4/23/24, 5:10 PM Introduction to Convolutional Neural Network (CNN) using Tensorflow | by Govinda Dumane | Towards Data Science

Open in app

Search

Get unlimited access to the best of Medium for less than $1/week. Become a member

Introduction to Convolutional Neural Network

(CNN) using Tensorflow
Govinda Dumane · Follow
Published in Towards Data Science
7 min read · Mar 3, 2020

Listen Share More

Portions of this page are reproduced from work created and shared by Google and used according to terms
described in the Creative Commons 4.0 Attribution License. source

Machine Learning is being used in almost every type of industry. It is helping people
to minimize their work load as machines are capable of executing most of the
human tasks with high performance. Machines can do Predictive Analysis such as
classification & regression(predicting numerical values) and tasks like driving car
which require some kind of intelligence.

https://towardsdatascience.com/introduction-to-convolutional-neural-network-cnn-de73f69c5b83 1/17
4/23/24, 5:10 PM Introduction to Convolutional Neural Network (CNN) using Tensorflow | by Govinda Dumane | Towards Data Science

Machine Learning is part of Artificial Intelligence, in which we provide data to the

machine so that it can learn pattern from the data and it will be able to predict
solution for similar future problems. Neural Network(NN) is inspired by neural
network of the human brain. Computer Vision is a field of Artificial Intelligence
which focuses on problems related to images. CNN combined with Computer Vision
is capable of performing complex operations ranging from classifying images to
solving scientific problems of astronomy and building self-driving cars. .

Geoffrey Hinton Said, “I think people need to

understand that deep learning is making a lot of
things, behind the scenes, much better.”

So question is, How these machines learn to process image?

It uses Convolution Neural Network for doing this task effectively. Let’s understand
what is Convolutional Neural Network, aka CNN.

As we know that image is 2-dimensional array of pixels. Any image can be classified
based on it’s features. Scikit-learn algorithms like SVM, decision-tree, Random-
Forest, etc which are good at solving classification problem, fail to extract
appropriate features from the image.

That’s where Convolutional Neural Network comes into the picture. CNN is
combination of Convolutional Layers and Neural Network.

Basically any Neural Network which is used for image processing, consist of
following layers -

Input layer, Convolutional Layer, Pooling Layer, Dense Layer.

Convolution is nothing but a filter which is applied on image to extract feature from
it. We will use such different convolutions to extract different features like edges,

https://towardsdatascience.com/introduction-to-convolutional-neural-network-cnn-de73f69c5b83 2/17
4/23/24, 5:10 PM Introduction to Convolutional Neural Network (CNN) using Tensorflow | by Govinda Dumane | Towards Data Science

high-lighted patterns from the image.

How Convolution work on the image. source

What this convolution does is, it creates a filter of some size (default size is 3X3 ).
After creating filter, it starts performing element-wise multiplication starting from
top left corner of image. Element-wise multiplication means multiplying elements
with same index. These computed values are summed up to obtain a pixel value and
it is stored in the new matrix. We will use this newly generated matrix for further
processing.

Conv2D(32, 3, activation='relu')
# 32 filters or convolutions of size 3 X 3, with relu as activation
function.

The size of matrix decreases as we keep on applying filters on the obtained matrix.

https://towardsdatascience.com/introduction-to-convolutional-neural-network-cnn-de73f69c5b83 3/17
4/23/24, 5:10 PM Introduction to Convolutional Neural Network (CNN) using Tensorflow | by Govinda Dumane | Towards Data Science

Size of new matrix = (Size of old matrix — filter size)

+1
When we say that size of convolutional layer is 32. It means that 32 randomly
generated filters will be applied to the image, which outputs 32 feature matrices for
that image. These feature matrices are passed to next layer as input.

After applying convolutions, there is another concept as pooling. Pooling is used to

reduce the size of image. There are two types of pooling :

1. Max Pooling: It is nothing but selecting maximum value from the matrix of
specified size(default size is 2 X 2). This method is helpful to extract features
with high importance or which are high-lighted in the image.

High-lighted feature is part of image having high pixel values.

Max Pooling with size 2 X 2. source

MaxPooling2D() # method for Max-pooling layer

# default size of matrix is 2 X 2

2. Average Pooling: Unlike Max-pooling, Average pooling takes average of all the
pixel values of the matrix( default size is 2 X 2) of pooling layer.

https://towardsdatascience.com/introduction-to-convolutional-neural-network-cnn-de73f69c5b83 4/17
4/23/24, 5:10 PM Introduction to Convolutional Neural Network (CNN) using Tensorflow | by Govinda Dumane | Towards Data Science

Averaging Pooling. source

In above example, image size is 4 X 4 and pooling size is 2 X 2. Starting from top left
pixels. It will calculate average of 2 X 2 chunk matrices. For 1st 2 X 2 chunk, output
value is calculated as (1+3+2+9)/4 = 15 / 4 =3.75. In similar way, all other values will
be calculated.

