By Leonard Loo, Nikhila Ravi, Kimia Mavon and Yihang Yan
Watch the video to learn about our project!
Please don't shift around the directories. You can run the code in the various .ipynb as they are and they will read from the data folder.
Milestone1: No data needed. Pulled directly from TMDB. Milestone2: No data needed. Pulled directly from TMDB and IMDB. Milestone3: Used train_data_with_sampling.csv, test_data.csv and keywords.csv. Milestone4: No data needed. Pulled posters directly from our Github repo. Note: The data augmentation code's data is not included, because there are too many posters generated.
This project was created for the AC209b class at Harvard Spring 2017