nvinfer1::CudaError when attempting to run imagenet-console (Jetson TX2)

[xoxota99]

After installing JetPack 3.2 (L4T 28.2) on a Jetson TX2, and following Instructions for "Building From Source on Jetson", when I tried to run the Image Classification example, "./imagenet-console orange_0.jpg output_0.jpg", I got the following cryptic error:

`imagenet-console args (3): 0 [./imagenet-console] 1 [orange_0.jpg] 2 [output_0.jpg]

imageNet -- loading classification network model from: -- prototxt networks/googlenet.prototxt -- model networks/bvlc_googlenet.caffemodel -- class_labels networks/ilsvrc12_synset_words.txt -- input_blob 'data' -- output_blob 'prob' -- batch_size 2

[GIE] TensorRT version 3.0, build 3004 [GIE] attempting to open cache file networks/bvlc_googlenet.caffemodel.2.tensorcache [GIE] cache file not found, profiling network model [GIE] cudnnLayerUtils.cpp (288) - Cuda Error in smVersion: 38 terminate called after throwing an instance of 'nvinfer1::CudaError' what(): std::exception Aborted (core dumped)`

Any ideas why? Did I do something wrong, and if so, what?

[dusty-nv]

This is a strange error, because TX2 is sm_62 (not sm_38 like in the error above).

Are you sure the CUDA drivers were installed OK? Can you run deviceQuery and bandwidthTest CUDA samples ok and post the output of deviceQuery?

[ghost]

Hi, @xoxota99 @dusty-nv I have the same error. but, I try [imagenet-camera]

hey, @dusty-nv i installed cuda and CUDA sampled test OK.

Any ideas why?