Imagenet-camera not working with Jetson TX1

Camera is working using this command:
gst-launch-1.0 nvcamerasrc ! nvoverlaysink

However, I Am getting this error now when using imagenet-camera googlenet and image-console. I thought it may be file corruption but downloaded multiple times with no luck.

Can you help resolve?

ubuntu@tegra-ubuntu:~/jetson-inference/build/aarch64/bin$ ./imagenet-camera googlenet
args (2): 0 [./imagenet-camera] 1 [googlenet]

[gstreamer] initialized gstreamer, version
[gstreamer] gstreamer decoder pipeline string:
nvcamerasrc fpsRange=“30.0 30.0” ! video/x-raw(memory:NVMM), width=(int)1280, height=(int)720, format=(string)NV12 ! nvvidconv flip-method=0 ! video/x-raw ! appsink name=mysink

imagenet-camera: successfully initialized video device
width: 1280
height: 720
depth: 12 (bpp)

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 2.1, build 2102
[GIE] attempting to open cache file networks/bvlc_googlenet.caffemodel.2.tensorcache
[GIE] cache file not found, profiling network model
terminate called after throwing an instance of ‘nvinfer1::CudaError’
what(): std::exception


Could you upgrade your TensorRT to 3.0 (JetPack3.2 DP) and give it a try?

I have a TX1, what is the installation guide for this upgrade?


Sorry for missing it. JetPack3.2 DP is only for TX2.

We are checking this issue internally.
Will reply here later.



We have verified the imagenet-camera sample and it works well on our side.
Could you delete the complete jetson-inference folder and retry it again?

Thanks, and please let us know the results.