Convolutional Neural Networks with TensorFlow in Python

Introducing you to the fundamentals of convolutional neural networks (CNNs) and computer vision. We will learn about what makes CNNs tick, discuss some effective techniques to improve their performance, and undertake a big practical project.

with Nikola Pulev and Iskren Vankov

Course Overview

This course offers a deep dive into an advanced neural network construction – convolutional neural networks. First, we explain the concept of image kernels, and how it relates to CNNs. Then, you will get familiar with the CNN itself, its building blocks, and what makes this kind of network necessary for computer vision. You’ll apply the theoretical bit to the MNIST example using TensorFlow, and understand how to track and visualize useful metrics using TensorBoard in a dedicated practical section. Later in the course, you’ll be introduced to a handful of techniques to improve the performance of neural networks, and a huge real-world practical project for classifying fashion item pictures. Finally, we will cap it all off with an intriguing look through the history of the most influential CNN architectures.

48 High Quality Lessons

8 Practical Tasks

4 Hours of Video

Certificate of Achievement

Skills you will gain

jupytermachine learningprogrammingpythontheory

What You'll Learn

Introducing you to the workings of convolutional neural networks (CNNs) and computer vision. You will learn the basics of convolution and its role in CNNs, as well as the main structure of such networks and how to implement them in practice.

Learn the fundamentals of CNNs

Get the hang of convolution

Perform computer vision

Master working with TensorFlow and Tensorboard

Approach multilabel classification

Understand kernels

Curriculum

Introduction to the course Free

2 Lesson 10 Min

What does the course cover? Free Why CNNs? Free
Kernels Free

5 Lesson 17 Min

Introduction to image kernels Free How do image transformations work? Free Kernels as matrices Free Convolution - applying kernels Free Edge handling Free
CNN Introduction

4 Lesson 23 Min

CNNs motivation Feature maps Pooling and Stride Dimensions
Neural network techniques (revision)

3 Lesson 9 Min

Activation functions Overfitting and early stopping Optimizers
Setting up the environment

2 Lesson 2 Min

Setting up the environment - Do not skip, please! Installing the packages
CNN assembling - MNIST

5 Lesson 45 Min

Road plan A simple CNN architecture Preprocessing the data Building and training the CNN Testing the trained CNN
Tensorboard: Visualization tool for TensorFlow

3 Lesson 36 Min

Tensorboard on the MNIST example Confusion matrix and visualizing it with Tensorboard Using Tensorboard to tune hyperparameters
Common techniques for better performance of neural networks

5 Lesson 19 Min

Introduction Regularization L2 Regularization and weight decay Dropout Data augmentation
A practical project: Labelling fashion items

13 Lesson 79 Min

Introduction to the problem The objective and the images Converting images to arrays Getting started with the code concepts Primary classification task - Part 1 Primary classification task - Part 2 Primary classification task - Part 3 Trousers and Jeans - discussion of approaches Trousers and Jeans - All Trousers and Jeans - Gender + Type Trousers and Jeans - comparing the methods L2 regularization and Dropout Data augmentation - Shoes All
Understanding CNNs

1 Lesson 7 Min

Unexpected failures
Popular CNN architectures

5 Lesson 19 Min

Introduction - the ILSVRC challenge AlexNet - CNN success VGG - more layers GoogleNet - computational efficiency ResNet - revolution of depth

“This course is a fantastic training opportunity to help you gain insights into the rapidly expanding field of Deep Learning and Computer Vision through the use of Convolutional Neural Networks. By the end of this course, you will be completely equipped with all the tools you need to confidently work on CNN projects!”

Nikola Pulev

Silver medal at Physics Olympiad

Courses You May Like

61 lessons 4 hours

SQL + Tableau + Python

with Martin Ganchev

166 lessons 5 hours

Deep Learning with TensorFlow 2

with Iskren Vankov, Iliya Valchanov

72 lessons 5 hours

Machine Learning in Python

with Iliya Valchanov

64 lessons 3 hours

Linear Algebra and Feature Selection

with Aleksandar Samsiev, Ivan Manov

14 lessons 1 hours

Machine Learning with Naïve Bayes

with Hristina Hristova

70 lessons 6 hours

Machine Learning in Excel

with Ivan Kitov

15 lessons 1 hours

Machine Learning with Support Vector Machines

with Elitsa Kaloyanova

Convolutional Neural Networks with TensorFlow in Python

with Nikola Pulev and Iskren Vankov