GitLab

* Update README.md

adding autocast remark to readme

* Update README.md

small typo fix

* Adding notebooks for gradient analysis

* Updated the Readme

* Refactored training script for sfno

* removing concatanated skip connections

* Added some logic for initializing weights adaptively

* Cleanup and fixing initialization in SFNO. Removing non-linear variant of SFNO

* Updated initialization scheme for SFNO

* Some more cleanup in SFNO

* updated the SFNO architecture

Major Cleanup of SFNO. Retiring non-linear architecture and fixing initialization. Adding scripts for training and validation.

* Adding notebooks for gradient analysis

* Updated the Readme

Fixing issues in README.md

* Adding plotting routines and reworked Readme

* Added illustration of spherical harmonics to Readme

* Updated Changelog

* improved readability of legendre.py

* bugfix in computation of dlegpoly

* Moving conversion from numpy to torch from the legendre module to the sht module

* renaming to vdm in tests.py

* fixing contig in distributed sht

* make it normally contiguous before all to all

* commented the code to be a WAR

* reworked SFNO example

* updated changelog

* Added gradient check to test suite
* reduced size of the unit test
* switched to parametrized for unittests

fixed error in getting started notebook

Adding missing dependency to functoools.partial in sfno.py

Fix __init__.py file to import from local "examples" dir.

Fixing precision mismatch error in weight contractions

Without this fix, importing torch_harmonics had run into a module import error
when trying to execute:
```import examples```

Update __init__.py

Don't import sfno by default (or try/except importing apex)