(For details about training, visit: https://github.com/ElyasYassin/ImageToPoem )
Welcome to the Image2Poem Demo, a simple web app created as part of our Intro to Machine Learning class project. This application transforms images into poems, showcasing the intersection of creativity and AI. Follow the instructions below to set up and run the app.
-
Clone the Repository
git clone <repository_url> cd <repository_directory>
-
Setup a virtual environment
You can either use Anaconda or Venv to avoid dependency issues (Here's the documentation: https://docs.conda.io/projects/conda/en/latest/user-guide/install/index.html / https://docs.python.org/3/library/venv.html) -
Install Dependencies
pip install -r requirements.txt
-
Download Trained Models
https://drive.google.com/file/d/1Oe385qiqWQBprXzI31MXeMBSkbr4D3Q5/view?usp=sharing -
Run Flask App
flask --app app run
- Initial Load Time: The web app might take a few seconds to display upon launch.
- Sound Generation Delay: Generating the audio for the poem will take around 20 seconds (You can look at the terminal for progress information)
- Bug Alert: If the poem, sound, or image doesn’t update properly, try restarting the Flask app.