How to do inference with "Preprocessed Tensor input mode" with nvinfer plugin

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

How can I do inference with “Preprocessed Tensor input mode” with nvinfer plugin?

In order to do inference with “Preprocessed Tensor input mode”, I thought I should edit config file.
But I couldn’t find the exact way if I read the document below.
https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_plugin_gst-nvinfer.html?highlight=nvinfer

Woud you please how to do inference with “Preprocessed Tensor input mode”?

3

please set input-tensor-from-meta to 1. please refer to sample \opt\nvidia\deepstream\deepstream-6.2\sources\apps\sample_apps\deepstream-preprocess-test

1 Like
5

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.