Skip to content

maksymbuleshnyi/Yoga_classification

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 

Repository files navigation

ML Bootcamp Competition 2023 for Ukrainians

About the competition (taken from Kaggle)

Yoga has gained popularity in the past couple of decades and because of its success in making people physically and mentally fit, it has become widely popular all over the world. Especially in the last 2 years after the pandemic hit the world, people have been spending most of their time in their homes which opens up more suitable conditions and possibilities of practicing yoga.

However, it is very important to stretch the body correctly in every asana as each yoga pose targets a specific muscle of your body and the problem with yoga is that, just like any other exercise, it is of utmost importance to practice it correctly as any incorrect posture during a yoga session can be unproductive and possibly detrimental.

Human pose estimation is a well-known problem in computer vision to locate joint positions. The application of pose estimation for yoga is challenging as it involves a complex configuration of postures. Furthermore, some state-of-the-art methods fail to perform well when the asana involves horizontal body posture or when both the legs overlap each other or any similar complex pose.

In this competition, we formulate the pose estimation as a classification task and you will have to classify different yoga asanas into different classes. You will be responsible for creating algorithms capable of performing a precise classification by aiming for higher Mean F1 scores. The dataset has pictures of different yoga poses and the class to which it belongs. There are a total of 6 classes based on the posture of the person performing the asana. Evaluation of your algorithms would be based on the Mean F1 score.

Results

Approach which I used here gave 0.9 score on new data.

Link to competition:

https://www.kaggle.com/competitions/ukraine-ml-bootcamp-2023

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors