search

davidtvs / PyTorch-ENet

PyTorch implementation of ENet
MIT License
383 stars 129 forks source link

test IoU is nan #40

Closed ykk136 closed 4 years ago

ykk136 commented 4 years ago

Thank you for opening the wonderful codes of ENet for us. When I try to select the "test" mode , the result is like this:

Avg. loss: 13.1708 | Mean IoU: nan unlabeled: nan road: nan sidewalk: nan building: nan wall: nan ...

And all the IoUs are nan. However, when I choose to train the ENet model, the mIoU is normal, but I am sure that the project uses the same iou.py and confusionmatrix.py. Would you like to explain the reason for me? Thank you very much!

ykk136 commented 4 years ago

I see. #8 can perfectly explain the problem.