Skip to content

The second part of my Bachelor's Degree project: "Translating" flowcharts into their respective pseudocode by using the method of Image Captioning. This involves a Convolutional Neural Network and a Recurrent Neural Network.

License

Notifications You must be signed in to change notification settings

JohannaMichael/flowchart-image-captioning

Repository files navigation

About Flowchart Image Captioning

This project aims to caption or translate flowcharts into their respective pseudocode.

Flowchart Translation on Image

Flowchart Translation on Mask

As a guide, I used this article.

This project still holds lots of room for improvement. Some of the main ones are:

  1. Image Captioning with an Attention Mechanism
  2. More pseudocode/flowchart data. Until now I only fed 37 flowcharts with 37 pseudocode translations into the model.
  3. Use a Domain Specific Language instead of pseudocode for easier translation.

Run Jupyter notebooks

Run jupyter notebook in the terminal. Open the inspect_image_caption_model.ipynb Jupyter Notebooks to view results within the code.

About

The second part of my Bachelor's Degree project: "Translating" flowcharts into their respective pseudocode by using the method of Image Captioning. This involves a Convolutional Neural Network and a Recurrent Neural Network.

Resources

License

Stars

Watchers

Forks

Packages

No packages published