Deploy PyTorch on DeepStream 5.0

Accelerated Computing Intelligent Video Analytics DeepStream SDK
, ,
1

Good day nvidia developer community
I’m trying to deploy my pytorch model (MTCNN Detection) on deepstream 5.0, is there an example I can refer to?

Setup Information:
• Hardware Platform: GPU
• DeepStream Version: 5.0
• TensorRT Version: 7
• NVIDIA GPU Driver Version: 440

3

Hi,

First, please convert your model into onnx format.
Then you can refer to following detection sample for the information:
/opt/nvidia/deepstream/deepstream-5.0/sources/objectDetector_FasterRCNN
/opt/nvidia/deepstream/deepstream-5.0/sources/objectDetector_SSD
/opt/nvidia/deepstream/deepstream-5.0/sources/objectDetector_Yolo

Thanks.