train-DeepLab icon indicating copy to clipboard operation
train-DeepLab copied to clipboard

Different mean_iou on VOC12

Open dingfg opened this issue 6 years ago • 1 comments

I tested resnet-101 successfully, but it's not the same as the author's miou. The result before densecrf on the validation set was 0.7646 and the paper was 0.7635. Strangely, the miou I ran out of VGG-16 was consistent with the paper. Does anyone have the same problem?

dingfg avatar Mar 21 '18 08:03 dingfg

What did you use for evaluate? Is it evaluate_deeplab.py. I use VOCdevkit to evaluate result,but their value of iou is not the same. Thanks

zhwis avatar May 23 '18 00:05 zhwis