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.

Upcore Plus X Low FPS performance on MYRIAD

semta_ai
Beginner
273 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_Mode...

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
246 Views

Hi Semta,

 

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

 

Regards,

Rizal

 

semta_ai
Beginner
239 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,

 

Rizal_Intel
Moderator
230 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


Munesh_Intel
Moderator
216 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


Reply