This repo for Cassava plant disease classification using Deep Learning (DL) approach froom kaggle competitions.
From the images provided, the goal is classify the images into:
Cassava Bacterial Blight (CBB)
Cassava Brown Streak Disease (CBSD)
Cassava Green Mottle (CGM)
Cassava Mosaic Disease (CMD)
Healthy
The following command is to get the images, labels, and classes from kaggle competition
kaggle competitions download -c cassava-leaf-disease-classification
Then, run the following command to unzip the file
unzip cassava-leaf-disease-classification.zip
You can see now the following Directories/Files:
test_images
train_images
train.csv
Check the provided notebook.
Run main.py file to train and evaluate the model using the below command:
python main.py --batch_size 64 --epochs 10 --num_classes 5 --class_weights True --lr 0.000001 --gpu_number 1