I'm currently working on an iOS App where I want to detect if there is a table, chair or bench in the current camera input.

My idea was to take the MobileNetV2 model and get it to classify these three categories with transfer learning in TensorFlow. Because there are cases where none of these three objects are visible, I would add a fourth class "none" and feed it with random pictures of different unrelated things.

Is this approach a good idea, or is there a better way of doing this?

  • 1
    $\begingroup$ In the past, we had similar questions, for example, this, this or this. Let me know if any of those posts is a duplicate of your post. $\endgroup$
    – nbro
    Jun 23, 2021 at 9:51
  • $\begingroup$ @nbro thank you for these suggestions. They were helpful for my problem :) $\endgroup$
    – Robin
    Jun 25, 2021 at 6:21


You must log in to answer this question.