zym1119/DeepLabv3_MobileNetv2_PyTorch

use your model meet some problems,could you help me?

Opened this issue · 4 comments

csufangyu commented

I run your code,meet the error as flows:
square_avg.mul_(alpha).addcmul_(1 - alpha, grad, grad)
RuntimeError: cuda runtime error (59) : device-side assert triggered at /pytorch/aten/src/THC/generic/THCTensorMathPairwise.cu:81
could you help me?thanks!

zym1119 commented

sorry to reply you so late, can you show me more error information plz?

zym1119 commented

i thought this may be caused by wrong in label tensor, maybe your label have negative value like -1, in cityscapes, the trainid of 'license plate' is -1, this may raise an error

  • 👍1
lcaikk1314 commented

i thought this may be caused by wrong in label tensor, maybe your label have negative value like -1, in cityscapes, the trainid of 'license plate' is -1, this may raise an error

Then how solve it in your git

JessicaDuFirst commented

I meet the same problem,did you solve it ??please tell the solution, thanks