Thank you for enjoying the article.
For Multi-class classification
Update the myMaskRCNNConfig with the number of classes based on your custom dataset
# number of classes (we would normally add +1 for the background)
# kangaroo + BG
NUM_CLASSES = 1+1
Update the code for load_dataset() to include the different classes in your dataset
# Add classes. We have only one class to add.
self.add_class(“dataset”, 1, “kangaroo”)
Update the code for load_mask() to include the different classes in your dataset
put the images for different classes in the different folders for train, test and validation datasets
Hope this helps