search

isht7 / pytorch-deeplab-resnet

DeepLab resnet v2 model in pytorch
MIT License
602 stars 118 forks source link

the result? #36

Open yyfyan opened 6 years ago

yyfyan commented 6 years ago

Hi,Good job. I used your trained model, VOC12_scenes_16000.pth, to test,But get the lower mIou 66.35%，not get your mIou result.

1

isht7 commented 6 years ago

Would you mind sharing screenshot of your evaluation code used here?

yyfyan commented 6 years ago

I used the evalpyt2.py evalpyt2.py.zip

yyfyan commented 6 years ago

and when read the train.py，I found the flip augment is not used,becauses you only flip the image ,not use the double images(origali image and flip image).

marvis commented 5 years ago

@yyfyan I got exactly the same result as yours.

evalpyt.py: pytorch 1 0.7467628417262675 evalpyt2.py: pytorch 1 Mean iou = 0.6635553130340005

Have you solved this problem?