There are so many kinds of data and so many kinds of data annotations.

For deep learning, the quantity required is high. The question is always “how much is enough?”

You kind of need to narrow your question.

If I was you, I’d look at your competitors and see what they claim to do. Often it’s shipping customers’ image data off to somewhere for cheap labor. And requires the customer to look at the annotations to verify they’re as expected. In my limited experience, there’s a LOT of review.

Data is everything.