How to save inference results to file in deepstream

Please provide complete information as applicable to your setup.

**• Hardware Platform (Jetson / GPU)jetson
**• DeepStream Version5.1
**• JetPack Version (valid for Jetson only)4.6
**• TensorRT Version7.1
• NVIDIA GPU Driver Version (valid for GPU only)
I now have a custom classification model, and I want to classify each frame of the input image and save the classification result to a file.

1 please refer to deepstream-app, it can save output to file after inference, the path is:
/opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-app
start command is like this: deepstream-app -c …/…/…/…/samples/configs/deepstream-app/source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt
you can enable [sink2], set type to 3. here are some parameters description : Gst-nvinfer — DeepStream 6.3 Release documentation

2 use your model in the configure file, and set your model as primary gie. please refer to this link:

Thank you very much

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