AveragePooling2D() # method for Average pooling layer

# default size of matrix is 2 X 2

In most of the cases, max pooling is used because its performance is much better
than average pooling.

In any Neural Network, first layer will be input layer and last will be the output layer.
Input layer contains all the inputs, here images is inputs. These images are given as
input to the first convolutional layer. The output of 1st layer will be given as input to
the 2nd layer, so on & so forth. This process will continue till the last layer.

While defining Neural Network, first convolutional layer requires the shape of image
that is passed to it as input. After passing the image, through all convolutional layers
and pooling layers, output will be passed to dense layer.

We can not pass output of convolutional layer directly to the dense layer because
output of convolutional layer is in multi-dimensional shape and dense layer
requires input in single-dimensional shape i.e. 1-D array.

So we will use Flatten() method in between convolutional and dense layer. Flatten()
method converts multi-dimensional matrix to single dimensional matrix. In Neural
Network, non-linear function is used as activation function.

https://towardsdatascience.com/introduction-to-convolutional-neural-network-cnn-de73f69c5b83 5/17
4/23/24, 5:10 PM Introduction to Convolutional Neural Network (CNN) using Tensorflow | by Govinda Dumane | Towards Data Science

Graph for linear function. source

Linear function is the expression having highest exponent as 1. Graph of linear

function is straight line.

Example: Y= 2X +3.

Graph for non-linear function. source

Whereas Non-linear function is the expression having highest exponent greater

than 1. The graph of non-linear function is not straight line, rather it is curve.

Example: Y= X²

Dense Layer is simple layer of neurons in which each neuron receives input from all
the neurons of previous layer, thus called as dense. Dense Layer is used to classify
image based on output from convolutional layers.

https://towardsdatascience.com/introduction-to-convolutional-neural-network-cnn-de73f69c5b83 6/17
4/23/24, 5:10 PM Introduction to Convolutional Neural Network (CNN) using Tensorflow | by Govinda Dumane | Towards Data Science

Working of single neuron. A layer contains multiple number of such neurons. source

Each Layer in the Neural Network contains neurons, which compute the weighted
average of its input and this weighted average is passed through a non-linear
function, called as an “activation function”. Result of this activation function is
treated as output of that neuron. In similar way, the process is carried out for all
neurons of all layers.

The output of the last layer will be considered as output for that image.

#sample code for creating Convolutional Neural Network

model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=
(32, 32, 3)))
model.add(layers.MaxPooling2D())
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D())
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.Flatten())
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(10, activation='softmax'))

Here, output layer has 10 neurons with softmax activation function. Softmax
activation function is used when we have 2 or more than 2 classes. If we have total
https://towardsdatascience.com/introduction-to-convolutional-neural-network-cnn-de73f69c5b83 7/17
4/23/24, 5:10 PM Introduction to Convolutional Neural Network (CNN) using Tensorflow | by Govinda Dumane | Towards Data Science

10 classes, then the number of neurons in the output layer will be 10 . Each neuron
represents one class.

All 10 neurons will return probabilities of the input image for the respective class.
Class with highest probability will be considered as output for that image.

In same way, we will pass all the images as to convolutional layer and then to the
Neural Network, which will produce corresponding outputs for those images.

model.summary()

summary() method will display the architecture of the model.

Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d (Conv2D) (None, 30, 30, 32) 896
_________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 15, 15, 32) 0
_________________________________________________________________
conv2d_1 (Conv2D) (None, 13, 13, 64) 18496
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 6, 6, 64) 0
_________________________________________________________________
conv2d_2 (Conv2D) (None, 4, 4, 64) 36928
_________________________________________________________________
flatten (Flatten) (None, 1024) 0
_________________________________________________________________
dense (Dense) (None, 64) 65600
_________________________________________________________________
dense_1 (Dense) (None, 10) 650
=================================================================
Total params: 122,570
Trainable params: 122,570
Non-trainable params: 0
_________________________________________________________________

Parameters (params) are the weights and biases that will be used for computation in
all neurons of the CNN.

When we train any model on some number of images, it will determine some
specific values for all parameters(i.e. weights and biases), which are used to process

https://towardsdatascience.com/introduction-to-convolutional-neural-network-cnn-de73f69c5b83 8/17
4/23/24, 5:10 PM Introduction to Convolutional Neural Network (CNN) using Tensorflow | by Govinda Dumane | Towards Data Science

the image and predict the output for that image.

Convolutional Neural Networks are primarily used for binary and multi-class, multi-
label classification. There are some pre-trained models like Inception, VGG16, VGG19,
mobilenet, etc which are created by some researchers after training them on millions
of images to classify images in multiple categories. These models have learned
patterns for classifying images. If you are planning to build an image classifier, then
you can also use one of these models as base layer and add some dense layers of
your choice at the end. The number of dense layers will vary depending on your
requirement and number of output classes.

In this article, we did a walkthrough of the basics of Convolutional Neural Network

which is very important for building image-classifier model. In next article, let’s see
how to build an image classifier using pre-trained model.

If you want to check more about Convolutional Neural Network, you can refer to the
official website of Tensorflow, here.

