CNN Program
import tensorflow as tf
from [Link] import Sequential
from [Link] import Conv2D, MaxPooling2D, Flatten,
Dense, Dropout
from [Link] import ImageDataGenerator
import numpy as np
import [Link] as plt
import cv2
# Load and preprocess the CIFAR-10 dataset, selecting only dog and cat
classes
(x_train, y_train), (x_test, y_test) =
[Link].cifar10.load_data()
class_names = ['airplane', 'automobile', 'bird', 'cat', 'deer',
'dog', 'frog', 'horse', 'ship', 'truck']
index_dog = class_names.index('dog')
index_cat = class_names.index('cat')
# Fix: Flatten y_train before creating the boolean index
y_train = y_train.flatten()
y_test = y_test.flatten()
x_train = x_train[(y_train == index_dog) | (y_train == index_cat)]
y_train = y_train[(y_train == index_dog) | (y_train == index_cat)]
x_test = x_test[(y_test == index_dog) | (y_test == index_cat)]
y_test = y_test[(y_test == index_dog) | (y_test == index_cat)]
# Normalize pixel values to the range [0, 1]
x_train = x_train / 255.0
x_test = x_test / 255.0
# Build the CNN model
model = Sequential([
Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32, 3)),
MaxPooling2D((2, 2)),
Conv2D(64, (3, 3), activation='relu'),
MaxPooling2D((2, 2)),
Flatten(),
Dense(64, activation='relu'),
Dense(1, activation='sigmoid')
])
[Link](optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy'])
# Train the model
history = [Link](x_train, y_train, epochs=10,
validation_data=(x_test, y_test))
# Evaluate the model
test_loss, test_acc = [Link](x_test, y_test, verbose=2)
print('\nTest accuracy:', test_acc)
# Function to predict the class of a single image
def predict_image(image_path):
img = [Link](image_path)
img = [Link](img, (32, 32))
img = img / 255.0
img = np.expand_dims(img, axis=0)
prediction = [Link](img)
if prediction[0][0] > 0.5:
print('Predicted: Dog')
else:
print('Predicted: Cat')
# Example usage:
image_path = '/content/[Link]'
predict_image(image_path)
Output:
