This is a "crowdsourcing" hackathon challenge from The 5th Deep Learning and Artificial Intelligence (DLAI5) Summer School, running from May 6-10, 2021.
Bad Apples!
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.
Acknowledgements
We thank all participants from DLAI5 hackathon session on Sat, May 8, 2021 who participated in the creation of this challenge.