Releases: f-dangel/backpack
Releases · f-dangel/backpack
Version 1.7.1
Compare
Sorry, something went wrong.
No results found
For details, see the changelog .
Version 1.7.0
Compare
Sorry, something went wrong.
No results found
For details, see the changelog .
Version 1.6.0
Compare
Sorry, something went wrong.
No results found
See the changelog for details
Version 1.5.2
Compare
Sorry, something went wrong.
No results found
For details, refer to the changelog .
Version 1.5.1
Compare
Sorry, something went wrong.
No results found
For details, refer to the changelog .
Version 1.5.0
Compare
Sorry, something went wrong.
No results found
For details see the changelog .
Version 1.4.0
Compare
Sorry, something went wrong.
No results found
See the changelog for details.
Version 1.3.0
Compare
Sorry, something went wrong.
No results found
See the changelog for details.
1.2.0
Compare
Sorry, something went wrong.
No results found
Added
Deprecated python3.5, tested compatibility with PyTorch 1.6.0 [PR ]
Support first-order extensions for Conv1d, Conv3d,
ConvTranspose1d, ConvTranspose2d, ConvTranspose3d
extensions.BatchGrad [PR ]
extensions.BatchL2Grad [PR ]
extensions.SumGradSquared and extensions.Variance [PR ]
Raise exceptions for unsupported exotic hyperparameters [PR1 , PR2 ]
New example: Backpropagating through BackPACK quantities [commit ]
New extensions in API: Block-diagonal curvature products
Exposed via extensions.HMP, extensions.GGNMP, extensions.PCHMP [PR ]
Examples: Hutchinson trace estimation [PR ] and Hessian-free optimization with CG [PR ]
Fixed
Add missing zero_grad in the diagonal GGN second-order optimization example [PR ]
Internal
Increased test coverage
New test suite for backpack.extensions [PR ]
New test suite for backpack.core [PR ]
Implemented derivatives of the following operations in backpack.core
More activation functions [PR ]
Conv1d, Conv3d [PR ]
ConvTranspose1d, ConvTranspose2d, ConvTranspose3d [PR ]
Refactor firstorder extensions to share more code [PR1 , PR2 ]
Removed detachs to support differentiating through quantities [PR ]
1.1.1
Compare
Sorry, something went wrong.
No results found
Added
Improved documentation, moved to ReadTheDocs [PR1 , PR2 , PR3 ]
Tested compatibility with PyTorch 1.5.0.
Support 2nd-order backprop for vectors in MSELoss [PR ]
Sanity checks to raise warnings if the following are used.
inplace modification [PR ],
unsupported loss parameters [PR ],
custom losses in 2nd-order backpropagation [PR ]
Fixed
Removed opt_einsum dependency [PR ]
Missing implementations and wrong backpropagation of KFRA for Conv2d, MaxPool2d, and AvgPool2d [PR ]
Remove try_view and use reshape to use PyTorch 1.4.0 improvements [PR ]
Internal