What modern tools would you recommend to replace a drawing classification machine learning model I built years ago (with Turi Create) to recognize emojis trained on drawings users submit? I tried an image classifier with CreateML but training time is much longer and accuracy is worse. Does Apple have a solution for drawing classification? Is a ML model still the best solution, or any AI advancements good for this use case? Thanks!
CreateML's image classification is designed to work on natural images, so it's not surprising that it may be sub-optimal on images from user drawings. There is no other dedicated custom model training solution for drawing classification.
You can always try some open source drawing classifier (PyTorch implementation), fine tuning onto your own data and convert it to Core AI (or CoreML) to run on device.
If you can try CreateML framework instead of the CreateML app you can plug in an open source image feature extractor that is more suited for drawings (than natural images). That path you do not have to worry about setting up training in Python.
