I’ve added training samples with 5 different habitat types for satellite image classification.
However when I run train vector classifier only 4 classes are produced.
What does this mean? Is it possible there is not enough spectral separability between two of the classes?
How many available samples do you have for each class?
Hello. Between 500 to 1000
This is enough samples.
What is the confusion matrix for training and validation: is the “missing” class equally diluted in the other ones? Or confused with a single other class?
Do you notice the same for training and validation evaluations?
What classifier do you use?
It could be great to have partial logs to help you better.
I find strange that one class is completely missing: In the case of a very hard-to-separate class, I would rather expect a great amount of confusion between classes, but not expecting a class that is completely missing…
Thanks remi. Sorry for not replying. I’ve moved on from this now. Was up against a deadline so had to improvise with some manual alteration.