Skip to content

Conversation

@Benjamintdk
Copy link

@Benjamintdk Benjamintdk commented Jan 18, 2022

Resolves #42

  • Refactored predict.py by creating a separate function, generate_predictions, to account for cases where MODEL_PATH is either a file or directory path to saved weights, and averages the results obtained for the latter
  • Added functionality at the end of the predict function to save the labels of high and low confidence examples to a csv file
  • Updated ReadMe to explain changes made

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Average predictions from the 4 ML models to find start and end times of orca calls

1 participant