faster-rcnn.pytorch
faster-rcnn.pytorch copied to clipboard
Zero mAP when testing
Similar to #671 I am getting all zeros for test results, but there is no answer as to why in that post. Like this previous post, it seems as though i am getting non-zero mAP from manual insepction and from the training loss.
Can anyone explain how they might have fixed it?
hey @rkruegs123 , any update on this? I too am facing this issue. The training loss decreases well, but when I run test_net.py I get 0 mAP for all classes
I met the same issue , have you solved it ?
Do your labels have space or upper cases?
In pascal_voc.py, cls = self._class_to_ind[obj.find('name').text.lower().strip()]
This code causes your labels mismatch to classes.
Maybe you should modify 2 places:
-
self._classes = (...)
Make sure classes are same as your labels. -
cls = self._class_to_ind[obj.find('name').text]