search

sdemyanov / ConvNet

Convolutional Neural Networks for Matlab for classification and segmentation, including Invariang Backpropagation (IBP) and Adversarial Training (AT) algorithms. Trained on GPU, require cuDNN v5.
240 stars 141 forks source link

cnnexamples fails #17

Open jamborta opened 9 years ago

jamborta commented 9 years ago

Hi Sergey,

thank you for sharing this code.

I am trying to run one of your examples ( the cpu version of it), but it fails with the following error:

Error using genweights_mex Assertion Failed: In 'mexGetScalar' mx_array is not numeric

Error in genweights (line 4) weights = genweights_mex(layers, params);

Error in cnnexamples (line 82) weights = single(genweights(layers, params, funtype));

looks like the signature of genweights_mex changed?

sdemyanov commented 9 years ago

Hi,

nothing changed, everything should work. Check again the arguments you are passing. If not, send the code you are running, I'll check it.

Sergey.

TrungNg commented 9 years ago

Hi, this question is originated from the very first step, so I'd like to post it in the same topic here. in the settings.h file: // COMP_REGIME = 1 -> MULTITHREAD CPU do you mean multithread GPU? is this option faster than the option 2? (Sr, I'm newbie to CUDA)

TrungNg commented 9 years ago

where can i find "compile" script? is it Makefile? or compile.m? if it's compile.m, what parameters should I pass to compile?

sdemyanov commented 9 years ago

"do you mean multithread GPU?" No, I mean multithread CPU.

sdemyanov commented 9 years ago

"where can i find "compile" script? is it Makefile? or compile.m? if it's compile.m, what parameters should I pass to compile?"

Makefile is for compiling the GPU version on Linux. compile.m is for compiling all versions (1-CPU, 2-multithread CPU, 3-GPU) on both Windows and Linux. The parameter is the number of version.

HosnaCSE commented 8 years ago

Hello,

I get the same error during the compilation of your code.

Error using genweights_mex Assertion Failed: In 'mexGetScalar' mx_array is not numeric

Error in genweights (line 4) weights = genweights_mex(layers, params);

Error in cnnexamples (line 82) weights = single(genweights(layers, params, funtype));

Can you help me out there?

YaoJUN94 commented 8 years ago

@HosnaCSE did you solve your problem? May I know how u solve it??

Thank you.