An interactive visualization application designed to help non-experts learn about Recurrent Neural Networks (RNNs).
For a live demo of this App, visit: https://damien0x0023.github.io/rnnExplainer/. Please note that try this demo with a screen which is larger than 8 inches and has a minimum resolution of 1280x720. I will appreciate if you can answer some questions for me after the tour.
Clone or download this repository:
git clone [email protected]:damien0x0023/rnnExplainer.git
# use degit if you don't want to download commit histories
degit damien0x0023/rnnExplainer
Install the dependencies:
npm install
or
yarn
Then run RNN Explainer:
npm run dev
or
yarn dev
Navigate to localhost:5000. You should see the Explainer running in your broswer.
To see how train to train the CNN, visit the directory ./tiny-vgg/. To see how to train RNN , visit the directory ./imdb/.
This version is modified from CNN Explainer by Poloclub. CNN Explainer was created by Jay Wang, Robert Turko, Omar Shaikh, Haekyu Park, Nilaksh Das, Fred Hohman, Minsuk Kahng, and Polo Chau, which was the result of a research collaboration between Georgia Tech and Oregon State. For more information, check out their manuscript:
CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization. Wang, Zijie J., Robert Turko, Omar Shaikh, Haekyu Park, Nilaksh Das, Fred Hohman, Minsuk Kahng, and Duen Horng Chau. arXiv preprint 2020. arXiv:2004.15004.
The software is available under the MIT License.
I am full of ears if you have any questions, comments or suggestions. Feel free to open an issue or contac me.