Authors: Juan Zurita, Sebastián Ayala Ruano, Ximena Celi, Gilberto Rodríguez.
This is the repository for CDD, an early plant disease detector based on convolutional neural networks, trained to recognize two types of maize infectious diseases: Common rust of corn and Northern corn leaf blight. A Transfer Learning
strategy was applied due to the absence of large image datasets of corn diseases. The main library used to build our model was Pytorch
. This project was built during the Saturdays AI Quito 2021 artificial intelligence workshop.
The complete information regarding datasets, model, performance metrics, a web application to test CDD, a jupyter notebook of reference to reproduce our work, and further details are available at our GitHub Page.
Special thanks to Will Koehrsen for providing a reference jupyter notebook of Transfer Learning in PyTorch tasks, which we took as the starting point for our work. Also, thanks to PlantVillage initiative to provide the data used to train our model.