BEST

A Complete Guide to Deep Learning CNN - TensorFlow Keras Version

Name: A Complete Guide to Deep Learning CNN - TensorFlow Keras Version
Price: 110000 KRW

From core theories of Deep Learning and CNN to implementation methods of various CNN models, and practical Deep Learning development know-how through real-world problems, If you want to become a Deep Learning CNN technology expert, join us in this lecture :)

(5.0) 116 reviews

2,081 students

dooleyz3525

Deep Learning(DL)

CNN

Tensorflow

Keras

Kaggle

This course is prepared for Basic Learners.

What you will learn!

Core technological components of deep learning and CNNs
Important foundational frameworks comprising TensorFlow and Keras
Tuning Know-How to Improve the Performance of CNN Classification Models
Implementing Image Classification Using CNNs
Various image augmentation techniques and methods to improve model performance using them.
Detailed mechanisms of Keras ImageDataGenerator and Sequence
Image Data Preprocessing Techniques for Deep Learning CNNs
Key CNN models such as AlexNet, VGGNet, Inception, and ResNet.
Applied cutting-edge models such as Xception and EfficientNet.
Understanding and Applying Fine-Tuning of Pretrained Models
Ways to Improve Model Performance Using Various Learning Rate Scheduler Techniques
Practical Deep Learning Development Methods: Image Preprocessing, Data Processing, Model Creation, Optimal Performance Improvement, Performance Evaluation, etc.

Why I created this course 😚

The fastest-growing field of deep learning, CNN

Among the fields of deep learning utilization, the computer vision field based on deep learning CNN is the one that is growing the most rapidly and also changing the fastest. Therefore, in order to grow as an expert in the field of deep learning-based computer vision, it has become essential to have practical implementation skills and core competencies for CNN. To this end, we have released the course ' Deep Learning CNN Complete Guide - Fundamental Edition' . And we plan to release ' Deep Learning CNN Complete Guide - Advance Edition' with more advanced topics in the future.

What you will learn in this lecture

This time, the 'Deep Learning CNN Complete Guide - Fundamental' edition provides in-depth theory and practice of the core technology elements of deep learning and CNN, as well as various implementation techniques for building CNN image classification models and model performance optimization methods. In addition, by following many practical examples, you will be able to acquire image preprocessing, data loading, understanding the tf.keras framework, the internal architecture of the latest CNN model, and model performance tuning methods that can be used in real-world situations, and will help you grow into a deep learning CNN technology expert.

Deep Learning CNN Lecture, Ends with This Lecture.

Through 130 lectures and 30 hours of lectures, we cover in depth everything you need to understand CNN.
Check out some of the content and lecture materials below.

권 철민, 딥러닝 CNN 완벽 가이드

Check out the lecture materials in advance 🙂

Features of this course

1. In-depth theory and practice on the core technology elements that make up deep learning and CNN.

We will install the core fundamental knowledge of deep learning and CNN in your head through in-depth theory and practice.

2. Understanding the core framework that constitutes Tensorflow.Keras

We will help you implement more flexible and scalable powerful Keras-based CNN applications through detailed explanations and hands-on practice of the core framework that makes up Tensorflow.Keras.

3. From image preprocessing to optimal CNN model performance tuning!
Maximize your practical skills by learning the AZ of implementing image classification models through various practical examples.

In order to grow into a deep learning-based computer vision expert, you must also have basic technology for image processing. We will explain in detail the image processing-based technology for implementing deep learning image discrimination models, such as image preprocessing methods, image arrangement and characteristics, image library utilization, and augmentation techniques using dedicated tools such as Albumentations.

You will learn the ability to freely implement CNN image classification models through various data sets and difficult practical problems, as well as optimal performance tuning techniques for image classification models using the latest models such as Augmentation, Learning Rate Optimization, and EfficientNet .

4. We provide detailed explanations of the core CNN models that have become an important foundation for the development of modern CNNs at the source code level.

In order to use CNN for applications that extend beyond image classification models, it is important to understand how modern CNN models have evolved and what their core technologies are. To this end , we will explain in detail the architecture and characteristics of key CNN models such as AlexNet, VGGNet, GoogLeNet (Inception), and ResNet, as well as the implementation of these models at the source code level.

Guide to the Practice Environment

The practice environment is performed using the notebook kernel provided by Kaggle. After signing up for Kaggle, you can use the Jupyter Notebook environment similar to Colab by selecting the Code menu.

Kaggle Notebook kernel provides GPU P-100 VM for free. It also has a beautiful UI environment and can be easily linked with various data of Kaggle, so you can practice very conveniently. The practice code is written based on tf.keras of Tensorflow 2.4. For more detailed description of the practice environment, please refer to the introduction video of the practice environment in Session 0.

Lecture materials and practice code can be downloaded from 'Section 0: Lecture Introduction' and 'Download Lecture Materials and Practice Code' in Introduction to Practice Environment.

Because I know how valuable your efforts are.

