This hackathon was created to demonstrate the process of setting up a competition, along with the peril of using public datasets. This competition is to classify "fresh" vs "rotten" apples, bananas, and oranges. However, such classification can be rather subjective and the training/testing datasets suggest that it is really "fresh" vs "not-fresh". The validation dataset was mostly crowdsourced from participants at the DLAI5 hackathon from pics taken by themselves, with minimal data augmentation. Data labeling was a partially crowdsourced effort as well. Special thanks to the following contributors who provided real-life images, in chronological order of images received: Ramil Joaquin, Kmer Jaeriz Mesina, Adrian-Ver Federizo, Renel R. Dilao, Kelsey Kng, Sandipan Majhi, Sharmistha Bhattacharya. 

Watch for DLAI8 that will be coming this summer for more challenging competitions.