Predictions on test dataset with metrics

I’m trying to predict using a image classifier on the whole test dataset. Along with the predictions, I want to include the metrics such as F1 score (which fast ai already provides), precision, recall, etc on the whole test dataset.

Can someone give me an insight on how to best do it (instead of me maintaining the number of True Positives, False Positives, etc and calculate the required metrics in the end)?

1 Like