longcw / yolo2-pytorch

YOLOv2 in PyTorch

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

mAP when test VOC2007

yyhlvdl opened this issue · comments

I have trained VOC2007 for one epoch(without pre-trained), and test the model, the results is this:

AP for aeroplane = 0.0000
AP for bicycle = -1.0000
AP for bird = -1.0000
AP for boat = -1.0000
AP for bottle = -1.0000
AP for bus = -1.0000
AP for car = -1.0000
AP for cat = -1.0000
AP for chair = -1.0000
AP for cow = -1.0000
AP for diningtable = -1.0000
AP for dog = -1.0000
AP for horse = -1.0000
AP for motorbike = -1.0000
AP for person = -1.0000
AP for pottedplant = -1.0000
AP for sheep = -1.0000
AP for sofa = -1.0000
AP for train = -1.0000
AP for tvmonitor = 0.0000
Mean AP = -0.9000

what happened? Shouldn't mAP >0 always, even for one epoch? Can anyone solve my confusion,plz?