jetson-inference samples does't work

I installed jetson-inference successfully on the JetSon TX1. And I ran the samples. I also installed jetson-inference on the host-pc. But I could not run the examples. Trying to run any example gives an error like this:

/Desktop/jetson/jetson-inference/build/x86_64/bin$ sudo ./imagenet-console orange_0.jpg output1.jpg
imagenet-console
args (3): 0 [./imagenet-console] 1 [orange_0.jpg] 2 [output1.jpg]

[GIE] attempting to open cache file networks/bvlc_googlenet.caffemodel.2.tensorcache
[GIE] loading network profile from cache… networks/bvlc_googlenet.caffemodel.2.tensorcache
[GIE] platform does not have FP16 support.
[GIE] networks/bvlc_googlenet.caffemodel loaded
[GIE] CUDA engine context initialized with 2 bindings
[GIE] networks/bvlc_googlenet.caffemodel input binding index: 0
[GIE] networks/bvlc_googlenet.caffemodel input dims (b=2 c=3 h=224 w=224) size=1204224
[cuda] cudaAllocMapped 1204224 bytes, CPU 0x1020d000000 GPU 0x1020d000000
[GIE] networks/bvlc_googlenet.caffemodel output 0 prob binding index: 1
[GIE] networks/bvlc_googlenet.caffemodel output 0 prob dims (b=2 c=1000 h=1 w=1) size=8000
[cuda] cudaAllocMapped 8000 bytes, CPU 0x1020d200000 GPU 0x1020d200000
networks/bvlc_googlenet.caffemodel initialized.
[GIE] googlenet loaded
imageNet – loaded 1000 class info entries
googlenet initialized.
loaded image orange_0.jpg (1920 x 1920) 58982400 bytes
[cuda] cudaAllocMapped 58982400 bytes, CPU 0x1020d400000 GPU 0x1020d400000
[cuda] cudaGetLastError()
[cuda] invalid device function (error 8) (hex 0x08)
[cuda] /home/monster/Desktop/jetson/jetson-inference/imageNet.cu:97
[cuda] cudaPreImageNetMean((float4*)rgba, width, height, mInputCUDA, mWidth, mHeight, make_float3(104.0069879317889f, 116.66876761696767f, 122.6789143406786f))
[cuda] invalid device function (error 8) (hex 0x08)
[cuda] /home/monster/Desktop/jetson/jetson-inference/imageNet.cpp:184
imageNet::Classify() – cudaPreImageNetMean failed
imagenet-console: failed to classify ‘orange_0.jpg’ (result=-1)

shutting down…

Hi,

Thanks for your feedback.

Sample fails since invalid device function:

[cuda] invalid device function (error 8) (hex 0x08)

Jetson_inference is a sample for tegra device. Do you want to use it on x86 platform?

Hi, AstaLLL

Yes, I want to run it on the X86 platform. Because in github site; “Note that TensorRT samples from the repo are intended for deployment on embedded Jetson TX1 / TX2 module, however when cuDNN and TensorRT have been installed on the host side, the TensorRT samples in the repo can be compiled for PC.” says.

Is there no way to run it?

Here is the solution:


Thank you…