Skip files without labels

[benjaminjack]

Sometimes you might have an image in your dataset with no bees present. It would be nice if data.py and train.py could automatically skip unlabeled files, assuming that they don't have any bees in them. Or, alternatively, if we could make an image as containing no bees.

[matpalm]

this is actually covered already in the data model; an entry in the imgs table with no entries in the labels table is an image with no bees. https://github.com/matpalm/bnn/blob/master/label_db.py#L35

unlabelled shouldn't be the same as no bees;