Community
cancel
Showing results for 
Search instead for 
Did you mean: 
idata
Community Manager
392 Views

Movidius NCS2 low inference accuracy problem?

I have a dataset that I am training with Tensorflow's object detection model (SSD Mobilenet v1) and I am experiencing significant accuracy loss when converting for the movidius stick using the model_optimizer included with the OpenVINO SDK

 

The same dataset performs well when trained with the tiny yolov3 model in keras but with the NCS2 the boxes are giving out a lot of false positives and the boxes around the objects are too big.

 

Has anyone experienced something similar?

0 Kudos
1 Reply
idata
Community Manager
86 Views

Hi @robert_osmosis

 

I see that someone had responded to your response on the forums here. Please let me know if you still need help!

 

Best Regards,

 

Sahira
Reply