An Image Based Teachable Machine
Table of Contents
The No-Code Machine Learning interface is a web-based tool that makes it fast and easy to create machine learning models without any expertise or coding accessible to everyone. Users can train a simple model with the use of images without any coding required as datasets for training. And for all of this you just need setup of a computer & webcam.
This model uses a basic frontend created by HTML, CSS and Javascript and requires the KNN Model classifier as a backend. All the images that are gathered are uploaded to the server and then further on trained by putting into a KNN Classifier. Once, the images are trained with the classifier, the newly inputted images by the webcam can be tested live by the trained model. This helps you preview the accuracy of the model in realtime and if needed, you may add more training images in the database. Once done, you can download the model using a simple download button and further integrate the model in Arduino and other uses.
This project is inspired by the Google Teachable Machine, you may check it out Here .
You may explore the working of a Convolutional Neural Network Here.
In order to use the system, there are primarily three steps involved:
- Gathering Data:
Gather and group your examples into classes, or categories, that you want the computer to learn. Upload your own image files, or capture them live with a mic or webcam. - Train The Model:
Click on- train model, KNN Classifier starts training a neural network in your browser. - Test and Download:
There you can see your model output and done.
Every program is ever evolving and, that is possible only with valuable contributions. Any contributions you make are greatly appreciated.
- Fork the Project
- Create your Feature Branch (git checkout -b functionalities/Feature)
- Commit your Changes (git commit -m 'Add a Feature')
- Push to the Branch (git push origin functionalities/Feature)
- Open a Pull Request
If you have any further ideas or comments, go ahead to the next section and feel free to connect!
