https://github.com/vinothpandian/synz

Enhanced Synthetic Dataset for Training UI Element Detector From Lo-Fi Sketches
https://github.com/vinothpandian/synz

Last synced: 2 months ago
JSON representation

Enhanced Synthetic Dataset for Training UI Element Detector From Lo-Fi Sketches

• Host: GitHub
• URL: https://github.com/vinothpandian/synz
• Owner: vinothpandian
• License: cc-by-sa-4.0
• Created: 2020-12-31T03:32:58.000Z (about 4 years ago)
• Default Branch: master
• Last Pushed: 2022-12-08T07:51:25.000Z (about 2 years ago)
• Last Synced: 2024-04-14T13:01:39.880Z (10 months ago)
• Language: Jupyter Notebook
• Size: 48.8 KB
• Stars: 4
• Watchers: 1
• Forks: 2
• Open Issues: 11
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

README

        
SynZ: Enhanced Synthetic Dataset for Training UI Element Detector From Lo-Fi Sketches



  

  

    

  

  


  

    

  

  

    

  

  

    

  

  


  


  💾 

  

    SynZ Dataset in Kaggle

  

      

  💾 

  

    UISketch Dataset in Kaggle

  

  




---

## Script to extract SynZ annotations from RICO

- Follow the steps and run the script from the [`notebooks`](./notebooks) folder

  - Notebook [`RICO_data_extraction.ipynb`](./notebooks/01_RICO_data_extraction.ipynb) converts RICO annotations to a CSV file

  - Notebook [`RICO_to_SynZ_annotations.ipynb`](./notebooks/02_RICO_to_SynZ_annotations.ipynb) converts RICO annotations to SynZ annotations for further steps

---

## Generating SynZ sketches

To generate SynZ sketches from scratch,

- Download all the UISketch dataset to the [`data`](./data) folder

  - UISketch dataset from [kaggle](https://www.kaggle.com/vinothpandian/uisketch)

- Either run the notebooks described in previous section to generate `SynZ_ready_annotations.csv` file or download the SynZ annotations from [here](https://blackbox-toolkit.com/datasets/SynZ_ready_annotations.csv)

- Install the necessary requirements from `requirements.txt` file

  ```sh

  pip install -r requirements.txt

  ```

- Run the following command to generate SynZ dataset

  ```sh

  python generate_synz_dataset.py \

    --annotation_csv_path=./data/SynZ_ready_annotations.csv \

    --uisketch_labels_csv_path=./data/uisketch/labels.csv \

    --output_path=./data/SynZ \

    --number_of_versions=1 \

    run

  ```

---

## Downlading MetaMorph model trained weights

- Download the trained SynZ checkpoint from [here](https://blackbox-toolkit.com/models/synz_checkpoint.tar.gz) to [`models`](./models) folder

- Extract the `synz_checkpoint.tar.gz` folder to acquire the MetaMorph model's trained weights from `model_final.pth`

---

## Authors

👤 **Vinoth Pandian**

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

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

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

👤 **Sarah Suleri**

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

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