Execute tests error about cldnn HOT 4 CLOSED

By the way, If i only want to compile example_cldnn.cpp (in tutorial folder), how to compile it? gcc example_cldnn.cpp -o example_cldnn ?
When i see the code of example_cldnn.cpp, I find that i don't have the files, conv1_weights.bin, fc1_weights.data..etc, how to get this files?

Thank you very much

from cldnn.

Hi Jia-HongHenryLee,
We didn't have your device id in our list of supported HW's. I've added it already. Thanks for pointing it out.
Regarding to your second question: you have to prepare your own files with data and pare it to cldnn format.

from cldnn.

Hi tponieck,
What conv1_weights.bin and fc1_weights.data is ? How can i prepare for it?

from cldnn.

You need to fill memory primitive with data based on weights layout i.e.:
layout conv1_weights_layout(data_type, format::bfyx,{ conv1_out_channels, input_channels, conv_krnl_size, conv_krnl_size });
bfyx means order will be:
output featre map - input feature map - height (spatial y) - width (spatial x)
data should be float precision
to get better understanding I recommend to follow test case: basic_ofm_wsiz3x2x2x1_in2x2x1_nopad from: https://github.com/intel/clDNN/blob/master/tests/test_cases/convolution_gpu_test.cpp

from cldnn.