Number identification using Multilayer Perceptrons

import tensorflow as tf

from tensorflow.keras.datasets import mnist

from tensorflow.keras.models import Sequential

from tensorflow.keras.layers import Dense, Flatten

(x_train, y_train), (x_test, y_test) = mnist.load_data()

x_train = x_train.reshape(60000, 784).astype('float32') / 255

x_test = x_test.reshape(10000, 784).astype('float32') / 255

y_train = tf.keras.utils.to_categorical(y_train, 10)

y_test = tf.keras.utils.to_categorical(y_test, 10)

model = Sequential()

model.add(Dense(128, activation='relu', input_shape=(784,)))

model.add(Dense(64, activation='relu'))

model.add(Dense(10, activation='softmax'))

model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

model.fit(x_train, y_train, epochs=10, batch_size=128, validation_data=(x_test, y_test))

test_loss, test_acc = model.evaluate(x_test, y_test)

print('Test accuracy:', test_acc)

===============================================================================================

Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz
11490434/11490434 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step

/usr/local/lib/python3.10/dist-packages/keras/src/layers/core/dense.py:87: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.
  super().__init__(activity_regularizer=activity_regularizer, **kwargs)

Epoch 1/10
469/469 ━━━━━━━━━━━━━━━━━━━━ 6s 9ms/step - accuracy: 0.8367 - loss: 0.5865 - val_accuracy: 0.9484 - val_loss: 0.1730
Epoch 2/10
469/469 ━━━━━━━━━━━━━━━━━━━━ 5s 10ms/step - accuracy: 0.9540 - loss: 0.1528 - val_accuracy: 0.9669 - val_loss: 0.1128
Epoch 3/10
469/469 ━━━━━━━━━━━━━━━━━━━━ 3s 6ms/step - accuracy: 0.9700 - loss: 0.0989 - val_accuracy: 0.9698 - val_loss: 0.0966
Epoch 4/10
469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 5ms/step - accuracy: 0.9776 - loss: 0.0735 - val_accuracy: 0.9708 - val_loss: 0.0940
Epoch 5/10
469/469 ━━━━━━━━━━━━━━━━━━━━ 2s 5ms/step - accuracy: 0.9835 - loss: 0.0566 - val_accuracy: 0.9748 - val_loss: 0.0848
Epoch 6/10
469/469 ━━━━━━━━━━━━━━━━━━━━ 3s 5ms/step - accuracy: 0.9864 - loss: 0.0453 - val_accuracy: 0.9703 - val_loss: 0.0970
Epoch 7/10
469/469 ━━━━━━━━━━━━━━━━━━━━ 5s 10ms/step - accuracy: 0.9889 - loss: 0.0363 - val_accuracy: 0.9780 - val_loss: 0.0770
Epoch 8/10
469/469 ━━━━━━━━━━━━━━━━━━━━ 5s 11ms/step - accuracy: 0.9908 - loss: 0.0296 - val_accuracy: 0.9787 - val_loss: 0.0709
Epoch 9/10
469/469 ━━━━━━━━━━━━━━━━━━━━ 5s 10ms/step - accuracy: 0.9939 - loss: 0.0218 - val_accuracy: 0.9776 - val_loss: 0.0744
Epoch 10/10
469/469 ━━━━━━━━━━━━━━━━━━━━ 4s 9ms/step - accuracy: 0.9944 - loss: 0.0190 - val_accuracy: 0.9775 - val_loss: 0.0795
313/313 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9718 - loss: 0.0930
Test accuracy: 0.9775000214576721