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

By Abubakar Abid, Ali Abdalla, Ali Abid, Dawood Khan, Abdulrahman Alfozan, James Y. Zou. 2019

349 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Information Systems and Management, ML Systems & Hardware, Human-Computer Interaction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems and Management

Jimmy J. Lin

In ML Systems & Hardware

In Human-Computer Interaction

Yacine Jernite

Citations in the corpus

Persistent Anti-Muslim Bias in Large Language Models (2021, methodology): “We created a visual interface using the Gradio library [1], and used the model to generate captions for stock photos.”
Spacerini: Plug-and-play Search Engines with Pyserini and Hugging Face (2023, background): “Similarly to the authors of Gradio [1], a Python package for fast development of Machine Learning demos, we believe that the accessibility of data and model analysis tools is crucial to building both the understanding of and the trust in the underlying resources.”
The ROOTS Search Tool: Data Transparency for LLMs (2023, methodology): “The ROOTS Search Tool user interface is built with Gra-dio (Abid et al., 2019) and served via Hugging Face Spaces.”
LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models (2024, neutral): “L LAMA B OARD is a unified user interface based on Gradio (Abid et al., 2019) that allows users to customize the fine-tuning of LLMs without writing any code.”
DeepPurpose: a deep learning library for drug–target interaction prediction (2020, methodology): “We leverage Gradio (Abid et al., 2019) to create a web interface programmatically.”
Deep learning interpretation of echocardiograms (2019, methodology): “26 For example, in the frames in Figure 2 with pacemaker lead, when we manually mask the lead in the frame, EchoNet changs its prediction to no pacemaker.”
Humans or LLMs as the Judge? A Study on Judgement Bias (2024, methodology): “A screenshot of the user interface built upon gradio (Abid et al., 2019) for human judges is shown in Appendix H.”