  • Example using all extensions
    • First order extensions
    • Second order extensions
    • Block-diagonal curvature products

Backpack

  • Supported models
    • For first-order extensions
    • For second-order extensions
  • Available Extensions
    • First order extensions
    • BatchGrad()
    • BatchL2Grad()
    • SumGradSquared()
    • Variance()
    • Second order extensions
    • DiagGGNMC()
    • DiagGGNExact()
    • BatchDiagGGNMC()
    • BatchDiagGGNExact()
    • KFAC()
    • KFLR()
    • KFRA()
    • DiagHessian()
    • BatchDiagHessian()
    • SqrtGGNExact()
    • SqrtGGNMC()
    • Block-diagonal curvature products
    • HMP()
    • GGNMP()
    • PCHMP()
  • Good to know
    • Check that BackPACK does what you think it should do
    • Aggregating quantities and zero_grad()
    • extend-ing for first and second-order extension
    • Not (yet) supported models
  • Code examples and use cases
Next

© Copyright 2019, F. Dangel, F. Kunstner. Revision ffa60683.

Built with Sphinx using a theme provided by Read the Docs.
Read the Docs v: master
Versions
master
1.5.0
1.4.0
1.3.0
1.2.0
development
Downloads
On Read the Docs
Project Home
Builds