This folder shares my work for the Kaggle Plant Pathology Competition which is designed to engage students in the advanced field of agricultural disease detection using machine learning. Utilizing a dataset originally from the Kaggle Plant Pathology 2021 FGVC8 competition, participants will develop models to accurately classify different plant diseases in crops, with a focus on improving agricultural outcomes.
For more details refer to the original competition link: https://www.kaggle.com/competitions/plant-pathology-2021-fgvc8.
The primary objective is to develop a deep-learning model that can classify plant diseases based on images. Participants will use the provided training dataset, which consists of images resized to a maximum dimension of 600 pixels while maintaining the aspect ratio. The challenge is to use these images to train models that can accurately classify plant diseases in the test set.
Source: Derived from the Plant Pathology 2021 - FGVC8 Kaggle competition (https://www.kaggle.com/competitions/plant-pathology-2021-fgvc8).
Training Set: Publicly available images, resized with the largest dimension capped at 600 pixels. The dataset includes various classes of plant diseases.
For the original Kaggle Competition, details and background information on the dataset and Kaggle competition ‘Plant Pathology 2020 Challenge’ were published as a peer-reviewed research article.
Thapa, Ranjita; Zhang, Kai; Snavely, Noah; Belongie, Serge; Khan, Awais. The Plant Pathology Challenge 2020 data set to classify foliar disease of apples. Applications in Plant Sciences, 8 (9), 2020.
The evaluation metric for this competition is Mean F1-Score.