TFFRCNN
TFFRCNN copied to clipboard
Low and weird mAP results on new dataset
I have trained faster rcnn on a new dataset based on pascal_VOC format. The configurations are like pascal_VOC but there are 9 classes and the training is done with 10000 iterations. This is the results:
AP for car = 0.5931
AP for truck = 0.3333
AP for tractor = 0.3470
AP for campingcar = 0.4091
AP for van = 0.5000
AP for other = 0.1983
AP for pickup = 0.3439
AP for boat = 0.0769
AP for plane = -1.0000
Mean AP = 0.2002
As you can see the AP values are very low, and for objects of type plane , it's -1. What can cause this? Should I change anything else to improve the AP values?
Have you solved the problem? How?
@ailias not yet. I have reduced the anchor base size from 16 to 2. It helped but not enough. I am trying to change the scale size to see if it helps. this is helpful as well.
I have meet the same problems?have you solved it? @ailias
@hadi-ghnd have you solved the problem?