Data Augmentation using tf. image

Introduction

Hey there! Data augmentation is a really cool technique to easily increase the diversity of your training set. This is done by applying several random but realistic transformations to the data such as image rotation. In this article, we will be discussing how to perform Data Augmentation using tf. image.

With that said, Let’s Get Started

Setup

Let’s start by importing some basic libraries that we’ll need:

import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf
import tensorflow_datasets as tfds
from tensorflow.keras import layers

Downloading the dataset

• I will be using the tf_flowers dataset for this demonstration. You can download the dataset using Tensorflow Datasets.

Use pip install tensorflow datasets to download it.

(train_ds, val_ds, test_ds), metadata = tfds.load(
'tf_flowers',
split=['train[:80%]', 'train[80%:90%]', 'train[90%:]'],
with_info=True,
as_supervised=True,
)

Fetch an image to work with

get_label_name = metadata.features['label'].int2str
image, label = next(iter(train_ds))
_ = plt.imshow(image)
_ = plt.title(get_label_name(label))

Let’s use the following function to visualize and compare the original and augmented images side-by-side.

def visualize(original, augmented):
fig = plt.figure()
plt.subplot(1,2,1)
plt.title('Original image')
plt.imshow(original)
plt.subplot(1,2,2)
plt.title('Augmented image')
plt.imshow(augmented)

Now Let’s get into the Data Augmentation part

Flipping an Image

flipped = tf.image.flip_left_right(image)
visualize(image, flipped)

Grayscale the image

grayscaled = tf.image.rgb_to_grayscale(image)
visualize(image, tf.squeeze(grayscaled))
_ = plt.colorbar()

Saturate the image

saturated = tf.image.adjust_saturation(image, 3)
visualize(image, saturated)

Change image brightness

bright = tf.image.adjust_brightness(image, 0.4)
visualize(image, bright)

Center crop the image

cropped = tf.image.central_crop(image, central_fraction=0.5)
visualize(image,cropped)

Rotate the image

rotated = tf.image.rot90(image)
visualize(image, rotated)

Conclusion

Hope you had fun working with Data Augmentation! Do check out my other articles where I cover topics such as deep learning and other trending technologies.

Thanks for stopping by! Happy Learning!

You can check out my Linkedin at https://www.linkedin.com/in/fabchris10/