Convolutional Neural Networks for Image Classification

Convolutional Neural Networks for Image Classification, available at $59.99, has an average rating of 4.3, with 55 lectures, 21 quizzes, based on 90 reviews, and has 849 subscribers.

You will learn about Design deep CNNs architectures with high accuracy results Demonstrate classification in Real Time by camera Generate synthetic data to augment existing dataset Assemble own, custom dataset for Classification tasks Modify existing dataset for Classification tasks Apply preprocessing techniques for dataset before training Train deep CNNs in Keras Classify new images after training This course is ideal for individuals who are Students who want to build complete application for Image Classification with CNN or Students who want to improve their hard skills on Image Classification with CNN before their next interview for internship or dream job or Students who want to use CNN with their Own Data for Image Classification but don't know where to start or Young Researchers who study different Image Classification Algorithms and want to Train CNN with Custom Data and Compare results with other approaches or Students who know basics of Image Classification but want to know how to Train CNN with New Data or Students who study Computer Vision and want to know how to use CNN for Image Classification or Students who work on project of safety driven and want to Classify Traffic Signs with CNN or Students who develop alarm-warning system for driver and need to Classify Traffic Signs It is particularly useful for Students who want to build complete application for Image Classification with CNN or Students who want to improve their hard skills on Image Classification with CNN before their next interview for internship or dream job or Students who want to use CNN with their Own Data for Image Classification but don't know where to start or Young Researchers who study different Image Classification Algorithms and want to Train CNN with Custom Data and Compare results with other approaches or Students who know basics of Image Classification but want to know how to Train CNN with New Data or Students who study Computer Vision and want to know how to use CNN for Image Classification or Students who work on project of safety driven and want to Classify Traffic Signs with CNN or Students who develop alarm-warning system for driver and need to Classify Traffic Signs.

Enroll now: Convolutional Neural Networks for Image Classification

Summary

Title: Convolutional Neural Networks for Image Classification

Price: $59.99

Average Rating: 4.3

Number of Lectures: 55

Number of Quizzes: 21

Number of Published Lectures: 53

Number of Published Quizzes: 20

Number of Curriculum Items: 76

Number of Published Curriculum Objects: 73

Number of Practice Tests: 1

Number of Published Practice Tests: 1

Original Price: $199.99

Quality Status: approved

Status: Live

What You Will Learn

Design deep CNNs architectures with high accuracy results
Demonstrate classification in Real Time by camera
Generate synthetic data to augment existing dataset
Assemble own, custom dataset for Classification tasks
Modify existing dataset for Classification tasks
Apply preprocessing techniques for dataset before training
Train deep CNNs in Keras
Classify new images after training

Who Should Attend

Students who want to build complete application for Image Classification with CNN
Students who want to improve their hard skills on Image Classification with CNN before their next interview for internship or dream job
Students who want to use CNN with their Own Data for Image Classification but don't know where to start
Young Researchers who study different Image Classification Algorithms and want to Train CNN with Custom Data and Compare results with other approaches
Students who know basics of Image Classification but want to know how to Train CNN with New Data
Students who study Computer Vision and want to know how to use CNN for Image Classification
Students who work on project of safety driven and want to Classify Traffic Signs with CNN
Students who develop alarm-warning system for driver and need to Classify Traffic Signs

Target Audiences

Students who want to build complete application for Image Classification with CNN
Students who want to improve their hard skills on Image Classification with CNN before their next interview for internship or dream job
Students who want to use CNN with their Own Data for Image Classification but don't know where to start
Young Researchers who study different Image Classification Algorithms and want to Train CNN with Custom Data and Compare results with other approaches
Students who know basics of Image Classification but want to know how to Train CNN with New Data
Students who study Computer Vision and want to know how to use CNN for Image Classification
Students who work on project of safety driven and want to Classify Traffic Signs with CNN
Students who develop alarm-warning system for driver and need to Classify Traffic Signs

In this practical course, you’ll design, train and testyour own Convolutional Neural Network (CNN) for the tasks of Image Classification.

By the end of the course, you’ll be able to build your own applications for Image Classification.

At the beginning, you’ll implementconvolution, pooling and combination of these two operations to grayscale images by the help of different filters, pure Numpy library and ‘for’ loops. We will also implement convolution in Real Time by camera to detectobjects edges and to trackobjects movement.
After that, you’ll assemble images together, compose custom dataset for classification tasks and save created dataset into a binary file.
Next, you’ll convert existing dataset of Traffic Signs into needed format for classification tasks and saveit into a binary file.
Then, you’ll applypreprocessing techniques before training, produceand saveprocessed datasets into separate binary files.
At the next step, you’ll constructCNN models for classification tasks, selectneeded number of layers for accurate classification and adjustother parameters.
When the models are designed and datasets are ready, you’ll trainconstructed CNNs, testtrained models on completely new images, classify images in Real Time by camera and visualizetraining process of filters from randomly initialized to finally trained.
At the final step, you’ll passPractice Test according to the all learned material during the course.
As a bonus part, you’ll generateup to 1 millionadditional images and extend prepared dataset by new images via image rotation, image projection and brightness changing.

The main goal of the course is to develop and improve your hard skills in order to apply them for real problems of Image Classification based on Convolutional Neural Networks.

Every lecture of the course has SMART objectives. It means, that you can track your progress and witness practical results within the visible time frame, right after the end of the lecture.

S – specific (the lecture has specific objectives)
M – measurable (results are reasonable and can be quantified)
A – attainable (the lecture has clear steps to achieve the objectives)
R – result-oriented (results can be obtained by the end of the lecture)
T – time-oriented (results can be obtained within the visible time frame)

Course Curriculum

Chapter 1: Welcome

Lecture 1: Introduction to the course

Lecture 2: Quick Win #1: Convolution

Lecture 3: Quick Win #2: Pooling

Lecture 4: Quick Win #3: Convolution+Pooling

Lecture 5: Quick Win #4: Convolution in Real Time by camera

Lecture 6: Quick Win #5: Track movement of the object via Convolution

Lecture 7: Glossary

Lecture 8: Software Installation & Verification

Lecture 9: How to study the course?

Chapter 2: Assemble custom dataset for Image Classification

Lecture 1: Introduction & Learning objectives: Assembling dataset

Lecture 2: Toolkit to download images

Lecture 3: Download images from large and existing dataset by toolkit

Lecture 4: Activity: Download images for a given class

Lecture 5: Modify downloaded dataset to use it for Classification

Lecture 6: Download other datasets

Lecture 7: Process other datasets to use them for Classification

Lecture 8: Conclusion: key takeaways for assembling custom dataset

Chapter 3: Modify existing dataset of Traffic Signs for Classification

Lecture 1: Introduction & Learning objectives: Modifying existing dataset

Lecture 2: Download dataset of Traffic Signs

Lecture 3: Convert downloaded dataset to use it for Classification

Lecture 4: Conclusion: key takeaways for modifying existing dataset

Chapter 4: Apply preprocessing techniques for datasets before training

Lecture 1: Introduction & Learning objectives: Applying preprocessing approaches

Lecture 2: Construct set of datasets with colour images

Lecture 3: Construct set of datasets with grayscale images

Lecture 4: Conclusion: key takeaways for applying preprocessing techniques

Chapter 5: Design deep CNNs architectures for efficient Classification

Lecture 1: Introduction & Learning objectives: Designing deep architectures

Lecture 2: How many Convolutional-Pooling pairs of layers?

Lecture 3: How many Feature Maps in Convolutional layers?

Lecture 4: How many Neurons in Fully Connected layer?

Lecture 5: How much Dropout?

Lecture 6: What else?

Lecture 7: Save designed deep CNN models into binary files

Lecture 8: Conclusion: key takeaways for designing deep CNNs

Lecture 9: Heuristic approach to identify the best model

Chapter 6: Train and Test designed CNNs models

Lecture 1: Introduction & Learning objectives: Training developed deep CNNs models

Lecture 2: Overfit designed deep models with prepared datasets

Lecture 3: Train designed deep models with prepared datasets

Lecture 4: Test trained models

Lecture 5: Test Classification in Real Time by camera

Lecture 6: Combine: Detection & Classification in Real Time by camera

Lecture 7: Visualize training process of filters

Lecture 8: Conclusion: key takeaways for training designed CNNs

Chapter 7: Practice Test

Lecture 1: Review all the learned skills

Lecture 2: What is next?

Chapter 8: Generate synthetic data to augment datasets

Lecture 1: Introduction & Learning objectives: Generating additional artificial data

Lecture 2: Change brightness of images in dataset

Lecture 3: Manipulate images by geometric transformations

Lecture 4: Augment and equalize images in dataset

Lecture 5: Visualize unique examples from augmented dataset

Lecture 6: Conclusion: key takeaways for generating synthetic data

Chapter 9: How does it work?

Lecture 1: What does Confusion Matrix show?

Lecture 2: 2D Image Convolution: Numpy, Tensorflow, Keras

Chapter 10: How to move from image recognition to object detection?

Lecture 1: How to train YOLO v5 for object detection?

Instructors

Valentyn Sichkar
Computer Vision, Machine Learning, Image Processing

Rating Distribution

1 stars: 2 votes
2 stars: 4 votes
3 stars: 6 votes
4 stars: 33 votes
5 stars: 45 votes

Frequently Asked Questions

How long do I have access to the course materials?

You can view and review the lecture materials indefinitely, like an on-demand channel.

Can I take my courses with me wherever I go?

Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don’t have an internet connection, some instructors also let their students download course lectures. That’s up to the instructor though, so make sure you get on their good side!

Menu