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.
6503 Discussions

Upcore Plus X Low FPS performance on MYRIAD

semta_ai
Beginner
980 Views

Hi,

I am currently working on tensorflow object detection models.

I downloaded SSD MobileNet V1 COCO* from

https://docs.openvinotoolkit.org/latest/openvino_docs_MO_DG_prepare_model_convert_model_Convert_Model_From_TensorFlow.html

Then I used model optimizer to convert it  with its supported json file, pipeline config etc. Everything is just fine until this step. I got xml and bin files.

I send these files to my Upcore Plus. While I am running python- sample object detection I faced with low FPS on MYRIAD. When I choose -d CPU I got about 1.2 FPS. However in -d  MYRIAD  I got 0.26 FPS.

I did everything in your documentations. What I missed here?

0 Kudos
4 Replies
Rizal_Intel
Moderator
953 Views

Hi Semta,

 

This should be within expectation as the CPU is more powerful compared to the Neural Compute Stick 2.

 

Regards,

Rizal

 

0 Kudos
semta_ai
Beginner
946 Views

Hi Rizal_Intal,

Thank you for your answering. 

I am beginner in these fields. I do not have a roadmap. Do you have any suggestion for this problem. I need around 10 FPS on Upcore Plus X. Should I use different model, library or optimizer? Should I focus on CPU optimization?

Regards,

 

0 Kudos
Rizal_Intel
Moderator
937 Views

Hi Semta,

 

The easiest would be to change the model to something else that is less compute heavy.

The popular yolo model (some versions are available as Intel pretrained model) is one of the alternative for a fast model.

 

Regards,

Rizal


0 Kudos
Munesh_Intel
Moderator
923 Views

Hi Semta,

This thread will no longer be monitored since we have provided a suggestion. If you need any additional information from Intel, please submit a new question. 


Regards,

Munesh


0 Kudos
Reply