eforebrahim/Cassava-Leaf-Disease-Classification

Cassava Leaf Disease Classification Project

Background Information

“As the second-largest provider of carbohydrates in Africa, cassava is a key food security crop grown by smallholder farmers because it can withstand harsh conditions. At least 80% of household farms in Sub-Saharan Africa grow this starchy root, but viral diseases are major sources of poor yields. With the help of data science, it may be possible to identify common diseases so they can be treated.”

Data

The data contains about 21,000 images of Cassava plant belonging to 5 different categories (4 diseases and 1 healthy). The dataset was made available by Makerere University AI Lab via Kaggle Competition. You can get the dataset from here: (https://lnkd.in/dxGUTcN4)

Modeling

Pre-trained model efficientnet version b2 is used for modeling. Dropout layers were added to prevent model from overfitting. Validation precision of 0.855, recall of 0.813, and accuracy of 0.831 is achieved.

Deployment

The web app is hosted on huggingface spaces using streamlit user interface. #datascience #machinelearning #computervision #artificialintelligence

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference