For this project, we borrowed a dataset (https://www.kaggle.com/neha1703/movie-genre-from-its-poster) of imdb movie listings and modified it so that we have a dataset of 10,000 movie posters along with their imdb ratings. Using this, we created a tool that can take in a movie poster's image url and return an estimated rating of the movie based on what similar looking movie posters received. Our tool will return the predicted rating along with a histogram of the ratings of the similar movie posters.
In order to run, you will need to have python3 installed. When in the project folder:
- run "pip install -r requirements.txt" in order to install all the required libraries
- export FLASK_APP=main.py
- flask run
- open up http://127.0.0.1:5000/ in a browser
Note: After running one movie poster, python may quit. Repeat steps 3 and 4 to run again.
if flask doesn't work check this out: https://flask.palletsprojects.com/en/1.1.x/quickstart/
