Intel® Edge Software Hub
Get answers from community peers to your questions about building Edge Software Hub solutions for edge compute node.
Announcements
Welcome to the Intel Community! If you like the answer to your question, please mark it as 'Accepted Solution' to help others.

The Edge Software Vision Package for Red Hat Enterprise Linux is now available here.

Learn more about developing on Intel® Hardware and Software here.
401 Discussions

ESDQ AIbox deployment 1.2 Latency and Throughput metrics is null

AmandaLee
New Contributor I
1,081 Views

Dear Sir,

 

We run ESDQ AIbox 1.2 deployment configuration on TGL lake platform that have some fails.

1. On install step, it shown on AWS failed as below (this situation is same as ESDQ vision 6.0):

W: GPG error: https://dnw9lb6lzp2d8.cloudfront.net stable InRelease: The following signatures were invalid: EXPKEYSIG 68D644ABD2327D47 AWS Greengrass Master Key
E: The repository 'https://dnw9lb6lzp2d8.cloudfront.net stable InRelease' is not signed.

2. Latency and Throughput metrics are null in the ESDQ HTML report page. It is look like I need to download yolo-v3-tf.xml for test procedure. Is there have any guideline for how to do?

Screenshot from 2022-03-11 11-08-41.png

 

Best regards,

Amanda

Labels (1)
0 Kudos
1 Solution
AmandaLee
New Contributor I
882 Views

Hi Lim Xiang Yang,

 

The report data is available after adding root-permission("-u 0") to Yolov3Tests.sh Line58 as below:

docker run -it -d -u 0 --name $containerName -v /tmp/.X11-unix:/tmp/.X11-unix -e DISPLAY=$DISPLAY -v ~/Downloads:/mnt --device /dev/dri:/dev/dri --group-add=$(stat -c "%g" /dev/dri/render*) --rm $docker_pull_models /bin/bash

The result:

 Screenshot from 2022-03-18 09-49-30.png

Many thanks for your kindly help!

 

Regards,

Amanda

View solution in original post

0 Kudos
6 Replies
Xiang_Intel
Moderator
999 Views

Hi Amanda,

 

May I know if it's possible to share me with the esdqReport.zip file that is generated after the run to help me further align with my validation?

In the meantime, for the AWS,  you can deselect it in the customize menu.

Xiang_Intel_0-1647225359282.png

 

Thanks and regards,

Lim Xiang Yang

0 Kudos
AmandaLee
New Contributor I
968 Views

Hi Lim Xiang Yang,

 

Please find the attached file for the report.

For the AWS, can I modify the local file for deselect it?

 

Best Regards,

Amanda

0 Kudos
Xiang_Intel
Moderator
936 Views

Hi Amanda,

 

To deselect it locally here is the step you can do, 

1. Remove the AWS apt file

sudo rm -rf /etc/apt/sources.list.d/greengrass.list

2. Edit the configuration file to deselect AWS. Change the highlighted part from true to false

Xiang_Intel_0-1647248630528.png

3. Rerun the setup

 

As for the yolov3, can you try the following command to pull the container and then run the test again?

sudo docker pull synnexgrp/openvino:2021.4_developer_models

 

Thanks and regards,

Lim Xiang Yang

 

0 Kudos
AmandaLee
New Contributor I
923 Views

Hi Lim Xiang Yang,

Thanks for your kind assistance. The AWS item is deselected.

Screenshot from 2022-03-15 10-10-23.png

But for the yolov3, "synnexgrp/openvino:2021.4_developer_models" docker container is already pulling out before test procedure. For throughput test item, where can I find the detail step to generate test data and could I do it manually?

Screenshot from 2022-03-15 10-05-56.png

Thanks and regards,

Amanda

0 Kudos
Xiang_Intel
Moderator
906 Views

Hi Amanda,

 

May I know what is the output if you run the following command? Because from the log file provided, it seems like it has an issue copying the yolov3 model file to the directory.

ls -la / | grep mnt

 

Thanks and regards,

Lim Xiang Yang

0 Kudos
AmandaLee
New Contributor I
883 Views

Hi Lim Xiang Yang,

 

The report data is available after adding root-permission("-u 0") to Yolov3Tests.sh Line58 as below:

docker run -it -d -u 0 --name $containerName -v /tmp/.X11-unix:/tmp/.X11-unix -e DISPLAY=$DISPLAY -v ~/Downloads:/mnt --device /dev/dri:/dev/dri --group-add=$(stat -c "%g" /dev/dri/render*) --rm $docker_pull_models /bin/bash

The result:

 Screenshot from 2022-03-18 09-49-30.png

Many thanks for your kindly help!

 

Regards,

Amanda

0 Kudos
Reply