Custom classification model in Gstreamer pipeline
Hi All, I need an advice (and/or help with) creating a simple application on Jetson Nano 2 Gb with DeepStream SDK 5.1.
I have a PyTorch classification model converted to ONNX. This is ResNet18 based custom trained binary classification that I would like to implement to the whole input image. No object detection is required.
I was able to convert it to TRT engine but cannot figure out how to connect it to NVINFER layer.
All examples that I can find deal with primary detection and secondary classification. I can substitute the model in config.txt file with my engine file but I do not understand what parameters should be changed to tell that I need to classify the whole frame and there will be two classes.
Need your help to figure it out.
- Company Name: Ant Robotics
- Location: Both