iamgenet file not found 'networks/bvlc_googlenet.caffemodel ...

Robotics & Edge Computing Jetson & Embedded Systems Jetson TX2
1

Hello there!

I’m trying to complete “two days to a demo”.

I followed the guide provided at https://developer.nvidia.com/embedded/twodaystoademo

I get into “Using the Console Program on Jetson” but it looks like something is missing.

when using this command:

$ ./imagenet-console orange_0.jpg output_0.jpg

I got this response:

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 2.1, build 2102
[GIE] attempting to open cache file networks/bvlc_googlenet.caffemodel.2.tensorcache
[GIE] loading network profile from cache… networks/bvlc_googlenet.caffemodel.2.tensorcache
terminate called after throwing an instance of ‘nvinfer1::CudaError’
what(): std::exception
Aborted (core dumped)

I looked at Getting errors in using onboard camera (JetPack 3.1) - Jetson TX1 - NVIDIA Developer Forums but is a TX1 board and also seems not solved.

I am missing something?

I tried to reinstall and build from scratch jetson-inference folder again but same message appears.

Note: Inside networks directory, there is not bvlc_googlenet.caffemodel.2.tensorcache file, there is bvlc_googlenet.caffemodel instead.

thanks for your time !

2

are you following the guide provided at https://github.com/dusty-nv/jetson-inference/blob/master/README.md ?
specifically [url]https://github.com/dusty-nv/jetson-inference/blob/master/README.md#building-from-source-on-jetson[/url] ?

3

Hi Andrey,

I installed cuDNN, NVcaffe and Digits on the HOST.

I Didn’t test yet but digits seems to be ready and OK.

When I get into “building from source on Jetson” I followed step by step until using imagenet-console, which is giving me the error.

I search for driver’s versions with

head -1 /etc/nv_tegra_release

and got this:

R28 (release), REVISION: 1.0, GCID: 9379712, BOARD: t186ref, EABI: aarch64, DATE: Thu Jul 20 07:59:31 UTC 2017

I saw there is a REVISION 2.0 but I don’t know how to upgrade or if it’s necessary.

Thanks again

4

when you are doing “building from source on Jetson”
what instruction steps you are following?
try jetson-inference/README.md at master · dusty-nv/jetson-inference · GitHub

5

how to reproduce the error and what is the content of the error message?

6

if you are using tx2 flashed from Jetpack 3.1, you may also try Jetpack3.2 that will have R28.2

7

I will try that so.

Thanks !

8

Well, it was a sudo restriction.

I need to sudo the command, now it’s working fine.