Experiment - 4

Performing LetNet

import tensorflow as tf
from tensorflow.keras import datasets, layers, models
from tensorflow.keras.utils import to_categorical

# Load and preprocess the MNIST dataset

(train_images, train_labels), (test_images, test_labels) =
datasets.mnist.load_data()

# Normalize pixel values to be between 0 and 1

train_images, test_images = train_images / 255.0, test_images /
255.0

# Reshape the images to (28, 28, 1)

train_images = train_images.reshape(train_images.shape[0], 28,
28, 1)
test_images = test_images.reshape(test_images.shape[0], 28, 28,
1)

# Convert class vectors to one-hot encoded labels

train_labels = to_categorical(train_labels, 10)
test_labels = to_categorical(test_labels, 10)
# Define the LeNet model
def build_lenet(input_shape, num_classes):
model = models.Sequential()

model.add(layers.Conv2D(6, (5, 5), activation='relu',

input_shape=input_shape))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(16, (5, 5), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Flatten())
model.add(layers.Dense(120, activation='relu'))
model.add(layers.Dense(84, activation='relu'))
model.add(layers.Dense(num_classes, activation='softmax'))

return model

# Specify input shape and number of classes

input_shape = (28, 28, 1)
num_classes = 10

# Build the LeNet model

model = build_lenet(input_shape, num_classes)

# Compile the model

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

# Train the model

history = model.fit(train_images, train_labels, epochs=10,
validation_data=(test_images, test_labels))

# Evaluate the model

test_loss, test_acc = model.evaluate(test_images, test_labels,
verbose=2)
print(f'Test accuracy: {test_acc}')
# Save the model if needed
# model.save('lenet_mnist.h5')

Output:-
import tensorflow as tf
import matplotlib.pyplot as plt

# Load CIFAR-10 dataset

(x_train, y_train), (x_test, y_test) =
tf.keras.datasets.cifar10.load_data()

# Define class names (for CIFAR-10)

class_names = [
'airplane', 'automobile', 'bird', 'cat', 'deer',
'dog', 'frog', 'horse', 'ship', 'truck'
]

# Choose an image to visualize (change the index as needed)

image_index = 1

# Display the image

plt.figure()
plt.imshow(x_train[image_index])
plt.colorbar()
plt.grid(False)
plt.title(f'Label: {class_names[y_train[image_index][0]]}')
plt.show()

Label:-
import tensorflow as tf
import matplotlib.pyplot as plt

# Load CIFAR-10 dataset

(x_train, y_train), (x_test, y_test) =
tf.keras.datasets.cifar10.load_data()

# Define class names (for CIFAR-10)

class_names = [
'airplane', 'automobile', 'bird', 'cat', 'deer',
'dog', 'frog', 'horse', 'ship', 'truck'
]

# Choose an image to visualize (change the index as needed)

image_index = 0

# Display the image with improved interpolation

plt.figure()
plt.imshow(x_train[image_index], interpolation='nearest')
plt.colorbar()
plt.grid(False)
plt.title(f'Label: {class_names[y_train[image_index][0]]}')
plt.show()

Label:-
import tensorflow as tf
import matplotlib.pyplot as plt

# Load CIFAR-10 dataset

(x_train, y_train), (x_test, y_test) =
tf.keras.datasets.cifar10.load_data()

# Define class names (for CIFAR-10)

class_names = [
'airplane', 'automobile', 'bird', 'cat', 'deer',
'dog', 'frog', 'horse', 'ship', 'truck'
]

# Choose an image to visualize (change the index as needed)

image_index = 234

# Set a larger figure size for improved clarity

plt.figure(figsize=(5, 5))
plt.imshow(x_train[image_index])
plt.colorbar()
plt.grid(False)
plt.title(f'Label: {class_names[y_train[image_index][0]]}')
plt.show()

Label:-
import tensorflow as tf
import matplotlib.pyplot as plt

# Load CIFAR-10 dataset

(x_train, y_train), (x_test, y_test) =
tf.keras.datasets.cifar10.load_data()

# Define class names (for CIFAR-10)

class_names = [
'airplane', 'automobile', 'bird', 'cat', 'deer',
'dog', 'frog', 'horse', 'ship', 'truck'
]

# Choose an image to visualize (change the index as needed)

image_index = 990

# Set a larger figure size for improved clarity

plt.figure(figsize=(5, 5))
plt.imshow(x_train[image_index])
plt.grid(False)
plt.title(f'Class: {class_names[y_train[image_index][0]]}')
plt.axis('off') # Turn off axis labels
plt.show()

Label:-
import tensorflow as tf
from tensorflow.keras import layers, models
from tensorflow.keras.datasets import cifar10
from tensorflow.keras.utils import to_categorical

# Load CIFAR-10 dataset

(x_train, y_train), (x_test, y_test) = cifar10.load_data()

# Normalize pixel values to be between 0 and 1

x_train, x_test = x_train / 255.0, x_test / 255.0

# Convert class vectors to one-hot encoded labels

y_train = to_categorical(y_train, 10)
y_test = to_categorical(y_test, 10)

# Define the LeNet-5 model

model = models.Sequential()
model.add(layers.Conv2D(6, (5, 5), activation='relu',
input_shape=(32, 32, 3)))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(16, (5, 5), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Flatten())
model.add(layers.Dense(120, activation='relu'))
model.add(layers.Dense(84, activation='relu'))
model.add(layers.Dense(10, activation='softmax'))

# Compile the model

model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
# Train the model
model.fit(x_train, y_train, epochs=10, validation_data=(x_test,
y_test))

# Evaluate the model

test_loss, test_acc = model.evaluate(x_test, y_test, verbose=2)
print(f'Test accuracy: {test_acc}')

Output:-

import tensorflow as tf
from tensorflow.keras import layers, models
from tensorflow.keras.datasets import mnist
from tensorflow.keras.utils import to_categorical
import numpy as np

# Load MNIST dataset

(x_train, y_train), (x_test, y_test) = mnist.load_data()
# Normalize pixel values to be between 0 and 1
x_train, x_test = x_train / 255.0, x_test / 255.0

# Resize the images to 32x32

x_train_resized = []
x_test_resized = []

for img in x_train:

x_train_resized.append(tf.image.resize(tf.expand_dims(img,
axis=-1), (32, 32)).numpy())

for img in x_test:

x_test_resized.append(tf.image.resize(tf.expand_dims(img,
axis=-1), (32, 32)).numpy())

x_train = np.array(x_train_resized)
x_test = np.array(x_test_resized)

# Convert class vectors to one-hot encoded labels

y_train = to_categorical(y_train, 10)
y_test = to_categorical(y_test, 10)

# Define the LeNet-5 model

model = models.Sequential()
model.add(layers.Conv2D(6, (5, 5), activation='relu',
input_shape=(32, 32, 1)))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(16, (5, 5), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Flatten())
model.add(layers.Dense(120, activation='relu'))
model.add(layers.Dense(84, activation='relu'))
model.add(layers.Dense(10, activation='softmax'))
# Compile the model
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])

# Train the model

model.fit(x_train, y_train, epochs=2, batch_size=128,
validation_data=(x_test, y_test))

# Evaluate the model

test_loss, test_acc = model.evaluate(x_test, y_test, verbose=2)
print(f'Test accuracy: {test_acc}')

Output:-