Image Patching in Deepstream Python

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU): Jetson Nano B01
• DeepStream Version: 5.1
• JetPack Version (valid for Jetson only):4.5.1
• TensorRT Version:7.1.3
• Issue Type: question


My question is how to apply image patching and convert the frame to multiple images in deepstream python script. I have a custom YOLOV4 object detector, and instead of creating a simple pipeline in which the frame (from CSI camera) will be sent entirely to the nvinfer tensorrt engine, I want first to extract multiple patches from the image and send all these sub-images through the pipeline.

It would be awesome if you could assist me with this question. Thanks.

Please upgrade to DS 6.0. Can below plugin help in you use case by setting ROI in preprocess plugin?

Gst-nvdspreprocess (Alpha) — DeepStream 6.0 Release documentation (

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