keras: what is the difference between model.predict and model.predict_proba

Question

I found model.predict and model.predict_proba both give an identical 2D matrix representing probabilities at each category for each row.

What is the difference of the two functions?

Answer 1

Predict method:

predict(self, x, batch_size=32, verbose=0)

This function generates output predictions for the input samples, processing the samples in batches.

It will return a NumPy array of predictions.

Predict_proba method:

predict_proba(self, x, batch_size=32, verbose=1)

It generates class probability predictions for the input samples batch by batch.

It also returns a numpy array of probability predictions.

Hope this answer helps.