https://github.com/vinothpandian/akin-generator

UI wireframe generator that uses a SAGAN model to generate a UI wireframe for a given UI design pattern
https://github.com/vinothpandian/akin-generator

deep-learning gan generative-adversarial-network tensorflow ui-generation wireframe-generation

Last synced: 20 days ago
JSON representation

UI wireframe generator that uses a SAGAN model to generate a UI wireframe for a given UI design pattern

• Host: GitHub
• URL: https://github.com/vinothpandian/akin-generator
• Owner: vinothpandian
• License: mit
• Created: 2021-01-04T08:36:26.000Z (almost 4 years ago)
• Default Branch: main
• Last Pushed: 2024-02-25T17:17:50.000Z (10 months ago)
• Last Synced: 2024-04-14T13:01:33.097Z (9 months ago)
• Topics: deep-learning, gan, generative-adversarial-network, tensorflow, ui-generation, wireframe-generation
• Language: Python
• Homepage:
• Size: 617 KB
• Stars: 7
• Watchers: 3
• Forks: 2
• Open Issues: 7
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
Akin: Generating UI Wireframes From UI Design Patterns Using Deep Learning



  

  

    

  

  

    

  

  


  

    

  

  

    

  

  


  


  




> Akin is a UI wireframe generator that allows designers to chose a UI design pattern and provides them with multiple UI wireframes for a given UI design pattern. Akin uses a fine-tuned Self-Attention Generative Adversarial Network trained with 500 UI wireframes of 5 android UI design patterns

---

## Dataset

Akin uses a manually annotated subset of RICO dataset

- [Dataset with annotations and semantic images](https://blackbox-toolkit.s3.us-east-2.amazonaws.com/datasets/Akin_SAGAN_500.tar.gz)

---

## Setup and usage

Akin uses Python 3.7 and Tensorflow 2.1.

To install and retrain Akin, follow the steps below

- Download and extract the dataset to the `data/train` directory

  - [Dataset with annotations and semantic images](https://blackbox-toolkit.s3.us-east-2.amazonaws.com/datasets/Akin_SAGAN_500.tar.gz)

- Download the following files to the `models/` directory

  - [Akin trained checkpoint](https://blackbox-toolkit.s3.us-east-2.amazonaws.com/models/akin_checkpoints.tar.gz)

- Install dependencies

  ```sh

  pip install -r requirements.txt

  ```

- To train run

  ```sh

  python main.py --train

  ```

---

## Authors

👤 **Nishit Gajjar**

- Github: [@nishit](https://github.com/nishit727)

- LinkedIn: [@nishit](https://www.linkedin.com/in/nishit-gajjar-6354a172/)

👤 **Vinoth Pandian**

- Website: [vinoth.info](https://vinoth.info)

- Github: [@vinothpandian](https://github.com/vinothpandian)

- LinkedIn: [@vinothpandian](https://linkedin.com/in/vinothpandian)

---

## Thanks to

- [Leafinity](https://github.com/leafinity): Code based on their implementation of [SAGAN](https://github.com/leafinity/SAGAN-tensorflow2.0)