I am building a basic neural network using Keras and Tensorflow using mnist dataset using the following code:
import os
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras.datasets import mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.reshape(-1, 28*28).astype('float32') / 255.0
x_test = x_test.reshape(-1, 28*28).astype('float32') / 255.0
print(x_train.shape)
print(x_test.shape)
model = keras.Sequential(
[
keras.Input(shape=(28*28)),
layers.Dense(512, activation="relu"),
layers.Dense(256, activation="relu"),
layers.Dense(10),
]
)
model.compile(
loss = keras.losses.SparseCategoricalCrossentropy(from_logits=True),
optimizer = keras.optimizers.Adam(learning_rate=0.001),
metrics = ['accuracy'],
)
model.fit(x_train, y_train, batch_size=32, epochs=5, verbose=2)
My output is:
As we can see in the image above, each epoch is only going through 1875 (=60000/32) data points. Shouldn't it go through all the 60000 instances per epoch as there are 60000 records in training dataset?