Scribd
Upload
10 views

AIprog12

This document outlines the steps to download and train a neural network model on a Cat vs Dog dataset using TensorFlow. It includes commands for downloading datasets, setting up the runtime environment, and building a simple model with specified parameters. The training results show varying accuracy and loss metrics over ten epochs.

Uploaded by

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

AIprog12

This document outlines the steps to download and train a neural network model on a Cat vs Dog dataset using TensorFlow. It includes commands for downloading datasets, setting up the runtime environment, and building a simple model with specified parameters. The training results show varying accuracy and loss metrics over ten epochs.

Uploaded by

priya
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

!wget https://download.microsoft.

com/download/3/e/1/3e1c3f21-ecdb-4869-
8368-6deba77b919f/kagglecatsanddogs_5340.zip

!unzip kagglecatsanddogs_53

https://zenodo.org/records/5226945

!wget https://zenodo.org/records/5226945/files/cats_dogs_light.zip?
download=1

!unzip cats_dogs_light.zip?download=1

Step1: Set: Runtime -> Change Runtime type -> GPU

Step2: install Cat vs Dog dataset

!wget --no-check-certificate \
https://storage.googleapis.com/mledu-datasets/cats_and_dogs_filtered.zip \
-O /tmp/cats_and_dogs_filtered.zip

!unzip /tmp/cats_and_dogs_filtered.zip

Setp3: Code

import tensorflow as tf
from tensorflow.keras.layers import Conv2D, Flatten, Dense
from tensorflow.keras.models import Sequential
from tensorflow.keras.preprocessing.image import ImageDataGenerator

# Define constants
batch_size = 32
img_height = 150
img_width = 150
epochs = 10
# Create image data generators
train_datagen = ImageDataGenerator(rescale=1./255)
validation_datagen = ImageDataGenerator(rescale=1./255)
train_generator = train_datagen.flow_from_directory(
'/content/cats_and_dogs_filtered/train',
target_size=(img_height, img_width),
batch_size=batch_size,
class_mode='binary'
)
validation_generator = validation_datagen.flow_from_directory(
'/content/cats_and_dogs_filtered/validation',
target_size=(img_height, img_width),
batch_size=batch_size,
class_mode='binary'
)
# Build a simple neural network model
model = Sequential([
Flatten(input_shape=(img_height, img_width, 3)),
Dense(128, activation='relu'),
Dense(1, activation='sigmoid')
])
# Compile the model
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
11
# 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:
Found 2000 images belonging to 2 classes.
Found 1000 images belonging to 2 classes.
Epoch 1/10
62/62 ━━━━━━━━━━━━━━━━━━━━ 6s 78ms/step - accuracy: 0.5477 - loss: 13.6614 -
val_accuracy: 0.5746 - val_loss: 1.8352
Epoch 2/10
62/62 ━━━━━━━━━━━━━━━━━━━━ 1s 23ms/step - accuracy: 0.4375 - loss: 2.2653 -
val_accuracy: 0.5706 - val_loss: 1.7689
Epoch 3/10
62/62 ━━━━━━━━━━━━━━━━━━━━ 5s 83ms/step - accuracy: 0.5540 - loss: 2.9765 -
val_accuracy: 0.5575 - val_loss: 1.2186
Epoch 4/10
62/62 ━━━━━━━━━━━━━━━━━━━━ 1s 23ms/step - accuracy: 0.5000 - loss: 1.3509 -
val_accuracy: 0.5111 - val_loss: 2.9195
Epoch 5/10
62/62 ━━━━━━━━━━━━━━━━━━━━ 5s 83ms/step - accuracy: 0.5651 - loss: 2.6707 -
val_accuracy: 0.5423 - val_loss: 3.1215
Epoch 6/10
62/62 ━━━━━━━━━━━━━━━━━━━━ 2s 27ms/step - accuracy: 0.2812 - loss: 4.3689 -
val_accuracy: 0.5716 - val_loss: 1.5851
Epoch 7/10
62/62 ━━━━━━━━━━━━━━━━━━━━ 5s 76ms/step - accuracy: 0.6277 - loss: 1.6029 -
val_accuracy: 0.5171 - val_loss: 2.4660
Epoch 8/10
62/62 ━━━━━━━━━━━━━━━━━━━━ 1s 23ms/step - accuracy: 0.6875 - loss: 1.1648 -
val_accuracy: 0.5030 - val_loss: 3.6614
Epoch 9/10
62/62 ━━━━━━━━━━━━━━━━━━━━ 4s 67ms/step - accuracy: 0.5722 - loss: 2.0467 -
val_accuracy: 0.5514 - val_loss: 1.3998
Epoch 10/10
62/62 ━━━━━━━━━━━━━━━━━━━━ 1s 24ms/step - accuracy: 0.5000 - loss: 1.2462 -
val_accuracy: 0.5212 - val_loss: 2.4486

You might also like