search

fyu / drn

Dilated Residual Networks
https://www.vis.xyz/pub/drn
BSD 3-Clause "New" or "Revised" License
1.1k stars 219 forks source link

train error #9

Closed ZzzjzzZ closed 7 years ago

ZzzjzzZ commented 7 years ago

Hi, when I train the segment.py, it crashed, the problem is listed below：

THCudaCheck FAIL file=/opt/conda/conda-bld/pytorch_1503968623488/work/torch/lib/THC/generic/THCStorage.c line=32 error=59 : device-side assert triggered Traceback (most recent call last): File "segment.py", line 553, in main() File "segment.py", line 548, in main train_seg(args) File "segment.py", line 355, in train_seg eval_score=accuracy) File "segment.py", line 249, in train losses.update(loss.data[0], input.size(0)) RuntimeError: cuda runtime error (59) : device-side assert triggered at /opt/conda/conda-bld/pytorch_1503968623488/work/torch/lib/THC/generic/THCStorage.c:32

How can I get with this problem.

ZzzjzzZ commented 7 years ago

I have found that the problem is the num of class; in cityscapes dataset, the original labels have 37 classes, but you use 19 classes. Does it mean that I should relabel the ground-truth, or get with it using other methods. thx

fyu commented 7 years ago

You are supposed to convert the data to 19 classes based on trainId provided by Cityscapes team: https://github.com/mcordts/cityscapesScripts/blob/master/cityscapesscripts/helpers/labels.py#L61. This is the standard way to train and test semantic segmentation networks on Cityscapes.

ZzzjzzZ commented 7 years ago

thanks a lot