search

TorchJD / torchjd

Library for Jacobian descent with PyTorch. It enables optimization of neural networks with multiple losses (e.g. multi-task learning).
https://torchjd.org
MIT License
151 stars 0 forks source link

Add check that the tensor expects a .grad field in Store._compute. #106

Closed ValerianRey closed 2 months ago

ValerianRey commented 2 months ago
ValerianRey commented 2 months ago

To squash and merge with the following title and message:

Add check that the tensor expects a .grad field in Store._compute. (#106)

* Add new failing tests for Store
* Add check that the tensor expects a .grad field in Store._compute.
* Add changelog entry