Intel® DevCloud
Help for those needing help starting or connecting to the Intel® DevCloud
Announcements
The Intel sign-in experience is changing in February to support enhanced security controls. If you sign in, click here for more information.
1216 Discussions

OpenVINO SDK usage in Devcloud

skumar
Beginner
327 Views

Hi,

 

This is regarding the usage of OpenVino SDK in devcloud. I am trying to run sample inference but getting runtime error while loading the network, default device is CPU. It would be great if you can help me in pointing out what is being missed here.

 

  1. Setting up openvino environment is successful

(base) u119434@login-2:~/ov$ source /opt/intel/openvino/bin/setupvars.sh

[setupvars.sh] OpenVINO environment initialized

 

  1. Downloading face-detection-0206 from intel model zoo is successful

(base) u119434@login-2:~/ov$ /opt/intel/openvino/deployment_tools/tools/model_downloader/downloader.py --name face-detection-0206

 

  1. Running the sample object detection, python module, as per the documentation here throws runtime error, as given below

FP32

(base) u119434@login-2:~/ov$ /opt/intel/openvino/deployment_tools/inference_engine/samples/python/object_detection_sample_ssd/object_detection_sample_ssd.py -m ./intel/face-detection-0206/FP32/face-detection-0206.xml -i ./person_detection.png                             [ INFO ] Creating Inference Engine

[ INFO ] Reading the network: ./intel/face-detection-0206/FP32/face-detection-0206.xml

[ INFO ] Configuring input and output blobs

[ INFO ] Loading the model to the plugin

Traceback (most recent call last):

  File "/opt/intel/openvino/deployment_tools/inference_engine/samples/python/object_detection_sample_ssd/object_detection_sample_ssd.py", line 161, in <module>

    sys.exit(main())

  File "/opt/intel/openvino/deployment_tools/inference_engine/samples/python/object_detection_sample_ssd/object_detection_sample_ssd.py", line 85, in main

    exec_net = ie.load_network(network=net, device_name=args.device)

  File "ie_api.pyx", line 403, in openvino.inference_engine.ie_api.IECore.load_network

  File "ie_api.pyx", line 442, in openvino.inference_engine.ie_api.IECore.load_network

RuntimeError: could not create a memory object

FP16

[ INFO ] Creating Inference Engine

[ INFO ] Reading the network: ./intel/face-detection-0206/FP16/face-detection-0206.xml

[ INFO ] Configuring input and output blobs

[ INFO ] Loading the model to the plugin

thread_monitor Resource temporarily unavailable in pthread_create

While using GPU as default device

RuntimeError: Failed to create plugin /opt/intel/openvino/deployment_tools/inference_engine/lib/intel64/libclDNNPlugin.so for device GPU

Please, check your environment

[CLDNN ERROR]. No GPU device was found.

 

0 Kudos
1 Solution
ChrisB_Intel
Moderator
270 Views

I am not able to read the screen shot you attached, it is a bit to small. However, if you are using Cygwin to connect then you are connecting to the OneAPI devcloud, which does not have OpenVINO support. Cygwin is not available on the OpenVINO devcloud. Sounds like maybe you are thinking they are interchangeable?

Thanks

Chris



View solution in original post

3 Replies
ChrisB_Intel
Moderator
300 Views

Apologies for the issues you are running into. I am guessing you are running on 2021.4.2 version, is that correct?


It looks like it could be a memory issue on the node you are running on. Would you be able to send me which node/cpu you are running this with, a screen shot would be great? Additionally, as a test have you tried a different node?


Also, would you be able to provide me the whole model so I can take a look at it. Did you make any changes to the model you got from model soo, or are you running it exactly as is?


Thanks

Chris



skumar
Beginner
273 Views

Hi Chris,

 

I realized that it was running on the login session from Cygwin. After attaching to the Node, I could not see this memory error any more.

skumar_0-1644947038655.png

 

However the GPU device option (-d GPU) cannot be used still.

 

Thanks

Saravana

 

ChrisB_Intel
Moderator
271 Views

I am not able to read the screen shot you attached, it is a bit to small. However, if you are using Cygwin to connect then you are connecting to the OneAPI devcloud, which does not have OpenVINO support. Cygwin is not available on the OpenVINO devcloud. Sounds like maybe you are thinking they are interchangeable?

Thanks

Chris



Reply