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This repository has been archived by the owner on Mar 21, 2024.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

Add FP and TN to DeepMIL outputs and configure outputs for multi-class classification #679

Merged
merged 15 commits into from
Mar 4, 2022

Conversation

harshita-s
Copy link
Contributor

@harshita-s harshita-s commented Mar 1, 2022

This PR contains:

  • Extension of DeepMIL outputs to contain top/bottom FP and TN slides and tiles
  • Extension of DeepMIL outputs to multi-class problems: top/bottom TP and FN slides and tiles will be generated for each non-zero class
  • test_metrics_utils.py now includes top/bottom FP and TN slides and tiles

InnerEye/ML/Histopathology/models/deepmil.py Outdated Show resolved Hide resolved
InnerEye/ML/Histopathology/models/deepmil.py Outdated Show resolved Hide resolved
InnerEye/ML/Histopathology/models/deepmil.py Outdated Show resolved Hide resolved
InnerEye/ML/Histopathology/models/deepmil.py Show resolved Hide resolved
InnerEye/ML/Histopathology/utils/metrics_utils.py Outdated Show resolved Hide resolved
dccastro
dccastro previously approved these changes Mar 4, 2022
InnerEye/ML/Histopathology/models/deepmil.py Show resolved Hide resolved
InnerEye/ML/Histopathology/models/deepmil.py Outdated Show resolved Hide resolved
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.

None yet

3 participants