problem with MobileNetV2 + SSD and vehicle-license-plate-detection-barrier-0123

[AliRoostae]

Hi, I trained a model of type "MobileNetV2 + SSD" with 2 labels from same labels of "vehicle-license-plate-detection-barrier-0123" on a custom personal dataset of vehicles using TensorFlow Ver 2.9 and optimized it.
This model works correctly in Object Detection but it has some errors when I use "security_barrier_camera_demo" binary.
error message is:

MFX: Can't initialize session
[ INFO ] OpenVINO
[ INFO ] version: 2022.1.0
[ INFO ] build: 2022.1.0-7019-cdb9bec7210-releases/2022/1
[ INFO ] Reading model: my_ssd_mobilenet_v2-2022-8-12-2Class.xml
[ INFO ] Model name: my_ssd_mobilenet_v2-2022-8-12-2Class
[ INFO ] Inputs:
[ INFO ] input_tensor, u8, {1,300,300,3}, [N,H,W,C]
[ INFO ] Outputs:
[ INFO ] StatefulPartitionedCall/Identity, f32, {1,1,100,7}, [...]
[ ERROR ] unexpected ProposalCount

Any help is greatly appreciated.

[Zulkifli_Intel]

Hi Ali Roostae,

Thank you for reaching out to us.

Security Barrier Camera C++ Demo only supports these models:

• license-plate-recognition-barrier-0001
• license-plate-recognition-barrier-0007
• vehicle-attributes-recognition-barrier-0039
• vehicle-attributes-recognition-barrier-0042
• vehicle-license-plate-detection-barrier-0106
• vehicle-license-plate-detection-barrier-0123

 Sincerely,

Zulkifli 

[Zulkifli_Intel]

Hi Roostae,

Thank you for your question. If you need any additional information from Intel, please submit a new question as this thread is no longer being monitored.

Sincerely,

Zulkifli