search

icoz69 / CaNet

The code for paper "CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning"
190 stars 32 forks source link

IOU is 0.000 always #13

Closed sanersbug closed 4 years ago

sanersbug commented 4 years ago

In the train stage, the IOU is constant like this:

e:198 loss = 0.1104-:0.0000: 100%|██████████████| 15/15 [00:04<00:00, 3.53it/s] ----Evaluation---- IOU:0.0000 IOU for this epoch: 0.0000 best epoch:0 ,iout:0.0000 This epoch taks: 4.778814792633057 second still need hour:0.0027 e:199 loss = 0.1190-:0.0000: 100%|██████████████| 15/15 [00:04<00:00, 3.51it/s] ----Evaluation---- IOU:0.0000 IOU for this epoch: 0.0000 best epoch:0 ,iout:0.0000 This epoch taks: 4.783169269561768 second still need hour:0.0013

Anyone can thnow why?

GWwangshuo commented 4 years ago

In the train stage, the IOU is constant like this:

e:198 loss = 0.1104-:0.0000: 100%|██████████████| 15/15 [00:04<00:00, 3.53it/s] ----Evaluation---- IOU:0.0000 IOU for this epoch: 0.0000 best epoch:0 ,iout:0.0000 This epoch taks: 4.778814792633057 second still need hour:0.0027 e:199 loss = 0.1190-:0.0000: 100%|██████████████| 15/15 [00:04<00:00, 3.51it/s] ----Evaluation---- IOU:0.0000 IOU for this epoch: 0.0000 best epoch:0 ,iout:0.0000 This epoch taks: 4.783169269561768 second still need hour:0.0013

Anyone can thnow why?

@sanersbug Have you solved this problem?

sanersbug commented 4 years ago

@GWwangshuo Sorry, I give up it. How about you ?

icoz69 commented 4 years ago

hello did you update your PyTorch to the latest version? In my setup, all is well.

GWwangshuo commented 4 years ago

hello did you update your PyTorch to the latest version? In my setup, all is well.

Thanks for your suggestion. In my case, the IoU increases after many epochs.