The accuracy on voc is not as expected

[QiZhangsama]

I used pspnet101_voc2012.h5 and pspnet101_voc2012.json to test VOC data，and it's mIOU is 82.51% after uploaded the results. But the real value is 85.4% in the paper. I want to know why.

This is my resutls:

Competition	Category	Score
Object Segmentation (comp6)	background	95.69300
Object Segmentation (comp6)	aeroplane	93.16350
Object Segmentation (comp6)	bicycle	68.16070
Object Segmentation (comp6)	bird	92.60880
Object Segmentation (comp6)	boat	77.27700
Object Segmentation (comp6)	bottle	82.46240
Object Segmentation (comp6)	bus	91.86820
Object Segmentation (comp6)	car	91.61700
Object Segmentation (comp6)	cat	94.20940
Object Segmentation (comp6)	chair	37.09920
Object Segmentation (comp6)	cow	88.46340
Object Segmentation (comp6)	diningtable	74.82890
Object Segmentation (comp6)	dog	87.07190
Object Segmentation (comp6)	horse	93.95220
Object Segmentation (comp6)	motorbike	89.37420
Object Segmentation (comp6)	person	90.35040
Object Segmentation (comp6)	pottedplant	68.82600
Object Segmentation (comp6)	sheep	90.44340
Object Segmentation (comp6)	sofa	60.11600
Object Segmentation (comp6)	train	85.58210
Object Segmentation (comp6)	tvmonitor	79.56540
	Object Segmentation (comp6)	82.51110

[LeeThrzz]

I‘m sorry to bother you, I have a small question to ask you. Would you like to tell me which .py file that you used to test your accuracy? I didn't find it here, I am grateful that you can reply to me.

[xiaowoniuli]

I‘m sorry to bother you, I have a small question to ask you. Would you like to tell me which .py file that you used to test your accuracy? I didn't find it here, I am grateful that you can reply to me.

have you find it?

[LeeThrzz]

I‘m sorry to bother you, I have a small question to ask you. Would you like to tell me which .py file that you used to test your accuracy? I didn't find it here, I am grateful that you can reply to me.

have you find it?

no, if i find it I will tell you, and if you find it ,please tell me ,thanks