I'm not using "ImageDataGenerator" because I'm using hdf5 files. I used DataGenerator class (1) to feed data to the "model.fit_generator". So how can I get the confusion matrix given that I have batches of random data? Notice that I know how get it with "model.predict" using sklearn.
(1) https://stanford.edu/~shervine/blog/keras-how-to-generate-data-on-the-fly#