Test SSD object detection on a specific test image

I am looking to test my own image on an object detection task with a trained model as this is described in Part 2 Lesson 9, (Pascal VOC - object detection).

So far I haven’t seen any code to use a test set or even a single image to detect objects if any. Some specs about that image(s):

  • should not be part of the training, i.e. it should not be part of the md.trn_ds neither the md.val_ds.
  • there should be no ground-truth boundary box for it.

Has anyone tried it?

I’m facing the same issue, does someone have a solution?
I’m trying to run detection on a test image, for what I don’t have any BBoxes.