Scribd
Upload
13 views3 pages

Program 5

This document outlines a TensorFlow script for building and training a convolutional neural network (CNN) to classify images of cats and dogs. It includes data loading, preprocessing, model construction, training, evaluation, and visualization of training history. The model is trained for 10 epochs and evaluates its accuracy on a test dataset.

Uploaded by

monkeymingle312
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
13 views3 pages

Program 5

This document outlines a TensorFlow script for building and training a convolutional neural network (CNN) to classify images of cats and dogs. It includes data loading, preprocessing, model construction, training, evaluation, and visualization of training history. The model is trained for 10 epochs and evaluates its accuracy on a test dataset.

Uploaded by

monkeymingle312
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

import tensorflow as tf

import tensorflow_datasets as tfds

from [Link] import Sequential

from [Link] import Conv2D, MaxPooling2D, Flatten, Dense, Dropout

import [Link] as plt

# Load dataset

dataset_name = 'cats_vs_dogs'

(data_train, data_test), dataset_info = [Link](

dataset_name,

split=['train[:80%]', 'train[80%:]'],

as_supervised=True, # Include labels

with_info=True # Include dataset info

# Data preprocessing

IMG_SIZE = 150

def preprocess_image(image, label):

image = [Link](image, (IMG_SIZE, IMG_SIZE))

image = image / 255.0 # Normalize pixel values

return image, label

train_dataset = data_train.map(preprocess_image).shuffle(1000).batch(32).prefetch(1)

test_dataset = data_test.map(preprocess_image).batch(32).prefetch(1)

# Visualize a few samples

def plot_samples(dataset, n_samples=5):

[Link](figsize=(12, 8))

for i, (image, label) in enumerate([Link](n_samples)):

ax = [Link](1, n_samples, i + 1)
[Link]([Link]())

[Link]('Cat' if [Link]() == 0 else 'Dog')

[Link]('off')

[Link]()

plot_samples(data_train.map(preprocess_image))

# Build CNN model

model = Sequential([

Conv2D(32, (3, 3), activation='relu', input_shape=(IMG_SIZE, IMG_SIZE, 3)),

MaxPooling2D(2, 2),

Conv2D(64, (3, 3), activation='relu'),

MaxPooling2D(2, 2),

Conv2D(128, (3, 3), activation='relu'),

MaxPooling2D(2, 2),

Flatten(),

Dense(512, activation='relu'),

Dropout(0.5),

Dense(1, activation='sigmoid') # Binary classification

])

[Link](optimizer='adam',

loss='binary_crossentropy',

metrics=['accuracy'])

# Train the model

history = [Link](

train_dataset,

validation_data=test_dataset,

epochs=10

)
# Evaluate the model

loss, accuracy = [Link](test_dataset)

print(f"Test Accuracy: {accuracy:.2f}")

# Plot training history

acc = [Link]['accuracy']

val_acc = [Link]['val_accuracy']

loss = [Link]['loss']

val_loss = [Link]['val_loss']

epochs = range(len(acc))

[Link](figsize=(12, 8))

[Link](epochs, acc, 'r', label='Training Accuracy')

[Link](epochs, val_acc, 'b', label='Validation Accuracy')

[Link]('Training and Validation Accuracy')

[Link]()

[Link](figsize=(12, 8))

[Link](epochs, loss, 'r', label='Training Loss')

[Link](epochs, val_loss, 'b', label='Validation Loss')

[Link]('Training and Validation Loss')

[Link]()

[Link]()

You might also like