Deepstream default model for object detection

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) : NVIDIA GeForce RTX 3090
• DeepStream Version : 6.3
• JetPack Version (valid for Jetson only)
• TensorRT Version : 12.2
• NVIDIA GPU Driver Version (valid for GPU only) : 535.104.05
• 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)

I want to ask what is object detection model name that used in deepstream-test1 and deepstream-test2

in below github

I can see from below article it is ResNet10 and ResNet18 and these model used for classification not detection
https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_sample_configs_streams.html

Appreciate your help

The model for the primary detector (/opt/nvidia/deepstream/deepstream-6.3/samples/models/Primary_Detector/resnet10.caffemodel) is a “a DetectNet_v2 model with Resnet10 as backbone”, There are some discussion on this topic Resnet10 “primary detector” - Intelligent Video Analytics / DeepStream SDK - NVIDIA Developer Forums.

The several sgie used in deepstream-test2 (Secondary_CarColor/Secondary_CarMake/Secondary_VehicleTypes) are all for classification.

1 Like

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.