Intel® Distribution of OpenVINO™ Toolkit
Community support and discussions about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all things computer vision-related on Intel® platforms.
5774 Discussions

Ensemble learning of deep CNN models using OpenVINO

vkana3
Beginner
465 Views

Hi

I have created four different pre-trained models on a dataset and by averaging their scores, I have received an extrodinary performance.

But,  As I converted all those models to IR format, Can anyone tell me how to perform inference by taking the averge of all scores.!!

Thank you

 

0 Kudos
1 Solution
Munesh_Intel
Moderator
429 Views


Hi Vishnu,


As of now, we don’t have examples that demonstrate ensemble method.

I would suggest you follow the two links below regularly for more updates on the latest in AI from Intel.

https://www.intel.com/content/www/us/en/artificial-intelligence/research.html

https://twitter.com/IntelAIResearch


Regards,

Munesh


View solution in original post

4 Replies
Munesh_Intel
Moderator
450 Views

Hi Vishnu,


The following article, “Inference Performance Boost with Seldon on Intel® Xeon® Scalable Processors”, contains relevant information on using ensemble method.

https://www.intel.com/content/www/us/en/artificial-intelligence/posts/inference-performance-boost-wi...


Regards,

Munesh.


vkana3
Beginner
447 Views

Hi @Munesh_Intel 

Thank you for sharing it, Can please give me additional video resources involving sample examples and so on.!?

Munesh_Intel
Moderator
430 Views


Hi Vishnu,


As of now, we don’t have examples that demonstrate ensemble method.

I would suggest you follow the two links below regularly for more updates on the latest in AI from Intel.

https://www.intel.com/content/www/us/en/artificial-intelligence/research.html

https://twitter.com/IntelAIResearch


Regards,

Munesh


Munesh_Intel
Moderator
413 Views

Hi Vishnu,


This thread will no longer be monitored since this issue has been resolved. If you need any additional information from Intel, please submit a new question.


Regards,

Munesh


Reply