First, let us plot the actual images, that is, input images:

n = 7
plt.figure(figsize=(20, 4))
for i in range(n):
 
    ax = plt.subplot(1, 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)
plt.show() 

The plot of the actual images is as follows:

Plot the reconstructed image as follows:

n = 7
plt.figure(figsize=(20, 4))
for i in range(n):
    ax = plt.subplot(2, n, i + n + 1)
    plt.imshow(reconstructed_images[i].reshape(28, 28))
    plt.gray()
    ax.get_xaxis().set_visible(False)
    ax.get_yaxis().set_visible(False)

plt.show() 

The following shows the reconstructed images:

As you can see, the autoencoder has learned better representations of the input images and reconstructed them.