Vladkryvoruchko/PSPNet-Keras-tensorflow

The accuracy on voc is not as expected

QiZhangsama opened this issue · 3 comments

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

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.

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?

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