Skip to content
This repository has been archived by the owner on Mar 21, 2024. It is now read-only.

Minor changes to CovidModel config parameters and updated report #554

Merged
merged 5 commits into from
Aug 25, 2021

Conversation

Shruthi42
Copy link
Contributor

  • Do inference on both validation and test sets by default in the CovidModel config
  • Add parameter pretraining_dataset_id to NIH_COVID_BYOL to specify the training dataset
  • Update report in CovidModel

InnerEye/ML/configs/classification/CovidModel.py Outdated Show resolved Hide resolved
InnerEye/ML/configs/classification/CovidModel.py Outdated Show resolved Hide resolved
LoggingColumns.ModelOutput.value: [np.argmax(predictions)],
LoggingColumns.Label.value: [np.argmax(labels)]})
pred_cvx03vs12 = predictions[1] + predictions[2]
label_cvx03vs12 = 1 if labels[1] or labels[2] else 0
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

minor: for this kind of statement I believe the intent would be clearer with int(labels[1] or labels[2])

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

sorry, I meant label_cvx03vs12 = int(labels[1] or labels[2]). on second thought it may be better to revert to how it was initially, for consistency with the rest 🙂

InnerEye/ML/configs/classification/CovidModel.py Outdated Show resolved Hide resolved
@Shruthi42 Shruthi42 enabled auto-merge (squash) August 25, 2021 12:31
@Shruthi42 Shruthi42 merged commit 38a0313 into main Aug 25, 2021
@Shruthi42 Shruthi42 deleted the shbannur/update-covid-report branch August 25, 2021 13:24
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants