bouding boxes predictions on rpn about tf-faster-rcnn HOT 6 CLOSED

This is your example I was referring to (from the other repository):

from tf-faster-rcnn.

Hi, the lion prediction was made without the nms.
If you remove the non max suppression method, sort the predictions according to the probabilities and draw the first few results, you can get similar results.

from tf-faster-rcnn.

Or you can try my last update.
I made the change mentioned above in rpn predictor.

from tf-faster-rcnn.

With the latest update I got these (with a clean pulled master branch). All boxes are starting from upper left:


Doing a quick print of the selected_rpn_bboxes tensor gives values between 1 and 10:

From the TF docs it seems expected values should be between 0 and 1:

Should I try to retrain my model or I'm missing something?
Model is trained with rpn_trainer.py, mobilenet_v2 and voc/2007.

from tf-faster-rcnn.

Hi, your results already range from 0 to 1.
We can simply say that your model is not well trained.
When your model is sufficiently trained, you should get similar results below.

from tf-faster-rcnn.

Ok, I'll train it again for 100 epochs and for voc2012.
Thanks a lot!

from tf-faster-rcnn.