import numpy as np

import matplotlib.pyplot as plt

from tensorflow.keras.layers import Input, Dense
from tensorflow.keras.models import Model
from tensorflow.keras.datasets import mnist # Correcting the dataset name

# Load the MNIST dataset

(x_train, _), (x_test, _) = mnist.load_data()

# Preprocess the data

x_train = x_train.astype('float32') / 255.0
x_test = x_test.astype('float32') / 255.0
x_train = x_train.reshape((len(x_train), np.prod(x_train.shape[1:])))
x_test = x_test.reshape((len(x_test), np.prod(x_test.shape[1:])))

# Define the autoencoder model

input_img = Input(shape=(784,))
encoded = Dense(32, activation='relu')(input_img)
decoded = Dense(784, activation='sigmoid')(encoded)

autoencoder = Model(input_img, decoded)

autoencoder.compile(optimizer='adam', loss='binary_crossentropy')

# Train the autoencoder

autoencoder.fit(x_train, x_train, epochs=50, batch_size=256, shuffle=True,
validation_data=(x_test, x_test))

# Encode and decode the test images

encoded_imgs = autoencoder.predict(x_test)
decoded_imgs = encoded_imgs

# Visualize original and reconstructed images

n = 10 # Number of images to display
plt.figure(figsize=(20, 4))
for i in range(n):
# Original images
ax = plt.subplot(2, n, i + 1)
plt.imshow(x_test[i].reshape(28, 28))
plt.gray()
ax.get_xaxis().set_visible(False)
ax.get_yaxis().set_visible(False)

# Reconstructed images
ax = plt.subplot(2, n, i + 1 + n)
plt.imshow(decoded_imgs[i].reshape(28, 28)) # Use 'decoded_imgs'
plt.gray()
ax.get_xaxis().set_visible(False)
ax.get_yaxis().set_visible(False)

plt.show()

