Error "Tensor image cannot be both input and output"

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

We have a custom model that gives output confidence and paf while takes image as input. We are getting this error:

nvinfer gstnvinfer.cpp:511:gst_nvinfer_logger:<primary_gie_classifier> NvDsInferContext[UID 1]:log(): Tensor image cannot be both input and output
2

Hi,

This error indicates that the same layer used as input and output.
It’s recommended to check the output layer name which is used for converting the TensorRT model first.

Thanks.