Hi Vasu Bhaiya,
steps_per_epoch=(number_of training examples)/(batch_size)
This formula ensures that we cover all the training data in 1 epoch.
In tiny-imagenet 200 dataset
I came across training_data=100,000
Sir kept batch_size=128
Then steps_per_epoch = 781 ??
Kindly confirm…
Also if we use ImageDataGenerator to load the data as well as augment the data.
Why do we call it to have infinite training data?