GitLab

* Support jit hessian

* fix

* fix

* Add badge to display stable torch compatibility

* more

* more

* don't run on PR

* nl

* Support  periodic table Indexing in builtin models

* flake8

* more

* fix

* fix cuda

* Add element names to ANIModel

* nc trainer

Add helper module to convert species from element id in periodic table to 0, 1, 2, 3, ... format (#396)

* Init

* fix test

* flake8

* try fix

* Fix stupidity of len(self)

This is copy-pasted from https://github.com/aiqm/torchani/blob/master/.github/workflows/deploy-test-pypi.yml but I forgot to update it...

We should use the tag created on GitHub, not add a new tag named after date

* clean up py2 in setup.py

* Update setup.py

* Use type inference of arange to clean up code

* commit

* Allow passing pbc and cell to sequential

* revert

* Simplify ase interface

* fix

* fix

* fix

* flake8

* Update ase.py

* fix

* Try latest ASE

Just to see if ASE fixes its bug

* fix

* add mypy

* update

* fix

* only core

* add badge

* try

* Use namedtuple to improve API

* improve

* Fix race condition in test docs deploy

* try

* fix

* fix

* try

* fix

* __constants__ is deprecated

* commit

* Use modern type annotations for utils.py

* update (#377)

* Remove python2 support from CI, _six, etc. (#370)

* Remove python2 step 1

* badge

* Delete _six.py

* Simplify triple_by_molecule (#368)

* Simplify triple_by_molecule

* fix

* fix

* fix

* Use @ syntax (#371)

* Use modern type annotations for nn.py (#373)

* Use modern type annotations for nn.py

* flake8

* Use modern type annotations for models.py (#374)

* Use modern type annotations for aev.py

* commit

* Use modern type annotations for nn.py

* flake8

* Simplify triple_by_molecule

* fix

* fix

* fix

* Remove python2 step 1

* badge

* Delete _six.py

* Simplify code using torch.triu_indices

* Update aev.py

* Change homepage url

I forgot to change that when I move it from zasdfgbm/torchani to aiqm/torchani...

* Update setup.py

* Remove AEV cacher

* more

* more

* more

* flake8

* further cleanup

* Don't hard code ensemble size

* flake8

* fix

* Run tests on merge master, and everyday 0:00

* test

* try

* use array

* test

* test

* test

* fix all

* push only on master

* Remove ignite

* remove neurochem-test

* remove cache-aev

* fix cuda support

* Update aev.py