Compilation issues of custom model in Deepstream

Our team encountered few technical issues during custom model development and compilation in DeepStream.

Any technical help in solving these issues would be highly appreciated.

Issues encountered while running the custom SSD_Inception_V2 model in Deepstream

  1. Engine file not able to create for SSD_Inception_V2 because the output layer names were not getting matched with NMS and NMS_1.

Issues encountered while running custom SSD_Inception_V3

  1. Free pointer error as bboxes was not found while running. The program automatically stopped after processing 3-4 frames.

Issues encountered while running custom SSD_Mobilenet Caffemodel

  1. Parameter mismatch was happening while creating engine file from caffemodel.

Thank you
Rama

Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

Dear kesong,

PFB the required details

• Hardware Platform (Jetson / GPU) - Jetson TX2
• DeepStream Version - Deepstream 4.0
• JetPack Version (valid for Jetson only) - Jetpack 4.3
• TensorRT Version - TnsorRT 6.0
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs) -

Thank you
Rama Reddy R

Seems the DeepStream version is old. Can you upgrade to DS 5.1 and then check if still have those issues?

We have tried with Deepstream 5.1 as well.

In Deepstream 5.1, the sample ssd model was working fine but we still faced the problem with the output layer names while converting our custom model to engine file.

Output layer name is depend on your model. Please check your model and ensure set right name to DS.