I trained some weights to identify apples and oranges (using YOLOv3).
If I want to be able to identify peaches, which approach is usually recommended:
- Start clean and train the 3 classes.
- Train the peaches over the already-trained weights (with apples and oranges)
- Only train with peaches images
- Use all available training data (including apples and oranges)
This is what I have found:
- If I start clean, it will take longer until I can get a good result, but the detection is usually better.
- Every time I add a new class (using
2.2), the detection get worse for the already learned objects, but it takes less time until I can get a good result (however I suspect that apples and oranges become over-fitted?).
- I haven't tested
2.1, as I think that it won't be able to re-adjust the weights for the apples and the oranges.
Is the above expected? What is the recommended course of action?