BackPACK: Packing more into backprop
Project description
BackPACK is built on top of PyTorch. It efficiently computes quantities other than the gradient.
Website: https://backpack.pt Code: https://github.com/f-dangel/backpack Documentation: https://readthedocs.org/projects/backpack/ Bug reports & feature requests: https://github.com/f-dangel/backpack/issues
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
backpack-for-pytorch-1.1.1.tar.gz
(56.0 kB
view hashes)
Built Distribution
Close
Hashes for backpack-for-pytorch-1.1.1.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 44cca33038487f45fec85ef36bdce06750512f5a61c4ad3846057c40d44f32f3 |
|
MD5 | 9834010c495a5e3a4ef2ef5341692856 |
|
BLAKE2b-256 | cf59273cedc6d2e603b990a6031219829b401fb622a9e5d5c0d29e107379cc1c |
Close
Hashes for backpack_for_pytorch-1.1.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | d8f02db5fc3d5eb668a851da2e15c555fe29886d2883cd2ebc0c8b2a935f88e3 |
|
MD5 | b4cda0c5844920c3d03d5fb8e0035a62 |
|
BLAKE2b-256 | 72d3aca6e4c76fd5ce7f3a7388054eb8609cd50a254517c5df7f4980411cb59b |