inflearn logo

License Plate Recognition Project and Deep Learning Image Recognition All-in-One with TensorFlow

This is an all-in-one course where you can learn the entire process from the basics of deep learning, TensorFlow, and computer vision to practical applications through a real-world license plate recognition project. Through various hands-on exercises, you can develop the practical skills to apply the latest deep learning models to custom datasets.

(4.8) 73 reviews

684 learners

Level Basic

Course period Unlimited

Tensorflow
Tensorflow
Deep Learning(DL)
Deep Learning(DL)
Machine Learning(ML)
Machine Learning(ML)
CNN
CNN
NLP
NLP
Tensorflow
Tensorflow
Deep Learning(DL)
Deep Learning(DL)
Machine Learning(ML)
Machine Learning(ML)
CNN
CNN
NLP
NLP

Reviews from Early Learners

Reviews from Early Learners

4.8

5.0

김한주

30% enrolled

Unlike other lectures, I liked that it didn't stop at basic concepts and toy projects, but covered the level of use in the industry.

5.0

김준표

73% enrolled

I took this course because the introduction to deep learning with TensorFlow 2.0 course was very thorough and suited me well. I'm only listening to the first half, but the explanations are good and I can leave projects, so I think it will be very helpful for my future studies and job preparation.

5.0

kream

25% enrolled

This was a lecture that really helped me a lot while I was working on the project. It was very helpful because it taught me the basics and explained how the code was done.

What you will gain after the course

  • How to conduct real-world deep learning projects beyond basic examples like MNIST and CIFAR-10

  • How to apply the latest deep learning models to a custom dataset

  • Step-by-step learning from basic deep learning/machine learning concepts to practical applications

  • Deep understanding of deep learning model architectures proposed in recent papers (EfficientNet, CenterNet, EAST, ...)

  • Principles and usage of the latest deep learning models used in various computer vision domains, such as Object Detection, Text Detection, OCR, Image Captioning, and Generative Models.

  • How to improve the performance of deep learning models

Various real-world projects and latest research paper studies will help you
become a deep learning/computer vision expert. 😀

Please check before taking the course!

해당 커리큘럼 목록

<TensorFlow Object Detection API Guide Part 1 - Object Detection by Modifying 10 Lines of Code> Section 1

  • Introduction to the Object Detection Problem Domain
  • Object Detection Metric - IoU, mAP
  • Object Detection Datasets – Pascal VOC, MS COCO, KITTI, Open Images

<TensorFlow Object Detection API Guide Part 1 - Detecting Objects by Modifying 10 Lines of Code> Section 3

  • Introduction to TensorFlow Object Detection API

<TensorFlow Object Detection API Guide Part 1 - Object Detection with 10 Lines of Code Change> Section 4

  • R-CNN(Regions with CNN)
  • Fast R-CNN
  • Faster R-CNN
  • Non-Maximum Suppression (NMS)
  • SSD(Single Shot MultiBox Detector)
  • RetinaNet
  • CenterNet

<TensorFlow Object Detection API Guide Part1 - Object Detection with 10 Lines of Code Modification> Section 5

  • Object Detection using a Pre-Trained Model

<Introduction to Deep Learning with TensorFlow 2.0Section 1

  • Artificial Intelligence, Machine Learning, Deep Learning & Supervised Learning, Unsupervised Learning, Reinforcement Learning
  • Deep Learning and TensorFlow Application Fields
  • A Brief Overview of the History of Deep Learning

<Introduction to Deep Learning with TensorFlow 2.0Section 3

  • Basic Process of Machine Learning - Defining Hypothesis, Defining Loss Function, Defining Optimization
  • Implementing Linear Regression Algorithm using TensorFlow 2.0
  • Batch Gradient Descent, Stochastic Gradient Descent, Mini-Batch Gradient Descent
  • Training Data, Validation Data, Test Data & Overfitting
  • Softmax Regression & Cross-Entropy Loss Function & One-hot Encoding & MNIST
  • TensorFlow 2.0 Keras Subclassing
  • Implementing an MNIST Digit Classifier using TensorFlow 2.0 and Softmax Regression

<Introduction to Deep Learning with TensorFlow 2.0Section 4

  • Multi-Layer Perceptron MLP
  • Implementing an MNIST Digit Classifier using TensorFlow 2.0 and ANN

<Introduction to Deep Learning with TensorFlow 2.0Section 5

  • Concept of AutoEncoder
  • MNIST Data Reconstruction Using TensorFlow 2.0 and Autoencoders

