ternaus / TernausNetV2

TernausNetV2: Fully Convolutional Network for Instance Segmentation

Home Page:http://openaccess.thecvf.com/content_cvpr_2018_workshops/papers/w4/Iglovikov_TernausNetV2_Fully_Convolutional_CVPR_2018_paper.pdf

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

RuntimeError: CUDA Error encountered in <function CompiledLib.bn_forward_cuda at 0x7f2dfa433730>

nsutezo opened this issue · comments

Hi,
I'm trying to run Demo.ipynb but it breaks on the following line:

prediction = F.sigmoid(model(input_img)).data[0].cpu().numpy()

The error I get is below which I traced to line 16 of modules/functions.py

RuntimeError: CUDA Error encountered in <function CompiledLib.bn_forward_cuda at 0x7f2dfa433730>

Tracing the error, I see that it stems from conv2 = self.conv2(self.pool(conv1)) here.

I am not exactly sure how to fix it.
Kindly advise.

Hello,

I found that modifying the build.sh file as below solved the problem. This is because certain codes are needed for certain gpus.

CUDA_GENCODE="-arch=sm_30 \
 -gencode=arch=compute_30,code=sm_30 \
 -gencode=arch=compute_50,code=sm_50 \
 -gencode=arch=compute_52,code=sm_52 \
 -gencode=arch=compute_60,code=sm_60 \
 -gencode=arch=compute_61,code=sm_61 \
 -gencode=arch=compute_62,code=sm_62 \
 -gencode=arch=compute_70,code=sm_70 \
 -gencode=arch=compute_70,code=compute_70"

Is CUDA 9.0 required to run the code? Thanks!

Hard to tell. I believe I was using CUDA 9.0, but I am not sure that is is a requirement.

What CUDA version do you have installed?