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.

Object_detection_SSD sample error

Morishige__Akihito
458 Views

Hi, When I run the object_detection_SSD_sample, error is occured as follows.

[ ERROR ] Can't find output layer named bbox_pred

I don't know what should I do in this situation.

I used VOC0712_SSD300 to convert the IR model. I attached .xml file iused.

0 Kudos
4 Replies
Severine_H_Intel
Employee
458 Views

Dear Morishige, 

can you confirm that you ran the sample: object_detection_sample_ssd? The error you show is more typical from the sample: object_detection_sample​ which expects a layer called ​bbox_pred. 

Best, 

Severine

0 Kudos
Morishige__Akihito
458 Views

Thanks for reply. I can't  understand what [bbox_pred] means.

So what should I revise ? Where the typical bbox error occur ?

I ran the sample as follows. There is a error.

1. Download SSD model (downloader.py doesn't work correctly)

2. Convert caffemodel and deploy.prototxt to .xml by using model optimizer.

3. I ran the object_detection_ssd samle by using xml. 

0 Kudos
Severine_H_Intel
Employee
458 Views

Dear Morishige, 

I would like to reproduce your error, can you send me the link to the original model (if you took it from the internet)? Or add the .bin to the zip file along with the xml?

Best, 

Severine

0 Kudos
Morishige__Akihito
458 Views

I mistook the command. Sample run correctly.

Error was not object_detection_sample_ssd but object_detection_sample as you said.

Thank you for replying many times.

0 Kudos
Reply