bfp

backpack-for-pytorch

BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.

Showing:

Popularity

Downloads/wk

0

GitHub Stars

330

Maintenance

Last Commit

3mos ago

Contributors

10

Package

Dependencies

24

License

MIT

Categories

Readme

BackPACK BackPACK: Packing more into backprop

Travis Coveralls Python 3.6+

BackPACK is built on top of PyTorch. It efficiently computes quantities other than the gradient.

Provided quantities include:

  • Individual gradients from a mini-batch
  • Estimates of the gradient variance or second moment
  • Approximate second-order information (diagonal and Kronecker approximations)

Motivation: Computation of most quantities is not necessarily expensive (often just a small modification of the existing backward pass where backpropagated information can be reused). But it is difficult to do in the current software environment.

Installation

pip install backpack-for-pytorch

Examples

Contributing

BackPACK is actively being developed. We are appreciating any help. If you are considering to contribute, do not hesitate to contact us. An overview of the development procedure is provided in the developer README.

How to cite

If you are using BackPACK, consider citing the paper

@inproceedings{dangel2020backpack,
    title     = {Back{PACK}: Packing more into Backprop},
    author    = {Felix Dangel and Frederik Kunstner and Philipp Hennig},
    booktitle = {International Conference on Learning Representations},
    year      = {2020},
    url       = {https://openreview.net/forum?id=BJlrF24twB}
}

Rate & Review

Great Documentation0
Easy to Use0
Performant0
Highly Customizable0
Bleeding Edge0
Responsive Maintainers0
Poor Documentation0
Hard to Use0
Slow0
Buggy0
Abandoned0
Unwelcoming Community0
100