Thanks for reading. 😊

Follow

Written by Govinda Dumane

62 Followers · Writer for Towards Data Science

Software Developer Engineer in Test. I work on Python, JS, Automation testing, Framework Development

More from Govinda Dumane and Towards Data Science

https://towardsdatascience.com/introduction-to-convolutional-neural-network-cnn-de73f69c5b83 9/17
4/23/24, 5:10 PM Introduction to Convolutional Neural Network (CNN) using Tensorflow | by Govinda Dumane | Towards Data Science

Govinda Dumane in Towards Data Science

Image Augmentation using Python, Numpy, Opencv and Skimage

Image augmentation is a strategy that enables practitioners to significantly increase the
diversity of images available for training…

6 min read · Dec 24, 2019

90 3

Tim Sumner in Towards Data Science

A New Coefficient of Correlation

https://towardsdatascience.com/introduction-to-convolutional-neural-network-cnn-de73f69c5b83 10/17
4/23/24, 5:10 PM Introduction to Convolutional Neural Network (CNN) using Tensorflow | by Govinda Dumane | Towards Data Science

What if you were told there exists a new way to measure the relationship between two variables
just like correlation except possibly…

10 min read · Mar 31, 2024

2.9K 36

Cristian Leo in Towards Data Science

The Math Behind Neural Networks

Dive into Neural Networks, the backbone of modern AI, understand its mathematics,
implement it from scratch, and explore its applications

· 28 min read · Mar 29, 2024

2.9K 20

https://towardsdatascience.com/introduction-to-convolutional-neural-network-cnn-de73f69c5b83 11/17
4/23/24, 5:10 PM Introduction to Convolutional Neural Network (CNN) using Tensorflow | by Govinda Dumane | Towards Data Science

Rami Krispin in Towards Data Science

Setting A Dockerized Python Environment — The Elegant Way

This post provides a step-by-step guide for setting up a Python dockerized development
environment with VScode and the Dev Containers…

9 min read · Apr 3, 2024

786 1

See all from Govinda Dumane

See all from Towards Data Science

Recommended from Medium

https://towardsdatascience.com/introduction-to-convolutional-neural-network-cnn-de73f69c5b83 12/17
4/23/24, 5:10 PM Introduction to Convolutional Neural Network (CNN) using Tensorflow | by Govinda Dumane | Towards Data Science

DhanushKumar

Convolution and ReLU

Convolution is a mathematical operation that combines two functions to produce a third. In the
context of signal processing, it involves…

9 min read · Nov 23, 2023

54

Lovelyn David

Understanding the Convolution Operation in CNN with an Example

https://towardsdatascience.com/introduction-to-convolutional-neural-network-cnn-de73f69c5b83 13/17
4/23/24, 5:10 PM Introduction to Convolutional Neural Network (CNN) using Tensorflow | by Govinda Dumane | Towards Data Science

The convolutional neural network gets its name from the hidden layers that perform the
convolution operation. The convolution operation is…

4 min read · Jan 18, 2024

2 1

Lists

Staff Picks
626 stories · 914 saves

Stories to Help You Level-Up at Work

19 stories · 571 saves

Self-Improvement 101
20 stories · 1651 saves

Productivity 101
20 stories · 1525 saves

Namita

Convolutional Neural Networks

Before kickstarting into CNNs we must first know about an image. What really is an RGB
image?

https://towardsdatascience.com/introduction-to-convolutional-neural-network-cnn-de73f69c5b83 14/17
4/23/24, 5:10 PM Introduction to Convolutional Neural Network (CNN) using Tensorflow | by Govinda Dumane | Towards Data Science

5 min read · Dec 11, 2023

61 1

Azeem - I

Understanding ResNet Architecture: A Deep Dive into Residual Neural

Network
Residual Network is a deep Learning model used for computer vision applications. The ResNet
(Residual Neural Network) architecture was…

6 min read · Nov 14, 2023

104

https://towardsdatascience.com/introduction-to-convolutional-neural-network-cnn-de73f69c5b83 15/17
4/23/24, 5:10 PM Introduction to Convolutional Neural Network (CNN) using Tensorflow | by Govinda Dumane | Towards Data Science

Rodrigo Silva in Towards Data Science

Exploring Feature Extraction with CNNs

Using a Convolutional Neural Network to check specialization in feature extraction

8 min read · Nov 25, 2023

368 1

Juan C Olamendy

Understanding ReLU, LeakyReLU, and PReLU: A Comprehensive Guide

Why should you care about ReLU and its variants in neural networks?
https://towardsdatascience.com/introduction-to-convolutional-neural-network-cnn-de73f69c5b83 16/17
4/23/24, 5:10 PM Introduction to Convolutional Neural Network (CNN) using Tensorflow | by Govinda Dumane | Towards Data Science

6 min read · Dec 4, 2023

104 1

See more recommendations

https://towardsdatascience.com/introduction-to-convolutional-neural-network-cnn-de73f69c5b83 17/17