CUDA error during the testing stage

[Fengyboy]

Hi there,

I modified the testing Python code provided in the package. However when I try to predict images using the pre-trained BSDS model, I got the following error:
F0106 13:18:05.372474 6347 syncedmem.cpp:19] Check failed: error == cudaSuccess (29 vs. 0) driver shutting down

I have tested on two machines, one with GTX Titan X and the other with GTX 960, giving the same error. If I supply a list images, this only happens after the code finishes processing all the images. It appears to be one of the side effects of certain version of Caffe. So far I have not yet found any solutions, could you please help me with this?

Thanks in advance,
Feng

[Fengyboy]

I've figured out the problem. Basically in the Make.config file, the line of # WITH_PYTHON_LAYER := 1 should be uncommented. So after recompiling the code, it works fine now.

[daiw10]

@Fengyboy I also got "F0212 11:44:17.588241 13859 syncedmem.cpp:19] Check failed: error == cudaSuccess (29 vs. 0) driver shutting down"
and I have uncommented the "with_python_layer"
my environment is ubuntu16.04 and cuda 8.0,GTX TITan X and I make the caffe in the project. Would you give me some advice? Many thanks :)

[aditipanda]

@Fengyboy I tried your solution but it didn't work. I am still getting the same error.