Deep Learning Practical Project
I want to classify pictures of pizza and spaghetti! This is a deep learning practical project course that follows the A to Z of a practical project to classify images using CNN, one of the deep learning algorithms.
This course is prepared for Intermediate Learners.
What you will learn!
Understanding the Deep Learning Development Process
Understanding CNN components and model principles
Understanding OpenCV to improve the performance of CNN models
Deep learning utilization ability through CNN model practice
It automatically classifies images?
Deep Learning CNN Algorithm Project with My Own Hands!
Deep learning image classification model
If you want to make it yourself!
Do you remember the Go match between AlphaGo and Lee Sedol ? It was an event that showed the world how far artificial intelligence (AI) technology had advanced. Many media outlets were vying to release articles related to AI. In particular, machine learning/deep learning also received attention. At the time, there was a huge craze in Korea. Related books were on the bestseller list in bookstores, and everyone was knocking on the doors of academies to learn languages like Python or TensorFlow.
But as time went by, the enthusiasm gradually began to die down. Everyone said they were learning it, but no one around me was learning deep learning. What could be the problem? It’s probably because it’s too difficult. No matter how easy the words are, they’re technical terms, so they’re hard to understand.
So, we at Masocampus will help you learn about CNN, one of the essential parts of deep learning, and help you immerse yourself in deep learning by carrying out an image classification project .
In this deep learning practical project course,
We cover the entire process from the concept of CNN to actual implementation so that anyone can learn deep learning easily and without burden. We will create an image classification project using CNN, an image recognition AI model among the important core models of deep learning, and easily distinguish various image files that are difficult to distinguish due to similar appearances, such as dogs and cats, using the deep learning CNN algorithm.
If you want to easily distinguish between dogs and cats, pizza and spaghetti , try conquering CNN, the core deep learning algorithm!
Deep Learning, so that you can use it properly
We will provide you with a solid foundation.
Deep learning brings overwhelming productivity improvements regardless of the field!
This is a process to completely grasp the concepts in order to “properly” utilize deep learning.
Recommended for these people ✅
- Practitioners who want to use image classification in their work
- People who want to build a career in the IT industry (starting a business/changing jobs/joining a company)
- Managers and practitioners who want to introduce AI into their business
- Those who want to learn the core techniques of deep learning CNN
You can acquire the following capabilities 👍
- Understanding the Deep Learning Development Process
- Understand the principles of CNN components and models
- Understanding OpenCV to Improve CNN Model Performance
- Deep learning utilization ability through CNN model practice
Unique features of this course!
Thoroughly in 3 steps.
Through this lecture, you will understand the working principles of the currently hottest deep learning CNN algorithm and be able to actually implement a deep learning model through practice.
Step 1. Understand CNN concept and operation process
We will delve into the principles of each, from what CNN is, which shows excellent performance in image classification among deep learning algorithms, to data preparation using the lickr API, data preprocessing, data augmentation using OpenCV to increase accuracy, and the NN model operation process!
Convert image files to Numpy formatStep 2. Practice the Deep Learning CNN Modeling Process
A representative deep learning image classification algorithm, CNN! You can design a CNN algorithm model that can classify images much more precisely and accurately than DNN and apply it directly to real-world situations.
CNN model diagramStep 3. Use my CNN model anytime, anywhere with Flask and Ngrok
Using Flask, a micro web framework, I designed a CNN model myself, configured a Flask server, and uploaded it to a webpage. Using Ngrok, a tunnel program that allows external access to the local area, I was able to access the webpage I created from anywhere, not just my computer.
Predicting models with photos I tookStep 4. Turning insights discovered in the digital world into reality
You can become a deep learning expert who can design and train a model using CNN, predict what images are posted on a website, and discover various insights through this.
Building a website with Flask serverQ&A 💬
Q. Is prior knowledge of Python programming required?
This lecture and subsequent deep learning lectures at Maso Campus require basic Python skills.
For those who are not familiar with Python, we recommend taking Maso Campus' 'Introduction to Python Data Analysis' and 'Practical Python Data Analysis' courses first.
Q. Are there any requirements or conditions for taking the course?
Since this is a hands-on lecture, it would be a good idea to prepare a dual monitor or extra device that can separate the lecture screen and the hands-on screen. Also, since the hands-on training will be conducted based on Windows OS, we recommend taking the lecture in a Windows environment.
Q. I heard that deep learning requires a high-spec PC. Do I need a high-spec PC for practical training?
Although it is recommended to run it in a high-spec environment, this lecture will be conducted in a virtual environment using Anaconda and Jupyter Notebook. Therefore, if you have a general business PC, you will have no difficulty taking the course.
📢 Please check before taking the class!
- As this is a practice-oriented lecture, it would be a good idea to prepare a dual monitor or an extra device that can separate the lecture video and practice windows.
- Since the practical training will be conducted on Windows, we recommend taking the course in a Windows environment.
- Lecture notes and practice files can be downloaded from the section "Textbook Download Center."
Recommended for
these people!
Who is this course right for?
Practitioners who want to try using image classification for their work
Anyone who wants to build a career in the IT industry, such as starting a business, changing jobs, or joining a company
Managers and practitioners who want to introduce artificial intelligence into their business
Anyone who wants to start by learning the core techniques of CNN to build deep learning capabilities.
Need to know before starting?
This course requires basic Python skills.
I recommend that you take Maso Campus' [Introduction to Python] and [Python Practice] courses first.
5,233
Students
531
Reviews
59
Answers
4.7
Rating
75
Courses
"어제보다 성장하겠습니다. 그리고, 어제보다 성장하려는 사람을 돕겠습니다."
마소캠퍼스의 진심과 소망을 담은 Actionable Content로,
2013년부터 온오프라인으로 함께해 온 누적 강의 1억시간!
이 소중한 경험과 시간은 언제나 마소캠퍼스와 수강생 모두의 성장의 원천입니다.
마소캠퍼스 팀은 우리의 모두의 성장을 위해 두 가지 원칙을 반드시 지킵니다.
1. 배우면 반드시 쓸 수 있는 Actionable Content
2. 참여자의 시간과 수고를 존중하는 Time-Saving Curriculum
마소캠퍼스의 Actionable and Time-Saving Curriculum으로 성장의 길을 함께 걸어나가길 기원합니다.
Curriculum
All
23 lectures ∙ (2hr 37min)
Course Materials: