I am using Xcode's Create ML tool (right-click on Xcode icon in the dock → Open Developer Tool → Create ML). It works pretty well except that it always completes the training with the message:
Completed training - converged early at 10 iterations
even though I set Maximum Iterations to 100 (default is 25). When I test the model using new images by dragging them into the Preview tab and if it fails to identify the image correctly, I would add it to the training data, and rerun the training afresh. But again it would converge early at 10 iterations. Seems like it never gets to see the newly added images which were supposed to help improve its accuracy. How do I make Create ML work on all the images in the training data?