<Introduction to Deep Learning with TensorFlow 2.0Section 6

  • The Challenges of Computer Vision Problems and the Advent of the CNN-based Computer Vision Era
  • Core Concepts of Convolutional Neural Networks - Convolution, Pooling
  • Implementing CNN for MNIST Digit Classification Using TensorFlow 2.0
  • Dropout
  • Implementing CNN for CIFAR-10 Image Classification Using TensorFlow 2.0

<Introduction to Deep Learning with TensorFlow 2.0> Section 7

  • Recurrent Neural Network (RNN)
  • Vanishing Gradient Problem & LSTM & GRU
  • Concept of Embedding & Char-RNN
  • Implementing Char-RNN using TensorFlow 2.0

<Introduction to Deep Learning with TensorFlow 2.0Section 8

  • Saving and loading parameters using the tf.train.CheckpointManager API
  • Visualizing the learning process using TensorBoard

<Introduction to Deep Learning with TensorFlow 2.0Section 9

  • Introduction to various Computer Vision problem domains
  • Introduction to Various Natural Language Processing (NLP) Problem Domains

Learn how to use the latest deep learning models actually used by Naver (CRAFT) and Kakao (EAST).

An All-in-One lecture to become a deep learning computer vision expert!

  • We have combined all the essential elements you need to learn to become a deep learning computer vision expert into a single course.
  • Essential theoretical knowledge for understanding the latest deep learning models : Learn the essential theory and knowledge required step-by-step, starting from the basics of machine learning and deep learning (ANN, CNN) to the principles of the latest deep learning models (EfficientNet, CenterNet).
  • Code implementation skills using Python/TensorFlow 2.0 : Learn step-by-step implementation skills for real-world projects using Python and TensorFlow 2.0.
  • Various practical projects for applying Custom Datasets: Instead of basic examples like MNIST, we will carry out various practical projects to apply the latest deep learning models to various Custom Datasets.

Recommended for
these people

Who is this course right for?

  • Anyone who wants to seriously study deep learning/computer vision

  • Those who want to conduct practical projects using deep learning/computer vision

Need to know before starting?

  • Basic Python knowledge

Hello
This is AISchool

9,756

Learners

754

Reviews

357

Answers

4.6

Rating

32

Courses

More

Curriculum

All

126 lectures ∙ (20hr 51min)

Course Materials:

Lecture resources
Published: 
Last updated: 

Reviews

All

73 reviews

4.8

73 reviews

  • seojk1234560728님의 프로필 이미지
    seojk1234560728

    Reviews 1

    Average Rating 5.0

    5

    25% enrolled

    This was a lecture that really helped me a lot while I was working on the project. It was very helpful because it taught me the basics and explained how the code was done.

    • aischool
      Instructor

      Hello. Thank you for taking the time to take the class~!. I will try my best to create more satisfactory lectures. Have a nice day!

  • dkoh0716님의 프로필 이미지
    dkoh0716

    Reviews 1

    Average Rating 5.0

    5

    100% enrolled

    Thank you for the informative and good lecture.

    • aischool
      Instructor

      Hello. Thank you for taking the time to take the class~!. I will try my best to create more satisfactory lectures. Have a nice day!

  • whdghk8152040님의 프로필 이미지
    whdghk8152040

    Reviews 6

    Average Rating 5.0

    5

    30% enrolled

    Unlike other lectures, I liked that it didn't stop at basic concepts and toy projects, but covered the level of use in the industry.

    • aischool
      Instructor

      Hello. Thank you for taking the time to take the class~!. Thank you for the detailed course review~. I will try my best to create a more satisfactory course. Have a nice day!

  • slhyj954421님의 프로필 이미지
    slhyj954421

    Reviews 1

    Average Rating 5.0

    5

    67% enrolled

    I am planning to major in Machine Learning in graduate school, and this has been very helpful in understanding my weaknesses and practicing.

    • aischool
      Instructor

      Hello. Thank you for taking the time to take the class~!. I will try my best to create more satisfactory lectures. Have a nice day!

  • junpyokim4448님의 프로필 이미지
    junpyokim4448

    Reviews 5

    Average Rating 5.0

    5

    73% enrolled

    I took this course because the introduction to deep learning with TensorFlow 2.0 course was very thorough and suited me well. I'm only listening to the first half, but the explanations are good and I can leave projects, so I think it will be very helpful for my future studies and job preparation.

    • aischool
      Instructor

      Hello. Thank you for taking the time to take the class~!. I will try my best to create more satisfactory lectures. Have a nice day!

AISchool's other courses

Check out other courses by the instructor!

Similar courses

Explore other courses in the same field!

$110.00