search

openvinotoolkit / openvino

OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference
https://docs.openvino.ai
Apache License 2.0
7.06k stars 2.22k forks source link

Problem while installing openvino on NVIDIA Jetson TX2 #2360

Closed GraceKafuu closed 4 years ago

GraceKafuu commented 4 years ago

Hi, I have installed openvino by following this pagehttps://software.intel.com/content/www/us/en/develop/articles/arm64-sbc-and-ncs2.html. All the steps have run successfully, I just skipped install opencv, because JetPack already include opencv.

The problem is I can run benchmark_app and classification_sample, it worked fine:

nvidia@nvidia-desktop:~/openvino/bin/aarch64/Release$ ./classification_sample_async -i ~/OpenVINO/cat.jpg -m ~/OpenVINO/models/squeezenet/squeezenet_v1.1.xml -d MYRIAD [ INFO ] InferenceEngine: API version ............ 2.1 Build .................. custom_master_4b348500d4174ed26ec067b5fbb783b4f1a35341 Description ....... API [ INFO ] Parsing input parameters [ INFO ] Parsing input parameters [ INFO ] Files were added: 1 [ INFO ] /home/nvidia/OpenVINO/cat.jpg [ INFO ] Creating Inference Engine MYRIAD myriadPlugin version ......... 2.1 Build ........... custom_master_4b348500d4174ed26ec067b5fbb783b4f1a35341

[ INFO ] Loading network files [ INFO ] Preparing input blobs [ WARNING ] Image is resized from (4272, 2848) to (227, 227) [ INFO ] Batch size is 1 [ INFO ] Loading model to the device [ INFO ] Create infer request [ INFO ] Start inference (10 asynchronous executions) [ INFO ] Completed 1 async request execution [ INFO ] Completed 2 async request execution [ INFO ] Completed 3 async request execution [ INFO ] Completed 4 async request execution [ INFO ] Completed 5 async request execution [ INFO ] Completed 6 async request execution [ INFO ] Completed 7 async request execution [ INFO ] Completed 8 async request execution [ INFO ] Completed 9 async request execution [ INFO ] Completed 10 async request execution [ INFO ] Processing output blobs

Top 10 results:

Image /home/nvidia/OpenVINO/cat.jpg

classid probability

281 0.4206543
285 0.3176270
282 0.2512207
287 0.0074654
885 0.0006542
434 0.0004086
330 0.0003848
478 0.0002766
292 0.0002723
700 0.0000831

[ INFO ] Execution successful

[ INFO ] This sample is an API example, for any performance measurements please use the dedicated benchmark_app tool

But when I run python files:

from openvino.inference_engine import IECore

ModuleNotFoundError: No module named 'openvino'

Can anyone help me ?

jgespino commented 4 years ago

Hi @GraceKafuu

Did you try exporting PYTHONPATHand LD_LIBRARY_PATHvariables?

Should be something similar to the following. Please note this was on a x86 Ubuntu install with Python 3.6 and your path may be different. 

$ export PYTHONPATH=$PYTHONPATH:/home/user/openvino/bin/intel64/Release/lib/python_api/python3.6/
$ export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/home/user/openvino/bin/intel64/Release/lib/

Regards, Jesus

jgespino commented 4 years ago

Hi @GraceKafuu

Were you able to import OpenVINO to your python application?

Regards, Jesus

jgespino commented 4 years ago

Closing due to inactivity, please re-open or start a new issue if additional assistance is needed.