ashnkumar/sketch-code
Keras model to generate HTML code from hand-drawn website mockups. Implements an image captioning architecture to drawn source images.
Supports both single-image and batch conversion pipelines, with training capabilities including data augmentation and fine-tuning on pretrained weights. Built on TensorFlow/Keras with an encoder-decoder architecture that learns to map visual elements from wireframes to semantic HTML tokens, evaluated using BLEU score metrics. Includes a 1,700-image synthetic dataset and pretrained model weights for immediate inference on sketch-like inputs.
5,157 stars. No commits in the last 6 months.
Stars
5,157
Forks
683
Language
Python
License
—
Category
Last pushed
Apr 05, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ashnkumar/sketch-code"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
tonybeltramelli/pix2code
pix2code: Generating Code from a Graphical User Interface Screenshot
bobbens/sketch_simplification
Models and code related to sketch simplification of rough sketches.
emilwallner/Screenshot-to-code
A neural network that transforms a design mock-up into a static website.
jchenghu/ExpansionNet_v2
Implementation code of the work "Exploiting Multiple Sequence Lengths in Fast End to End...
MiteshPuthran/Image-Caption-Generator
The LSTM model generates captions for the input images after extracting features from...