Gradio: Hassle-Free Sharing and Testing of ML Models in the Wild

TL;DR

Gradio is an open-source Python tool that simplifies sharing and testing ML models by creating easy-to-access visual interfaces, enhancing collaboration and feedback from non-technical users.

Contribution

This paper introduces Gradio, a versatile tool that enables rapid creation of shareable ML model interfaces, improving accessibility and interdisciplinary collaboration.

Findings

Facilitates easy sharing of ML models via URLs

Supports multiple interface types and frameworks

Enhances collaboration with domain experts

Abstract

Accessibility is a major challenge of machine learning (ML). Typical ML models are built by specialists and require specialized hardware/software as well as ML experience to validate. This makes it challenging for non-technical collaborators and endpoint users (e.g. physicians) to easily provide feedback on model development and to gain trust in ML. The accessibility challenge also makes collaboration more difficult and limits the ML researcher's exposure to realistic data and scenarios that occur in the wild. To improve accessibility and facilitate collaboration, we developed an open-source Python package, Gradio, which allows researchers to rapidly generate a visual interface for their ML models. Gradio makes accessing any ML model as easy as sharing a URL. Our development of Gradio is informed by interviews with a number of machine learning researchers who participate in interdisciplinary collaborations. Their feedback identified that Gradio should support a variety of interfaces and frameworks, allow for easy sharing of the interface, allow for input manipulation and interactive inference by the domain expert, as well as allow embedding the interface in iPython notebooks. We developed these features and carried out a case study to understand Gradio's usefulness and usability in the setting of a machine learning collaboration between a researcher and a cardiologist.