autoencoder.py

#!/usr/bin/env python
# coding: utf-8

# In[1]:


# Step 1: Import Libraries
import numpy as np
import matplotlib.pyplot as plt
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, UpSampling2D
from tensorflow.keras.datasets import mnist
from sklearn.model_selection import train_test_split

# Step 2: Load and Preprocess the Data
# Load MNIST dataset (you can replace this with your dataset)
(x_train, _), (x_test, _) = mnist.load_data()

# Normalize and reshape the data
x_train = x_train.astype("float32") / 255.
x_test = x_test.astype("float32") / 255.
x_train = np.expand_dims(x_train, axis=-1)
x_test = np.expand_dims(x_test, axis=-1)

# Split into training and validation sets
x_train, x_val = train_test_split(x_train, test_size=0.2, random_state=42)

# Step 3: Define the Autoencoder Architecture
input_img = Input(shape=(28, 28, 1))

# Encoder
x = Conv2D(32, (3, 3), activation='relu', padding='same')(input_img)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(64, (3, 3), activation='relu', padding='same')(x)
encoded = MaxPooling2D((2, 2), padding='same')(x)

# Decoder
x = Conv2D(64, (3, 3), activation='relu', padding='same')(encoded)
x = UpSampling2D((2, 2))(x)
x = Conv2D(32, (3, 3), activation='relu', padding='same')(x)
x = UpSampling2D((2, 2))(x)
decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(x)

# Compile the model
autoencoder = Model(input_img, decoded)
autoencoder.compile(optimizer='adam', loss='binary_crossentropy')

# Step 4: Train the Model
history = autoencoder.fit(
    x_train, x_train,
    epochs=20,
    batch_size=128,
    shuffle=True,
    validation_data=(x_val, x_val)
)

# Step 5: Evaluate the Model
# Predict on the test set
decoded_imgs = autoencoder.predict(x_test)

# Step 6: Visualize the Results
n = 10  # number of images to display
plt.figure(figsize=(20, 4))
for i in range(n):
    # Display original
    ax = plt.subplot(2, n, i + 1)
    plt.imshow(x_test[i].reshape(28, 28), cmap='gray')
    plt.axis('off')

    # Display reconstruction
    ax = plt.subplot(2, n, i + 1 + n)
    plt.imshow(decoded_imgs[i].reshape(28, 28), cmap='gray')
    plt.axis('off')
plt.show()


# In[ ]: