Define steps_per_epoch in Keras

Question

I was reading the Deep Learning in Python book and wanted to understand more on the what happens when you define the steps_per_epoch and batch size. The example they use consists of 4000 images of dogs and cats, with 2000 for training, 1000 for validation, and 1000 for testing. They provide two examples of their model. One with image augmentation one without. I am confused on why they changed the batch size between the two cases.

I have understood the process is that 1 epoch is 1 pass over the entire training dataset. The batch size determines how many of the images are shown per one step. When we change the batch size, we change the number of images to be learned from. For their first example with 2000 images in training, a batch size of 20, 100 steps per epoch is logical and what they use. It will take 100 steps to see 2000 images, completing an epoch. On their next example, they implement more augmentations than re-scaling the image (6 total of rotation changes, zooms, shears, etc), the batch size increases to 32, but they left steps per epoch at 100. I assumed with the increase in batch size, steps_per_epoch declines and in this case to be 63 (round up from 62.5). Why do they leave steps_per_epoch the same in this case? In the end, does the model not see some training data or see too much data given the rounding issue?

from keras.preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(rescale=1./255)
test_datagane = ImageDataGenerator(rescale=1./255)
train_generator=train_datagen.flow_from_directory(
    train_dir,
    target_size = (150,150)
    batch_size=20 # for model 2 batch_size=32
    class_mode='binary')
validation_generator = test_datagen.flow_from_directory(
    validation_dir,
    target_size = (150,150)
    batch_size=20 # for model 2 batch_size=32
    class_mode='binary')
history = model.fit_generator(
    train_generator,
    steps_per_epoch = 100,  # same for both models
    epochs=30,
    validation_data=validation_generator,
    validation_steps=50) # same for both models

Frightera Frightera · Accepted Answer · 2021-02-10T19:47:54

With 2000 images and a batch_size = 32, it would have 62.5 steps as you stated, so you can not have 100 steps with 32 batch size. Here's what happens if you specify steps to 100:

WARNING:tensorflow:Your input ran out of data; interrupting training. 
Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches.

Also that's what will you see, if you want to print length of generator:

len(train_generator) = 63, batch_size = 32
len(train_generator) = 50, batch_size = 20

Define steps_per_epoch in Keras

1 Answers