-
Notifications
You must be signed in to change notification settings - Fork 6.8k
fcnxs example validation accuracy does not change #1815
Comments
during training, your labels may be all equaled to zeros, because 0.730370 is the background's ratio |
@sinaj ,you may check you data, i think it may be something wrong there, especially the label. |
@sinaj any update? as I was having exactly the same problem, even after checking the label. |
@sinaj i have same error,did you solve it |
@Hjy20255 No, could not solve it. |
I was having similar problem when porting fcn8s from vgg16 to resnet, changing |
sorry,i can not find use_global_stats in symbol_fcnxs.py |
Try debug the output of each layer by adding following code before executing forward pass (in this case, the code exists in
And there should be no numerical overflow (displayed as |
Hello,
I am trying to use the example code for image segmentation. I simply changed the train.lst and val.lst to replace my images, but when I run it, although the train accuracy changes, the validation accuracy does not change at all (it is always 0.730370). Is there any potential situation that it could happen?
Here is the log:
The text was updated successfully, but these errors were encountered: