Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Following a chat with @CatEek, I've come to realize that my previous attempt to pull patches from the dataloaders in order to export the model to the BMZ format was difficult to read (patches needed to be denormalized in order to be put through the BMZ pipeline).
I've decided to just force users to input an array. This can be the training or prediction arrays, this is a simple solution to having a clearer code to maintain,
CAREamist._create_data_for_bmz
,input_array
now mandatory forCAREamist.export_to_bmz
.Changes Made
CAREamist.export_to_bmz
.CAREamist._create_data_for_bmz
and corresponding tests.Breaking changes
Any code not inputing
input_array
, e.g. all notebooks examples.Currently, if the array does not have the same dimensions/axes as what the configuration states, users should get an error from the reshape function.
Additional Notes and Examples
Before, after training a model or loading a model, the following code would run:
It would create input data for the BMZ, using the following steps:
mean
andstd
in the configurationNow, users have to provide an input array:
Please ensure your PR meets the following requirements: