Utilities for training and visualizations #143
Conversation
arccnet/models/dataset_utils.py
Outdated
There was a problem hiding this comment.
Probably best to not have this hard coded
arccnet/models/dataset_utils.py
Outdated
There was a problem hiding this comment.
read from config - or pass as variable
arccnet/models/dataset_utils.py
Outdated
There was a problem hiding this comment.
Maybe use units or failing that np.radtodeg or np.degtorad
arccnet/models/train_utils.py
Outdated
|
Eh looks much better the example code is evaluated so it has to run which is why the test are failing. The examples are great but don't need them on every function if it not trivial to setup the variables etc |
arccnet/models/tests/test_utils.py
Outdated
There was a problem hiding this comment.
This shouldn't be necessary
| if __name__ == "__main__": | |
| pytest.main([__file__]) |
setup.cfg
Outdated
There was a problem hiding this comment.
We need a strategy here specifically if we change a major version 1.x.y to 2.x.y probably need rerun the dataset generation and training
arccnet/catalogs/flares/helio.py
Outdated
There was a problem hiding this comment.
So this is a sunpy version update change so need to be careful with these
arccnet/models/labels.py
Outdated
There was a problem hiding this comment.
If these should be treated as constants would usually uppercase them?
… be should be treated as constants
2 participants
No description provided.