Plant Disease Prediction

The workflow demonstrates how to do transfer-learning. We are using the pre-trained deep learning network Resnet50 and are repurposing it to predict two apple tree diseases, rust and scab, based on images of apple leaves. To do so, we are freezing the weights of the first third of the layers and only retrained the weights of the remaining two thirds of the layers. Additionally, we are using the Keras Imaga Data Generator for image augmentation.

External resources

• Data: The Plant Pathology Challenge 2020 data set to classify foliar disease of apples