tonybeltramelli/pix2code
pix2code: Generating Code from a Graphical User Interface Screenshot
Uses a CNN-RNN encoder-decoder architecture trained end-to-end to synthesize platform-specific code (iOS, Android, web) from UI screenshots, achieving 77% token-level accuracy. The model generates an intermediate domain-specific language (.gui format) that compilers then transpile to native markup (Storyboard, Android XML, HTML/CSS). Training leverages memory-efficient generators and supports beam search decoding for improved output quality beyond greedy inference.
12,051 stars. No commits in the last 6 months.
Stars
12,051
Forks
1,439
Language
Python
License
Apache-2.0
Category
Last pushed
May 29, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/tonybeltramelli/pix2code"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
emilwallner/Screenshot-to-code
A neural network that transforms a design mock-up into a static website.
bobbens/sketch_simplification
Models and code related to sketch simplification of rough sketches.
ashnkumar/sketch-code
Keras model to generate HTML code from hand-drawn website mockups. Implements an image...
MiteshPuthran/Image-Caption-Generator
The LSTM model generates captions for the input images after extracting features from...
jchenghu/ExpansionNet_v2
Implementation code of the work "Exploiting Multiple Sequence Lengths in Fast End to End...