floydhub/pix2code-template

Build a neural network to code a basic a HTML and CSS website based on a picture of a design mockup.

36
/ 100
Emerging

Combines convolutional neural networks for image feature extraction with recurrent sequence-to-sequence models to generate simplified 17-token markup that translates to Bootstrap HTML/CSS. Trains on 1500+ synthetically generated website screenshots with 97% accuracy using a tweaked encoder-decoder architecture from the original pix2code paper. Provides end-to-end pipeline including image preprocessing, model training in Keras/TensorFlow, and BLEU evaluation metrics on held-out test sets.

No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 20 / 25

How are scores calculated?

Stars

63

Forks

25

Language

Jupyter Notebook

License

Category

image-captioning

Last pushed

Sep 27, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/floydhub/pix2code-template"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.