Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.
6406 Discussions

[Error] Classification_sample run failure by using -d MYRIAD but -d GPU or -d CPU

Bill_Sung
Beginner
395 Views

Hi Sir,

    I use "classification_sample" to run IR of DenseNet_121 models to have failure message by use -d MYRIAD but it's good by -d GPU or -d CPU.

    My OS is Ubuntu 16.04 LTS, I think Movidius that is ready and plugged in well because message present start inference.

    Do you have saw such fail state  and have you any suggest or patch for that? Thanks.

BR

Bill

-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

 **** Please refer below message of command and result. *****

-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------

SKLU-IE1:~/workarea/intel/VINOtoolkit/OV201/Caffe_DenseNet_121/FP16$ classification_sample -m DenseNet_121.xml -i ~/intel/computer_vision_sdk/deployment_tools/demo/car.png -d MYRIAD -pp ~/intel/computer_vision_sdk/deployment_tools/inference_engine/lib/ubuntu_16.04/intel64/ 
[ INFO ] InferenceEngine: 
    API version ............ 1.2
    Build .................. 13911
[ INFO ] Parsing input parameters
[ INFO ] Loading plugin

    API version ............ 1.2
    Build .................. 13911
    Description ....... myriadPlugin
[ INFO ] Loading network files:
    DenseNet_121.xml
    DenseNet_121.bin
[ INFO ] Preparing input blobs
[ WARNING ] Image is resized from (787, 259) to (224, 224)
[ INFO ] Batch size is 1
[ INFO ] Preparing output blobs
[ INFO ] Loading model to the plugin
[ INFO ] Starting inference (1 iterations)
E: [xLink] [         0] dispatcherWaitEventComplete:693    waiting is timeout, sending reset remote event
E: [ncAPI] [         0] ncFifoReadElem:2810    Packet reading is failed.
info: /home/jenkins/workspace/ie-plugins/master/centos7-myriad-host/src/common/components/XLink/shared/XLink.c:1157: E: [ncAPI] [         0] ncFifoDestroy:2602    Failed to write to fifo before deleting it!
info: /home/jenkins/workspace/ie-plugins/master/centos7-myriad-host/src/common/components/XLink/shared/XLink.c:1157: info: /home/jenkins/workspace/ie-plugins/master/centos7-myriad-host/src/common/components/XLink/shared/XLink.c:1157: info: /home/jenkins/workspace/ie-plugins/master/centos7-myriad-host/src/common/components/XLink/shared/XLink.c:1092: info: /home/jenkins/workspace/ie-plugins/master/centos7-myriad-host/src/common/components/XLink/shared/XLink.c:1092: info: /home/jenkins/workspace/ie-plugins/master/centos7-myriad-host/src/common/components/XLink/shared/XLink.c:1092: info: /home/jenkins/workspace/ie-plugins/master/centos7-myriad-host/src/common/components/XLink/shared/XLink.c:1092: info: /home/jenkins/workspace/ie-plugins/master/centos7-myriad-host/src/common/components/XLink/shared/XLink.c:1363: [ ERROR ] Failed to read output from FIFO: NC_ERROR
 

0 Kudos
1 Reply
Monique_J_Intel
Employee
395 Views

Hi Bill,

I've tried to reproduce your issue and I couldn't but I did achieve success with the NCS2 stick on Ubuntu 16.04.3 with running densenet-121 on classification sample. However, I did run it with OpenVINO R4. I highly recommend you upgrade to the latest release which is R4 and try to run the classification sample again. Let me know if that resolves the issue.

Kind Regards,

Monique Jones

0 Kudos
Reply