A website that lets you dance to In My Feelings, the viral song by Drake. It uses PoseNet to compare DrAIke's and your poses and score how well you copied him.
Actually, this is really fun. You don't have be a dancer. Try it here.
As you can guess, the name “DrAIke” is the compound word of Drake and AI. DrAIke refers to both this webiste and the master dancer in this game. Your score will vary according to how well you imitate DrAike. Also, you'll be able to enjoy several exciting videos provided by PoseNet. This project utilizes TensorFlow.js, the popular deep learning framework that runs on browers, and PoseNet, the project that detects the poses through computer vision. Both are developed by Google. (I love you Google!)
This is one of our website pages. You will be shown in the pink box through webcam. PoseNet will estimate and show your poses like the one in the blue box.
Oh, let me introduce DrAIke. He's a really great dancer. His dream is beating Drake and thus becomming the best dancer in the world.
And DrAIke will show you his dancing videos depending on your score. This is only one of them. And it's Gangnam Style by Psy if you guessed right!
We began this project when we got inspired by this video of Siraj Raval, the well-known Youtuber who ambitiously educate deep learning to people. He also provided us with numerous feedbacks, leading to several critical improvements to our code. Here is his PoseNet code: https://github.com/llSourcell/InMyFeelings_Challenge
Thank you for sharing our website!
We will keep adding the documents here and improve our website.
Actually, we are highschoolers, and this is our first web project. So there can be many stupid codes. If you want to improve them, please let us know on "issues".
You can also play the demo provided by Google. Try it here!
PoseNet can be used to estimate either a single pose or multiple poses, meaning there is a version of the algorithm that can detect only one person in an image/video and one version that can detect multiple persons in an image/video.
This is a Pure Javascript implementation of PoseNet.
Refer to this blog post for a high-level description of PoseNet running on Tensorflow.js.
Credits for this code go to the Tensorflow team at Google.
And thank you, Siraj Raval! I love(?) you.