- Demo
- Overview
- Directory Tree
- How to Run
- Bug / Feature Request
- Contribution
- Technologies Used
- Contributor
- Credit
It's a web application that has been desinged to train Rock Paper Scissor Model in the browser in real time.
First Model is loaded from google api store and then it is being retrained by user where data is provided via webcam.
├── css
| ├── index.css
├── js
| ├── webcam.js
| ├── index.js
| ├── rps-dataset.js
├── retrain.html
a) Clone this project
git clone https://github.com/pandeynandancse/rock_paper_scissor_in_browser.git
b) Go to chrome extension and add an extension named as Web Server for Chrome "200 OK"
c) Go to search bar and search for chrome://apps and open 200 OK
d) Now 200 OK will be opened and click on choose folder and then open "rock_paper_scissor_in_browser" folder
e) A link i.e. http://127.0.0.1:8887 will be apppeared and open this link in browser.
f) Now you are done. Train your model is browser for each category and then start prediction .
If you find a bug (the website couldn't handle the query and / or gave undesired results), kindly open an issue here by including your search query and the expected result.
If you'd like to request a new function, feel free to do so by opening an issue here. Please include sample queries and their corresponding results.
If you'd like to do some contribution, feel free to do so by opening a pull request here. Please include sample queries and their corresponding results.
Nandan Pandey |
Thanks to coursera and Laurence Moroney, AI Lead at google brain, with the help of whose this project is successfully made. Sole purpose of this project was to understand using Tensoflow js for in-browser training and prediction.