You can't become an expert in any field without effort. No, if you become an expert without effort, you are not an expert. Because I know that you want to become an expert in the field of deep learning, and I know the value of the effort you put into it, I have put my heart and soul into creating a complete guide to deep learning CNN so that even a little time you invest in studying deep learning will not be wasted.

This course will serve as a valuable stepping stone for you to grow into a deep learning expert.

A lecture that will be helpful if you learn it in advance ✨

Kwon Chul-min, a knowledge sharer, lecture series on 'Machine Learning'

1 Complete Guide to Python Machine Learning

People met by Inflearn

Check out Kwon Chul-min's interview! | Go see

Recommended for
these people!

Who is this course right for?

For those looking to significantly enhance their basic competencies in deep learning and CNNs
For those who need a solid understanding of CNNs
For those who want to use deep learning image classification models in the field of computer vision
Those preparing for Kaggle or Dacon image classification competitions.
Anyone interested in other deep learning studies

Need to know before starting?

Basic proficiency in Python and a foundational understanding of Numpy and Pandas are required.
You should have a basic understanding of machine learning. (e.g., overfitting or why you need training/validation/test datasets)

Hello
This is dooleyz3525

25,089

Students

1,184

Reviews

3,919

Answers

4.9

Rating

Courses

(전) 엔코아 컨설팅

(전) 한국 오라클

AI 프리랜서 컨설턴트

파이썬 머신러닝 완벽 가이드 저자

Curriculum

All

135 lectures ∙ (31hr 39min)

Course Materials:

Lecture resources

Section 1. Course Introduction and Setup

3 lectures ∙ (18min)

Section 2. Deep Learning Basics - Overview and Gradient Descent

13 lectures ∙ (3hr 11min)

Section 3. Understanding Deep Learning - Error Backpropagation, Activation Function, Loss Function, Optimizer

11 lectures ∙ (2hr 53min)

17. Understanding Deep Neural Networks and Backpropagation Overview
18:27
18. Understanding Backpropagation - The Chain Rule of Differentiation
23:31
19. Deep Neural Network applying chained function composition
06:00
20. Gradient Application Mechanism of Backpropagation - 01
15:10
21. Gradient Application Mechanism of Error Backpropagation (Backpropagation) - 02
10:13
22. Understanding Activation Function
20:24
23. Reviewing Deep Learning Model Learning Mechanism in Tensorflow Playground
10:02
24. Understanding Loss Functions and Cross Entropy Details - 01
16:40
25. Understanding Loss Functions and Cross Entropy Details - 02
16:34
26. Understanding Optimizers - Momentum, AdaGrad
21:01
27. Understanding Optimizers - RMSProp, Adam
15:17

Section 4. Keras Framework

15 lectures ∙ (3hr 18min)

Section 5. Understanding CNN

12 lectures ∙ (2hr 40min)

Section 6. Implementing CNN Models and Applying Basic Performance Improvement Techniques

13 lectures ∙ (2hr 49min)

Section 7. Understanding Data Augmentation - Using Keras ImageDataGenerator

7 lectures ∙ (1hr 58min)

Section 8. Using Pre-trained CNN Models and Understanding the Keras Generator Mechanism

10 lectures ∙ (2hr 30min)

Section 9. Augmentation using Albumentation and Keras Sequence

10 lectures ∙ (2hr 33min)

Section 10. Dissecting Advanced CNN Models - AlexNet, VGGNet, GoogLeNet

12 lectures ∙ (2hr 28min)

Section 11. Breaking Down Advanced CNN Models - ResNet Details and EfficientNet Overview

8 lectures ∙ (1hr 54min)

Section 12. Fine-tuning of Pre-trained Models and Application of Various Learning Rate Schedulers

7 lectures ∙ (1hr 30min)

Section 13. Comprehensive Practice 1 - 120 Dog Breed ID Model Optimization

8 lectures ∙ (2hr 11min)

Section 14. Comprehensive Practice 2 - Kaggle Plant Pathology (Plant leaf disease diagnosis) Competition

6 lectures ∙ (1hr 22min)

