Suppose you have a NN model which predicts a probability (
Sigmoid in the last layer and
BCELoss as a loss function), and the target column has the values
False, a you use roc_auc as a accuracy metric.
- How can you perform an Error Analysis? I mean … take a look at the missclassified samples
- How can I know if a sample was missclassified? I don’t have any probability threshold to classify a sample as