Hello. I started working with Deepstream. I working with deepstream-5.1 on Jetson TX2. I can use examples and custom networks with deepstream-app in console. How can i use models (such us trafficcamnet) with deepstream in my c++ project?
I didn’t get, you can run deepstream-app well, then it should work with your c++ projects, what’s the issue?
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)
Sorry if my question is incorrect. I have a video / image and I need to process it using a model (trafficcamnet). You using this model as an example in the deepstram-app.
I saw how to run model using deepstream-app, but I didn’t find any api or library so I could run the model directly in the c++ code.
• Hardware Platform (Jetson / GPU)-Jetson TX2
• DeepStream Version - 5.1
• JetPack Version - 4.5.1
• TensorRT Version - 7.1+ cuda10.2
Deepstream is based on Gstreamer pipeline, and nvinfer is responsible for consuming the DNN model via TensorRT, so you just need to build a gstreamer pipeline including nvinfer plugin, you can refer Gst-nvinfer — DeepStream 5.1 Release documentation
Also I think you need to get more familiar with gstreamer Basic tutorials
Thank you so much