none53/Screenshot-to-code

A detailed tutorial covering the code in this repository: Turning design mockups into code with deep learning.

The neural network is built in three iterations. Starting with a Hello World version, followed by the main neural network layers, and ending by training it to generalize.

The models are based on Tony Beltramelli's pix2code, and inspired by Airbnb's sketching interfaces, and Harvard's im2markup.

Note: only the Bootstrap version can generalize on new design mock-ups. It uses 16 domain-specific tokens which are translated into HTML/CSS. This version can be trained on a few GPUs. The raw HTML version has potential to generalize, but is still unproven and requires a few hundred GPUs to train.

A quick overview of the process:

1) Give a design image to the trained neural network

2) The neural network converts the image into HTML markup

3) Rendered output

Installation

FloydHub

Click this button to open a Workspace on FloydHub where you will find the same environment and dataset used for the Bootstrap version. You can also find the trained models for testing.

pip install floyd-cli
floyd login
git clone https://github.com/emilwallner/Screenshot-to-code-in-Keras
cd Screenshot-to-code-in-Keras/floydhub 
floyd init projectname
floyd run --gpu --env tensorflow-1.4 --data emilwallner/datasets/imagetocode/2:data --data emilwallner/datasets/html_models/1:weights --mode jupyter

Local

pip install keras tensorflow pillow h5py jupyter

git clone https://github.com/emilwallner/Screenshot-to-code-in-Keras
cd Screenshot-to-code-in-Keras/local
jupyter notebook

Go do the desired notebook, files that end with '.ipynb'. To run the model, go to the menu then click on Cell > Run all

The final version, the Bootstrap version, is prepared with a small set to test run the model. If you want to try it with all the data, you need to download the data here: https://www.floydhub.com/emilwallner/datasets/imagetocode, and specify the correct dir_name.

Folder structure

  |-floydhub                               #Folder to run the project on Floyhub
  |  |-Bootstrap                           #The Bootstrap version
  |  |  |-compiler                         #A compiler to turn the tokens to HTML/CSS (by pix2code)
  |  |-Hello_world                         #The Hello World version
  |  |-HTML                                #The HTML version
  |  |  |-resources									
  |  |  |  |-Resources_for_index_file      #CSS and images to test index.html file
  |  |  |  |-html                          #HTML files to train it on
  |  |  |  |-images                        #Screenshots for training
  |-local                                  #Local setup
  |  |-Bootstrap                           #The Bootstrap version
  |  |  |-compiler                         #A compiler to turn the tokens to HTML/CSS (by pix2code)
  |  |  |-resources											
  |  |  |  |-eval_light                    #10 test images and markup
  |  |-Hello_world                         #The Hello World version
  |  |-HTML                                #The HTML version
  |  |  |-Resources_for_index_file         #CSS,images and scripts to test index.html file
  |  |  |-html                             #HTML files to train it on
  |  |  |-images                           #Screenshots for training
  |-readme_images                          #Images for the readme page

Hello World

HTML

Bootstrap

Model weights

Acknowledgments

Thanks to IBM for donating computing power through their PowerAI platform
The code is largely influenced by Tony Beltramelli's pix2code paper. Code Paper
The structure and some of the functions are from Jason Brownlee's excellent tutorial

none53 / Screenshot-to-code