Published: 04/13/2021

Last updated: 05/13/2025

Reviews

All

116 reviews

5.0

116 reviews

잉여잉여킹
Reviews 1
∙
Average Rating 5.0
10/23/2023
5
49% enrolled
안녕하세요, 현재 인공지능을 전공으로 공부중인 학생입니다. 거짓말 안치고 대학교 수준 커리큘럼대로 진행을 해주시면서 강의해주시고.... 난이도는 대학교수준의 90%정도(?)로 체감됩니다.석사 수준의 깊이는 아니지만, 입문용~중상급까지는 무조건 이 강의로 모두 커버가 가능합니다. 그리고 난이도와는 별개로, 학교수업은 PPT만 읽다 끝나는데, 이 강의는 코드한줄한줄 따라할수있어서 너무 좋았습니다. 가끔 어느영역에서는 정말 '어?! 이정도까지 깊게들어간다고!?' 싶은 수준으로 설명해주시기도하셔서 놀랐습니다. (교수님이랑 짚는 포인트와 설명이 거의 똑같이 말씀하셔서 깜짝놀랐어요) 아쉬운점은 현대 머신러닝의 정점인 트랜스포머, 어탠션같은 부분들은 아직 다루지않는다는점입니다. 만약에 이 강의까지 나와버리면 권철민 선생님은거의 국내 머신러닝 사교육 본좌 등극하시게 될것같습니다. 인프런에서 내돈내산 강의중에 최고의만족도입니다.
poptato
Reviews 1
∙
Average Rating 5.0
07/26/2021
5
75% enrolled
지금 반정도 봤는데.. advanced 강의는 언제나오나요. 현기증 나니까 저 100% 듣기 전에 만들어주세요. 빨리 듣고 싶네요.
BJ Kim
Reviews 2
∙
Average Rating 5.0
04/19/2021
5
17% enrolled
다보진 못했지만 먼저 남기는 수강후기.. [장점] 1. 시작할 때 선수 지식에 대해 잘 정리해주심 2. 강의 이름은 CNN이지만 CNN에 한정되지 않고 딥러닝 기본기(SGD, Backprop등..)를 자세하게 알려주시기 때문에 뒤에 좀 어려운 응용 나와도 이해가능 3. 이미지 전처리도 자세하기 때문에 비전쪽 기본기없으신 분들도 도전가능(권철민 강사님의 비전쪽 강의 듣고오는것도 추천) 4. 단순 CNN 이미지 분류만 있지않고 최근 CNN이 어떻게 발전하고 있는지 또한 상세 설명 5. 강의자료에 이해하기 쉽게 그림이 많음 [아쉬운 점] 1. tf기반 강의이지만, torch도...ㅎㅎ [총평] 5점. 이미지 분야 딥러닝입문하시는분들은 무조건 들으시면 좋고 그냥 딥러닝에 입문하시는 분들도 딥러닝 기본기가 자세히 나와있기 때문에 들어두시면 좋습니다. CNN자체가 솔직히 요즘 이미지에만 쓰이지 않고 NLP나 예측모델링에도 쓰이고 있기 때문에 CNN깊게 이해하시고 활용하기에 좋습니다.
율언니
Reviews 6
∙
Average Rating 5.0
04/26/2021
5
50% enrolled
플젝 수행하면서 딥러닝 대강 안다고 생각했는데, 이강의로 그동안 주먹구구로 해왔구나를 느끼고 있습니다. 하루중에 틈날때마다 계속 듣고 있습니다. 도움 많이 되고 있고, 혹 나중에 심화과정 나오면 그 강의도 듣고 싶습니다.
백승환
Reviews 2
∙
Average Rating 5.0
04/30/2021
5
96% enrolled
CNN분야가 딥러닝을 조금이라도 해봤다고 하면 비교적 처음에 접하는 분야라 안다고 생각하지만, 생각보다 원리를 모르고 가져다 써서 유연한 대처가 어렵네요. 회사에서 필요할 때마다 github를 찾아 헤매든지 원리를 잘 모르고 그때그때 필요한 기능들을 급하게 조합해서 만들곤 합니다. 다른 업무와 병행하면서 하다 보니 tensorflow2.4, keras, kaggle 언젠가는 공부해야지 하면서 미루다가 지난번 강의하신 강의를 수강하면서 진행한 과제에 object detection을 이용해서 로봇 움직임에 성공적으로 적용하며 회사에서는 전문가(?)로 인정을 받았던 기억때문에 CNN도 다시 한번 정리할 겸, 깊이 파보고자 수강중에 있습니다. 수업 시간이 적지 않은데, 나쁘진 않은 것이 소스코드를 상세히 설명해주셔서 전체적으로 스윽~ 훑어보고 따로 표기했다가 나중에 그때그때 필요한 부분만 좀 더 세밀하게 들어봐도 좋을것 같습니다. --------------------------------------------------------- 일전에 남겼던 후기에 추가해서 남깁니다. 회사에서 다른 업무를 수행했다가 다시 컴퓨터 비전 부서가 만들어지면서 다시 한번 복기 하는 차원에서 처음부터 완강 했습니다. 다시 들어보니 이전에 급하게 넘어갔던 부분들이 좀 더 이해의 폭이 넓어지는군요. 역시 한번 듣고 끝날 강의가 아닙니다. 다시 한번 강추합니다.

dooleyz3525's other courses

Check out other courses by the instructor!

[개정판] 파이썬 머신러닝 완벽 가이드

권 철민

$99,000.00

Basic / Python, 머신러닝, 통계

4.9

(402)

A Complete Guide to Deep Learning CNN - TensorFlow Keras Version

This course is prepared for Basic Learners.

What you will learn!

Why I created this course 😚

The fastest-growing field of deep learning, CNN

What you will learn in this lecture

Deep Learning CNN Lecture, Ends with This Lecture.

Features of this course

Guide to the Practice Environment

Because I know how valuable your efforts are.

Kwon Chul-min, a knowledge sharer, lecture series on 'Machine Learning'

People met by Inflearn

Recommended for these people!

HelloThis is dooleyz3525

Curriculum

Reviews

dooleyz3525's other courses

Similar courses

Recommended for
these people!

Hello
This is dooleyz3525