Gradio: Hassle-Free Sharing and Testing of ML Models in the Wild
This tool addresses the problem of limited accessibility and collaboration in ML for researchers and non-technical users, though it is incremental as it builds on existing interface concepts.
The authors tackled the challenge of making machine learning models accessible to non-technical collaborators by developing Gradio, an open-source Python package that allows researchers to quickly create visual interfaces for their models, enabling easy sharing via URL and facilitating feedback from domain experts like physicians.
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.