keyboard_arrow_right 48% students got a significant career improvement
keyboard_arrow_rightGet skills to work on Object Detection right after the course
keyboard_arrow_rightAdd new projects to your Portfolio
keyboard_arrow_rightFully functional & Tested code that you can use
doneFormat:Runnable notebooks with theory & practice
doneEnvironment:GPU Server included
doneSupport:You can ask question to lector any time
doneLanguage:English
This course was designed as a next step of learning for people who already got basic knowledge from Coursera, Udemy, edX, etc and for people who want to expand their expertise in another area of Machine Learning. We are bridging the gap between theory and practical knowledge so you will be ready for real-life projects, master computer vision, and image processing and get a better job within months of the course completion.
It is created by developers for developers and provides a deep understanding of the object detection task in the computer vision field. Topics of the course will guide you through the path of developing modern object detection algorithms and models.
doneFormat:Runnable notebooks with theory & practice
doneEnvironment:GPU Server included
doneSupport:You can ask question to lector any time
doneLanguage:English
Estimated 1 month to complete
This lecture will teach you one of the classical ways of detecting objects without using neural networks and also will teach how to build an image processing pipeline for the task - Road Traffic Analytics.
Object detection can be hard if start learning it from the end. This lecture will teach make intro in detection task through simple localization models with using coordinates and masks.
YOLO - fist network that was aimed at fast inference. In this lecture we will get a deep understanding of its internals and why it was built in such a way and what problems developers tried to solve.
SSD - doing the same task as YOLO but was developed few months later by another researchers and it more robust then YoloV1. We will learn internals of this network and understand in what things it differs from YoloV1 and why.
Regional Proposal Networks - came to us from classical computer vision and was updated with convolutional networks. In this lecture we will learn the history of such networks and put our hands in internals of Faster RCNN.
Object detection evolves every day and today is a good thing to create multi-task networks and not only because then can solve few tasks in the same time, but also because they achive much higher accuracy then ever. In this lecture we take a look on the internals of curent state-of-the-art algorithm - Mask RCNN.
Once you learn how to build & train deep networks new problem arise - inference speed. In this lecture, I will cover standard ways of model optimization to decrease inference time and model size.
Find the nuclei in divergent images to advance medical discovery in Kaggle "Data Science Bowl"
Computer Science & Mathematical departments, Taras Shevchenko National University Machine Learning & Computer Vision Expert
Entrepreneur and Software Engineer with 15+ years of experience. Specialist in HL+HA and BigData Systems. Was working with Top10 IT product companies. The last 3 years mostly engaged in ML projects. Currently developing a Real-Time gaming recommendation engine heavily based on Computer Vision.
Senior Computer Vision Engineer
Outstanding course! The course is completely worth it. The instructor crystal clear communicates the concepts and it's explicit that he understands them very well. Lot's of deep explanation with a code. The approach he uses is not the same as in other courses, there is no videos but written theory with code that helps much better to illustrate and understand. Andrey also continuously updates materials while any questions arise. This is an advanced course for those who want better understand the task.
Software developer
The course is just amazing. Learned a lot of new things and time invested is totally worth it. Looking forward to more courses from you. Thanks a lot
Data Science Team Lead
This course gives a solid hands-on practical experience on the state of the models like YOLO, SSD, R-CNN. It's a good course with a deep explanation so you don't need to use the git repository and analyze the code. You need to have some Python knowledge and basic NN and CNN background and you will be just fine. Overall, this course is much better than the same ones on Coursera or Udemy
Marketing Manager
I have been looking for a Computer Vision Engineer to join my project but many of the candidates didn't have the required skills. That's how I discovered this course. It helped junior level developers to progress further in their careers. Key takeaways from the course: The lectures guide you through all the necessary topics required to handle the tools used in the lessons; Exceptional guidance is provided to understand the concepts better with many practical materials; Chance to train neural nets from the very scratch; Distinguish the level of complexity of vision algorithms as well as understand the limitations of this field. Andrey, thank you for the amazing course!
ml engineer
The course is a really big deal! Lectures are well structured and have a lot of author's tips from his practical experience. But the best feature of the course is simple and easy to read implementation of algorithms which is the only way to understand the details of the algorithms.
Founder at Data Science UA Conference
Some of our team is using this course to advance their knowledge about Object Detection in deep learning. The course fills in many of the holes in the field. Content is structured neatly, lectures are comprehensive but easy to understand. This is a practical course with a focus on coding and deals with topics that are not easily found around. Absolutely worth it, great course with an experienced instructor.
$100
Simple practical examples to give you a good understanding of how all this NN/AI things really work
This is a common technique in quantized and inference optimized models.
Learn how to match and translate points in space using SVD
Learn how to find homography transformation between two images