I have a dataset of 1061 samples, and I am using the following: epochs = 50 batch_size=20 dataset = dataset.repeat(epochs).batch(batch_size) Now if I use : model.fit(dataset , epochs = epochs , batch_size = batch_size) What will be the number of samples that will be input to the model in one epoch of training ? Is it 1061 ? Or 1061 * 50 = 53050 samples ? I searched for how does the dataset.repeat() works , but I am still confused about how it works with model.fit() specifically. Continue reading...