# emilwallner/Screenshot-to-code

A neural network that transforms a design mock-up into a static website.

Repository: https://github.com/emilwallner/Screenshot-to-code
Canonical: https://ross.abutalabs.com/products/emilwallner-screenshot-to-code
Language: HTML
License: NOASSERTION
License Family: other
Topics: keras, deep-learning, seq2seq, encoder-decoder, lstm, floydhub, machine-learning, cnn, cnn-keras, jupyter-notebook, jupyter
Last push: 2024-08-16T22:05:07+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3243, "days_push": 747, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 16493, forks 1543 (observed 2026-08-28T04:11:16.614609+00:00)

## What it is
A deep learning project and tutorial that trains a neural network (based on pix2code) to convert design mockup screenshots into static HTML/CSS websites. It is built in three educational iterations using Keras, CNNs, and GRU/LSTM encoder-decoder models.

## Use cases
- convert design mockups to html code
- train an ai to generate html from screenshots
- learn image-to-code deep learning techniques
- reproduce pix2code with keras
- generate bootstrap websites from design images
- study encoder-decoder models for code generation

## When to choose
- you want to learn how image-to-code models work step by step
- you need a simple educational implementation of pix2code in Keras
- you want to convert simple Bootstrap-style mockups into HTML/CSS

## When to avoid
- you need a production-ready design-to-code tool for complex layouts
- you want modern LLM-based screenshot-to-code conversion
- you cannot access GPUs or the original training dataset

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing, nlp
- domain: machine-learning, deep-learning, web-development, tutorials
- platform: python, cross-platform
- tags: image-to-code, seq2seq, encoder-decoder, pix2code, keras, html-generation, design-mockups, tutorial, gpu

## Member repositories
- emilwallner/Screenshot-to-code (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:16.614609+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:04:53.745087+00:00, confidence not recorded.
  - readme: https://github.com/emilwallner/Screenshot-to-code (fetched 2026-08-28T04:11:16.614609+00:00, sha 7b63eaa9ae2a)
- Data as of 2026-08-30T08:39:29.467469+00:00.