I want to use createML to generate an image recognition model. This works when I put the images in separate sub-folders. But my data consists of many images in one folder with a spreadsheet index of the photos according to several different attributes. I suppose I could write a script to move the images into the correct folders, and repeat this for each of the attributes. But I was hoping there’s a way of doing this directly in createML since I’m sure it’s a common requirement. Anyone know if createML can do this or does anyone know of an app that would save me writing the script?
CreateML only provides labeled directories and labeled files at this time. If there is some other way you would like to provide your training data, then won't you please consider filing a feature request explaining what you'd like to do.
You can file an enhancement request using the Feedback Assistant. Once you file the request, please post the FB number here.
If you're not familiar with how to file enhancement requests, take a look at Bug Reporting: How and Why?