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

Inference problem of Openvino with ssd_mobilenet_v1_coco

hellow, i have some question about the inference result of openvino IR

I download the ssd_mobilenet_v1_coco_2018_01_28 from  https://software.intel.com/en-us/articles/OpenVINO-Using-TensorFlow

than I convert the download model to openvino IR format using the following command 

python mo_tf.py --input_model <frozen_inference_graph.pb model path> --tensorflow_use_custom_operations_config <openvino path>\deployment_tools\model_optimizer\extensions\front\tf\ssd_support.json --tensorflow_object_detection_api_pipeline_config <pipeline.config path> --input_shape [1,300,300,3]

I convert the model successfully

however when I inference an image using the IR, the result is different from the tensorflow result using frozen_inference_graph.pb

for example, when I inference an image using frozen_inference_graph.pb , I find out all the detected objects with score larger than 30%:tensorflow_result.png

however,when I inference an image using openvino IR and get detected objects with scores larger than 30%, it come out many unexpected boxes:

openvino_result.png

although the 2 objects with largest scores (70%, 62%) is the same with tensorflow result(see the following picture), there are many unexpected boxes with scores about 51%~52%

openvion_result with_largest_2_scores.png

what I want to know is that is my result is correct?

if I set scores threshold to filter detected objects, I will get many unexpected results, how can I solve it?

is anybody can help? thank you vary much!

0 Kudos
2 Replies
Highlighted
Beginner
42 Views

is there anyone can give me some help?

0 Kudos
Highlighted
Employee
42 Views

Dear Liang, JianWei,

Most likely you did not pass in proper pre-processing switches into Model Optimizer.  Please review this IDZ post. Actually we provide mean and scale values for the most popular models (including mobilenet) on this page:

http://docs.openvinotoolkit.org/latest/_docs_MO_DG_prepare_model_convert_model_Convert_Model_From_Te...

Hope it helps !

Thanks,

Shubha

 

0 Kudos