[Revised Edition] Deep Learning Computer Vision Complete Guide
This course will help you become a deep learning-based computer vision expert needed in the field through in-depth theoretical explanations of Object Detection and Segmentation, along with practical examples that can be immediately applied in real-world work environments.
Understanding Deep Learning-based Object Detection and Segmentation
In-depth theoretical learning of RCNN series, SSD, YOLO, RetinaNet, EfficientDet, and Mask RCNN
Learn how to use representative implementation packages for Object Detection and Segmentation such as MMDetection, Ultralytics Yolo, and AutoML EfficientDet
Performing Image/Video Object Detection/Segmentation using OpenCV and Tensorflow Hub
Learn various challenging practical examples to reach a level where you can directly apply Object Detection/Segmentation in real-world work
Acquiring diverse foundational knowledge that comprises Object Detection/Segmentation
Training Custom Datasets Using Various Implementation Packages and Creating Your Own Model
Gain hands-on experience with the advantages and disadvantages of various Object Detection/Segmentation models through practical examples
Working with major datasets like Pascal VOC and MS-COCO and converting them to TFRecord
Creating training data by applying annotations to datasets using the CVAT Tool
Lower the barrier, deepen the core! Become a deep learning CNN practical expert.
Learn Deep Learning Computer Vision with the latest revised edition.
Average rating 4.9★ chosen by 1,300+ students, Inflearn Bestseller fully renewed in 2021!
Hello, this is Chulmin Kwon. Thanks to the support of many people, I am pleased to release the revised edition of 'The Complete Guide to Deep Learning Computer Vision'. About 90% of the videos from the existing course have been newly created, and I will introduce enhanced and additional content.
Based on the feedback you've provided for the course, we have created this revised edition with a focus on the following aspects.
More detailed theoretical explanations for topics that received many student questions
Object Detection/Segmentation package-based practice with the latest/best performance Object Detection/Segmentation có hiệu suất mới nhất/tốt nhất
Reflecting the latest trends in Object Detection/Segmentation
More flexible, diverse, and scalable practice code writing + more detailed explanations
Various other additional lessons đa dạng khác
The revised course is without a doubt superior to the first edition, with more detailed content. It will guide you into the latest deep learning-based Object Detection and Segmentation domains.
Course Introduction 📝
The core of deep learning computer vision technology is rapidly shifting to Object Detection and Segmentation.
▲Intelligent video information recognition ▲AI vision inspection smart factories ▲Automated medical image diagnosis ▲Robotics ▲Autonomous vehicles, and many other fields are seeing the spread of deep learning-based Object Detection and Segmentation technologies. Accordingly, leading AI companies both domestically and internationally are sparing no investment in these fields and are seeking to secure development talent.
Two Major Trends Finally Meet: Object Detection & Segmentation
In recent years, as the fields of Object Detection and Segmentation have rapidly advanced, the demand for talent with relevant practical skills has been increasing. Nevertheless, as these are cutting-edge fields applying deep learning, there is a shortage of books, materials, and lectures for learning, making it difficult to properly train personnel.
We will guide you to become a deep learning computer vision expert.
This course consists of in-depth theoretical explanations of Object Detection and Segmentation, along with numerous practical examples that can be directly applied in the field, and will help you grow into a deep learning-based computer vision expert needed in the industry.
From easy concept explanations to in-depth theory.
We provide clear explanations of the vast Object Detection/Segmentation field, from easy concepts to in-depth theory on RCNN series, SSD, YOLO, RetinaNet, EfficientDet, Mask RCNN, and more.
You can thoroughly learn concepts with detailed lecture slides.
Maximize your practical deep learning skills through hands-on examples.
There's no better way to improve your practical skills than by coding and implementing things yourself. This course consists of many hands-on examples, which will maximize your practical ability to implement Object Detection and Segmentation.
Those who have wondered how deep learning CNN can be applied in practice
Those who want to develop deep learning-based computer vision solutions
Those who want to expand from deep learning image classification capabilities to the latest CV technologies
Graduate school applicants in AI, job seekers/career changers in deep learning-based CV field
Please check the prerequisites.
Python programming experience and basic understanding of deep learning CNN are required..
Additionally, it would be even better if you have some experience with TF.Keras or PyTorch.
Cutting-edge CV technology you won't find anywhere else, all in one place.
Hands-on practice using state-of-the-art Object Detection/Segmentation implementation packages with exceptional performance
MMDetection, Ultralytics Yolo, AutoML EfficientDet, etc.
Hands-on inference practice using versatile OpenCV DNN and Tensorflow Hub
Object Detection/Segmentation practice on various images and videos
Various real-world applications utilizing computer vision technology
Model Training Practice with Various Custom Datasets
Various custom datasets
As a deep learning computer vision expert, you should be able to train models with various custom datasets to create your own Object Detection/Segmentation models. You should also be able to improve and evaluate the performance of these models.
This course will help you develop the ability to train custom datasets using various implementation packages and create optimal inference models.
Hands-on Custom Model Training / Inference with Self-Created Training Datasets
Hands-on practice with self-created training datasets
Using the annotation tool CVAT, you will directly create a training dataset by applying bounding box annotations to regular images, and practice custom model training and inference using this created dataset.
Lab Environment 🧰
This course primarily conducts hands-on exercises based on GPU. For GPU-based exercises, the practice environment will be set up on Runpod, and for exercises unrelated to GPU, you may use the Google Colab environment.
For Runpod, approximately $10 to $20 in additional costs will be incurred for the hands-on practice. While you can proceed with the practice with $10 (though it's a bit tight ^^;;), we recommend around $20 for a more comfortable practice experience.
Please check before enrolling!
If you do not use Runpod's GPU environment, you may have difficulty following the examples. Thank you for your understanding in advance.
Practice Code and Course Materials 👨💻
Practice code can be downloaded from https://github.com/chulminkw/DLCV_New.Reviewing the practice code in advance will help you assess the prerequisite programming level needed to understand the exercises.
320-page lecture PDF textbook provided
The textbook used in the course (320 pages) can be downloaded from Lecture Section 0: Course Materials.
To learn theory, there is no better way than hands-on practice.
Don't wait until you perfectly understand deep learning theory. There is no better way to learn theory than through practice.
Once you start coding, our brains are designed to follow along to gain concrete understanding. Try implementing the various practical examples presented in the lectures together with me. As you watch the lectures and actually implement them by typing on your keyboard, the parts that felt vague and abstract will gradually become tangible.
To become an expert, sometimes (though I think it's almost always the case) you need to run before you learn to walk. This course will be your best companion in developing your career and capabilities in the field of deep learning-based computer vision.
Thank you.
― Tony Stark's words to Jarvis during the Iron Man suit test in
It's really unbelievably good.. I was so mad at Infleun while listening to Coco Pytorch in the neighborhood. I found happiness after listening to this lecture. Thank you so much.
This is a great lecture that can be applied directly to practice. If the instructor has time, I hope that a lecture on data such as voice and text based on RNN will be opened.