Gradio is a library we built to let you make UIs out of your ML models with a few lines of code. Originally a Stanford project, we allow developers to take any preexisting model they have and build UIs that can be hosted and shared with minimum effort.
Hey Makers and Hunters,
As one of the creators of the library, I'll add that we hope to solve one of the biggest problems in machine learning right now:
- ML models are often trained on *very specific datasets* and fail in embarrassing/costly ways when deployed in real-world settings where things looks different than the training data
- The worst part is that these limitations are usually not detected until the model is released, because usually the ML engineers may not realize that their model is: biased, unfair, or fragile
It takes a diverse team of users and testers to realize this. Gradio gives you the ability to instantly create a web interface around your model that you can share with a public link.
Your users or testers or collaborators can (right from their browsers, without having to install any software) try your model, understand its limitations, and point out biases in the model and data.
Congrats fellas! This is amazing stuff, any plans to make a discover feed to find interesting (open source or otherwise) models that I can just play with?
Thanks! @zuhayeer For sure, we're actually launching exactly this soon. We'll be uploading interfaces for the most popular ML models, and will accept submissions soon after that.
Report
Congrats on the launch @ali_abdalla1! Gradio looks amazing!
Replies
Gradio
Toodle
Gradio
Levels.fyi
Gradio
Gradio