model_fit_generator_methods.py

# Augmenting on the fly with fit_generator()

# Directly use .flow()
model.fit_generator(datagen.flow(x_train, y_train, batch_size=batch_size), 
                    epochs=epochs, # one forward/backward pass of training data
                    steps_per_epoch=x_train.shape[0]//batch_size, # number of images comprising of one epoch
                    validation_data=(x_test, y_test), # data for validation
                    validation_steps=x_test.shape[0]//batch_size)

# or use iterator from .flow_from_directory()
model.fit_generator(train_generator, 
                    epochs=epochs,  # one forward/backward pass of training data
                    steps_per_epoch=x_train.shape[0]//batch_size,  # number of images comprising of one epoch
                    validation_data=(x_test, y_test), # Or validation_data=valid_generator
                    validation_steps=x_test.shape[0]//batch_size)

# or use iterator from .flow_from_datafram()
model.fit_generator(train_generator_df, 
                    epochs=epochs,  # one forward/backward pass of training data
                    steps_per_epoch=x_train.shape[0]//batch_size,  # number of images comprising of one epoch
                    validation_data=(x_test, y_test),  # Or validation_data=valid_generator
                    validation_steps=x_test.shape[0]//batch_size)