Caleydo / confusionflow-ui

Visualize learning dynamics in multi-class image classifiers (e.g., convolutional neural networks) 💬 @gfrogat @thinkh

Home Page:https://confusionflow.org

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Update precision/recall after subsetting of confusion matrix

thinkh opened this issue · comments

Currently the metrics curves (precision, recall, F1 score) are always computed for the whole confusion matrix. When filtering classes (i.e., subsetting the confusion matrix) these curves must be updated based on the selected set of classes.

Performance metrics for 10 classes:

image

Same performance metrics for 4 classes:
image

@gfrogat Check how the subsetting/computation is handled.

It seems that it is already correct, please check the computed performance values.