# pix2code: Generating Code from a Graphical User Interface Screenshot Source: [pix2code: Generating Code from a Graphical User Interface Screenshot]() Collection index: [llms.txt]() Data updated: 2025-12-14T16:48:11.320Z Authors: Tony Beltramelli Published: 2017-05-22T19:32:20.000Z ## Abstract Transforming a graphical user interface screenshot created by a designer into computer code is a typical task conducted by a developer in order to build customized software, websites, and mobile applications. In this paper, we show that deep learning methods can be leveraged to train a model end-to-end to automatically generate code from a single input image with over 77% of accuracy for three different platforms (i.e. iOS, Android and web-based technologies). ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [GUI to Code Generation on iOS UI Storyboard (test)](): GUI to Code Generation; iOS UI Storyboard (test); Error Rate: 22.73. - [GUI to Code Generation on Android UI XML (test)](): GUI to Code Generation; Android UI XML (test); Error Rate: 0.2234. - [GUI to Code Generation on web-based UI HTML/CSS (test)](): GUI to Code Generation; web-based UI HTML/CSS (test); Error Rate (%): 11.01. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()