23/02/2024, 15:46 EXP6_DOGS&CATS.

ipynb - Colaboratory

import os
import numpy as np
import tensorflow as tf
from tensorflow.keras.preprocessing.image import ImageDataGenerator, load_img, img_to_array
import matplotlib.pyplot as plt

#Mount google drive

from google.colab import drive

#Define the path to the directories containing train and test images
train_dir = '/content/drive/MyDrive/CAT-DOG/training set'
test_dir = '/content/drive/MyDrive/CAT-DOG/testing set'

path ='/content/drive/MyDrive/CAT-DOG/testing set'

classes =os.listdir(path)
classes

['dog testing set', 'cat testing set']

#PARAMETERS
batch_size =32
img_height = 150
img_width = 150
epochs = 10

#Preprocess images and setup the data augmentation

train_datagen = ImageDataGenerator(
rescale=1./255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True
)

test_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_directory(
train_dir,
target_size=(img_height, img_width),
batch_size=batch_size,
class_mode='binary'
)

Found 1403 images belonging to 2 classes.

validation_generator = test_datagen.flow_from_directory(
test_dir,
target_size=(img_height, img_width),
batch_size=batch_size,
class_mode='binary'
)

Found 609 images belonging to 2 classes.

# Display 10 images from training dataset

x_train, y_train = train_generator.next()
plt.figure(figsize=(10, 10))
for i in range(10):
plt.subplot(5, 5, i+1)
plt.imshow(x_train[i])
plt.axis('off')
plt.show()

https://colab.research.google.com/drive/1bPIWADb7bFmScoCKArfMgW9R4xsmHIUp#scrollTo=Labn3TiDXsx5&printMode=true 1/4
23/02/2024, 15:46 EXP6_DOGS&CATS.ipynb - Colaboratory

# Display 10 images from validation dataset

x_val, y_val = validation_generator.next()
plt.figure(figsize=(10, 10))
for i in range(10):
plt.subplot(5, 5, i+1)
plt.imshow(x_val[i])
plt.axis('off')
plt.show()

import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense

# Define the CNN model

model = Sequential([
Conv2D(32, (3, 3), activation='relu', input_shape=(150, 150, 3)),
MaxPooling2D(2, 2),
Conv2D(64, (3, 3), activation='relu'),
MaxPooling2D(2, 2),
Conv2D(128, (3, 3), activation='relu'),
MaxPooling2D(2, 2),
Conv2D(128, (3, 3), activation='relu'),
MaxPooling2D(2, 2),
Flatten(),
Dense(512, activation='relu'),
Dense(1, activation='sigmoid')
])

# Display model summary

model.summary()

Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d (Conv2D) (None, 148, 148, 32) 896

max_pooling2d (MaxPooling2 (None, 74, 74, 32) 0

D)

https://colab.research.google.com/drive/1bPIWADb7bFmScoCKArfMgW9R4xsmHIUp#scrollTo=Labn3TiDXsx5&printMode=true 2/4
23/02/2024, 15:46 EXP6_DOGS&CATS.ipynb - Colaboratory
conv2d_1 (Conv2D) (None, 72, 72, 64) 18496

max_pooling2d_1 (MaxPoolin (None, 36, 36, 64) 0

g2D)

conv2d_2 (Conv2D) (None, 34, 34, 128) 73856

max_pooling2d_2 (MaxPoolin (None, 17, 17, 128) 0

g2D)

conv2d_3 (Conv2D) (None, 15, 15, 128) 147584

max_pooling2d_3 (MaxPoolin (None, 7, 7, 128) 0

g2D)

flatten (Flatten) (None, 6272) 0

dense (Dense) (None, 512) 3211776

dense_1 (Dense) (None, 1) 513

=================================================================
Total params: 3453121 (13.17 MB)
Trainable params: 3453121 (13.17 MB)
Non-trainable params: 0 (0.00 Byte)
_________________________________________________________________

# Compile the model

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

# Train the model

history = model.fit(
train_generator,
steps_per_epoch=train_generator.samples // batch_size,
epochs=epochs,
validation_data=validation_generator,
validation_steps=validation_generator.samples // batch_size
)

output Epoch
43/43
1/10
[==============================] - 112s 3s/step - loss: 0.6930 - accuracy: 0.5179 - val_loss: 0.6931 - val_accuracy: 0.4984
Epoch 2/10
43/43 [==============================] - 79s 2s/step - loss: 0.6830 - accuracy: 0.5580 - val_loss: 0.7022 - val_accuracy: 0.4984
Epoch 3/10
43/43 [==============================] - 79s 2s/step - loss: 0.6772 - accuracy: 0.5573 - val_loss: 0.6636 - val_accuracy: 0.5724
Epoch 4/10
43/43 [==============================] - 78s 2s/step - loss: 0.6740 - accuracy: 0.5901 - val_loss: 0.6794 - val_accuracy: 0.5641
Epoch 5/10
43/43 [==============================] - 80s 2s/step - loss: 0.6476 - accuracy: 0.6265 - val_loss: 0.6578 - val_accuracy: 0.6447
Epoch 6/10
43/43 [==============================] - 81s 2s/step - loss: 0.6036 - accuracy: 0.6623 - val_loss: 0.6285 - val_accuracy: 0.6645
Epoch 7/10
43/43 [==============================] - 79s 2s/step - loss: 0.5894 - accuracy: 0.6951 - val_loss: 0.6599 - val_accuracy: 0.6513
Epoch 8/10
43/43 [==============================] - 81s 2s/step - loss: 0.6137 - accuracy: 0.6426 - val_loss: 0.6246 - val_accuracy: 0.7023
Epoch 9/10
43/43 [==============================] - 78s 2s/step - loss: 0.5756 - accuracy: 0.6973 - val_loss: 0.6031 - val_accuracy: 0.6793
Epoch 10/10
43/43 [==============================] - 80s 2s/step - loss: 0.5396 - accuracy: 0.7177 - val_loss: 0.6751 - val_accuracy: 0.6727

# Plot training and validation accuracy

plt.plot(history.history['accuracy'], label='Train Accuracy')
plt.plot(history.history['val_accuracy'], label='Validation Accuracy')
plt.xlabel('Epoch')
plt.ylabel('Accuracy')
plt.legend()
plt.title('Training and Validation Accuracy')
plt.show()

https://colab.research.google.com/drive/1bPIWADb7bFmScoCKArfMgW9R4xsmHIUp#scrollTo=Labn3TiDXsx5&printMode=true 3/4
23/02/2024, 15:46 EXP6_DOGS&CATS.ipynb - Colaboratory

# Print train and test accuracy

train_loss, train_accuracy = model.evaluate(train_generator)
test_loss, test_accuracy = model.evaluate(validation_generator)
print(f"Train Accuracy: {train_accuracy*100}")
print(f"Test Accuracy: {test_accuracy*100}")

44/44 [==============================] - 29s 665ms/step - loss: 0.5486 - accuracy: 0.7149

20/20 [==============================] - 11s 532ms/step - loss: 0.6766 - accuracy: 0.6716
Train Accuracy: 71.48966789245605
Test Accuracy: 67.15927720069885

https://colab.research.google.com/drive/1bPIWADb7bFmScoCKArfMgW9R4xsmHIUp#scrollTo=Labn3TiDXsx5&printMode=true 4/4