Epoch 1/50
235/235 [==============================] - 5s 14ms/step - loss: 0.2795 - val_loss: 0.1920
Epoch 2/50
235/235 [==============================] - 3s 13ms/step - loss: 0.1743 - val_loss: 0.1583
Epoch 3/50
235/235 [==============================] - 3s 13ms/step - loss: 0.1473 - val_loss: 0.1359
Epoch 4/50
235/235 [==============================] - 3s 15ms/step - loss: 0.1303 - val_loss: 0.1230
Epoch 5/50
235/235 [==============================] - 3s 15ms/step - loss: 0.1198 - val_loss: 0.1145
Epoch 6/50
235/235 [==============================] - 3s 12ms/step - loss: 0.1114 - val_loss: 0.1065
Epoch 7/50
235/235 [==============================] - 3s 13ms/step - loss: 0.1053 - val_loss: 0.1016
Epoch 8/50
235/235 [==============================] - 4s 16ms/step - loss: 0.1013 - val_loss: 0.0985
Epoch 9/50
235/235 [==============================] - 4s 15ms/step - loss: 0.0986 - val_loss: 0.0964
Epoch 10/50
235/235 [==============================] - 3s 13ms/step - loss: 0.0969 - val_loss: 0.0950
Epoch 11/50
235/235 [==============================] - 3s 13ms/step - loss: 0.0958 - val_loss: 0.0942
Epoch 12/50
235/235 [==============================] - 3s 14ms/step - loss: 0.0951 - val_loss: 0.0937
Epoch 13/50
235/235 [==============================] - 3s 15ms/step - loss: 0.0947 - val_loss: 0.0932
Epoch 14/50
235/235 [==============================] - 4s 17ms/step - loss: 0.0943 - val_loss: 0.0929
Epoch 15/50
235/235 [==============================] - 3s 15ms/step - loss: 0.0941 - val_loss: 0.0928
Epoch 16/50
235/235 [==============================] - 4s 15ms/step - loss: 0.0939 - val_loss: 0.0926
Epoch 17/50
235/235 [==============================] - 3s 15ms/step - loss: 0.0937 - val_loss: 0.0925
Epoch 18/50
235/235 [==============================] - 4s 15ms/step - loss: 0.0936 - val_loss: 0.0924
 Epoch 19/50
235/235 [==============================] - 3s 15ms/step - loss: 0.0935 - val_loss: 0.0923
Epoch 20/50
235/235 [==============================] - 4s 15ms/step - loss: 0.0934 - val_loss: 0.0922
Epoch 21/50
235/235 [==============================] - 3s 14ms/step - loss: 0.0934 - val_loss: 0.0922
Epoch 22/50
235/235 [==============================] - 4s 16ms/step - loss: 0.0933 - val_loss: 0.0920
Epoch 23/50
235/235 [==============================] - 5s 19ms/step - loss: 0.0932 - val_loss: 0.0920
Epoch 24/50
235/235 [==============================] - 4s 15ms/step - loss: 0.0932 - val_loss: 0.0920
Epoch 25/50
235/235 [==============================] - 4s 18ms/step - loss: 0.0932 - val_loss: 0.0919
Epoch 26/50
235/235 [==============================] - 3s 14ms/step - loss: 0.0931 - val_loss: 0.0919
Epoch 27/50
235/235 [==============================] - 4s 16ms/step - loss: 0.0931 - val_loss: 0.0919
Epoch 28/50
235/235 [==============================] - 4s 16ms/step - loss: 0.0930 - val_loss: 0.0918
Epoch 29/50
235/235 [==============================] - 3s 13ms/step - loss: 0.0930 - val_loss: 0.0918
Epoch 30/50
235/235 [==============================] - 3s 13ms/step - loss: 0.0930 - val_loss: 0.0918
Epoch 31/50
235/235 [==============================] - 3s 13ms/step - loss: 0.0929 - val_loss: 0.0918
Epoch 32/50
235/235 [==============================] - 3s 13ms/step - loss: 0.0929 - val_loss: 0.0917
Epoch 33/50
235/235 [==============================] - 3s 13ms/step - loss: 0.0929 - val_loss: 0.0917
Epoch 34/50
235/235 [==============================] - 3s 13ms/step - loss: 0.0929 - val_loss: 0.0918
Epoch 35/50
235/235 [==============================] - 3s 13ms/step - loss: 0.0928 - val_loss: 0.0917
Epoch 36/50
235/235 [==============================] - 3s 13ms/step - loss: 0.0928 - val_loss: 0.0918
Epoch 37/50
235/235 [==============================] - 3s 13ms/step - loss: 0.0928 - val_loss: 0.0917
Epoch 38/50
235/235 [==============================] - 3s 14ms/step - loss: 0.0928 - val_loss: 0.0916
Epoch 39/50
235/235 [==============================] - 4s 17ms/step - loss: 0.0928 - val_loss: 0.0917
Epoch 40/50
235/235 [==============================] - 3s 14ms/step - loss: 0.0927 - val_loss: 0.0916
Epoch 41/50
235/235 [==============================] - 3s 13ms/step - loss: 0.0927 - val_loss: 0.0916
Epoch 42/50
235/235 [==============================] - 3s 14ms/step - loss: 0.0927 - val_loss: 0.0916
Epoch 43/50
235/235 [==============================] - 3s 14ms/step - loss: 0.0927 - val_loss: 0.0916
Epoch 44/50
235/235 [==============================] - 4s 15ms/step - loss: 0.0927 - val_loss: 0.0916
Epoch 45/50
235/235 [==============================] - 4s 16ms/step - loss: 0.0927 - val_loss: 0.0916
Epoch 46/50
235/235 [==============================] - 3s 14ms/step - loss: 0.0927 - val_loss: 0.0915
Epoch 47/50
235/235 [==============================] - 3s 13ms/step - loss: 0.0926 - val_loss: 0.0916
Epoch 48/50
235/235 [==============================] - 3s 14ms/step - loss: 0.0926 - val_loss: 0.0915
Epoch 49/50
235/235 [==============================] - 3s 14ms/step - loss: 0.0926 - val_loss: 0.0915
Epoch 50/50
235/235 [==============================] - 3s 14ms/step - loss: 0.0926 - val_loss: 0.0915
313/313 [==============================] - 1s 3ms/step

Loading [MathJax]/jax/output/CommonHTML/fonts/TeX/fontdata.js