Community
cancel
Showing results for 
Search instead for 
Did you mean: 
Highlighted
Beginner
82 Views

Model performance reduced( not detecting properly ) on NCS2, after conversion from TensorFlow.

Hi,

I am running a SSD MobileNet V2 model trained using TensorFlow object detection API on a custom data-set.

I have attached the output of same image with and without NCS2. Apparently, the model performance seems to be reduced after the conversion. I am not aware of the problem. 

The OpenVINO version I am using is 2019.R3.

Below is the code I am using to convert from tensorflow to IR formats.

sudo python3 mo.py --framework tf --input_model Catering_v2_3C.pb --batch 12 --reverse_input_channels --tensorflow_object_detection_api_pipeline_config pipeline.config --tensorflow_use_custom_operations_config extensions/front/tf/ssd_support_api_v1.14.json --output=detection_classes,detection_scores,detection_boxes,num_detections --datatype  FP32

I am completely open to any suggestions.

kindly, help me to get past this hurdle.

Thank you, regards.

0 Kudos
2 Replies
Highlighted
34 Views

Hi dilip96,


Thanks for reaching out.


When developing for Intel® Neural Compute Stick 2 (Intel® NCS 2) you want to make sure that you use a model that uses FP16 precision. Hence, I would suggest you try using the --datatype FP16 parameter in your Model Optimizer conversion command.


More information is available at the following pages:

https://software.intel.com/content/www/us/en/develop/articles/should-i-choose-fp16-or-fp32-for-my-de...

https://docs.openvinotoolkit.org/latest/openvino_docs_MO_DG_prepare_model_convert_model_tf_specific_...


Also, I would encourage you to try out Intel® Distribution of OpenVINO™ Toolkit version 2020.4, which is a vastly improved version with the latest features and leading performance.


Regards,

Randall


0 Kudos
Highlighted
6 Views

Hi dilip96,


If you need any additional information, please submit a new question as this thread will no longer being monitored.


Regards,

Randall.


0 Kudos