Search code examples
machine-learningimage-processingcomputer-visionobject-detectionyolo

How To Do Image Labeling for YOLO


I have 5000 images for fish detection and tracking. These images consist of images of 5-10 different fish species. Should I do the labeling as a small number of fish species? Or should I do it as a fish top type varying between 50-100? Or shall I say all of them are fish? Would the number of images labeled 5-10 or 50-100 be few for training?


Solution

  • If you are interested in detecting any kind of fish, then you can give all kinds of fish the same class. If you want the model to detect and classify different types of fishes differently, your labelling should also be specific for each class

    And for the last question, yes, 5-10 or 50-100 would be few for training You must at least target 300-400 objects as the bare minimum for training