I have found inconsistent results in Deepstream with a model and engine I have trained using the TLT with the Caltech Birds dataset. I have noticed that with this engine and configuration that deepstream is not making detections anywhere but immediately close to the camera.
I’d like to ask the opinion of others here about the issue I have linked some short clips showing how this is performing.
Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
Jetson TX1 - for inference.
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• 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)
Reproduction can be done through using the same config and engines that I am using.
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)
Standard flash of Jetson to latest jetpack.
EDIT: What kinds of parameters in DeepStream can be configured to produce detection results from afar?