• Hardware Platform (Jetson / GPU) RTX 3060 • DeepStream Version deepstream:5.1-21.02-devel • TensorRT Version 7.2.2-1+cuda11.1 • NVIDIA GPU Driver Version (valid for GPU only) 510.60.02 • Issue Type( questions, new requirements, bugs) Question I am trying to extract the input of sgie-classifie…

Yes, nvdspreprocess will prepare the input tensor. Can you add bindings for the NvDsPreProcessBatchMeta by yourself?

you could use a probe similar to this blog. [image] Xavier NX-DeepStream 5.0 #4 - Handling Primary, Secondary Inference Results Blog about NVidia Jetson Nano, TX2.

Thank you for the help, but this blog-post tells us how to get the object’s metadata. I want to grab the input of nvinfer, e.g. what is the actual image going as the input of sgie

Can you share why you need dump the input of nvinfer?

My sgie is not giving the required accurate results, so I just wanted to check what is it’s input? how the images are preprocessed just before going to sgie-nvinfer.

Hope is helps for inference accuracy: [image] DeepStream SDK FAQ DeepStream SDK [DSx_All_App] Debug Tips for DeepStream Accuracy Issue Ensure the image pre-process before inference aligns with the training pre-process. 15.1 Confirm your model has got good accuracy in tr…

Thank you, setting these parameters improves performance a lot… But I still want to know if there is a way to extract the input of nvinfer or it is not possible in python right now?

[image] curious_cat: you could use a probe similar to this blog. NVIDIA Jetson and Raspberry Pi: Xavier NX-DeepStream 5.0 #4 - Handling Primary, Secondary Inference Results It gives segmentation fault when I try to convert RGBA to BGR using opencv

It worked when I changed mem type of nvvidconv to Unified CUDA Memory.

How are you going with this? I’m trying to test the same. My model was trained using pytorch normalization and resize. So I’d like to verify the pre-processing nvinfer is doing is equivalent. The nvinfer module includes normalization and I think also resizing by default. This happens inside the…

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

How to get the input of nvinfer in deepstream python app?

Accelerated Computing Intelligent Video Analytics DeepStream SDK

kesong May 18, 2022, 9:34am 7

Hope is helps for inference accuracy:

Topic		Replies	Views
How to get input (and output) of model inside nvinfer in Python - Correct way to probe nvinfer? DeepStream SDK python , deepstream	15	1616	February 6, 2024
How to get input fed to nvinfer with Python bindings DeepStream SDK	1	445	May 4, 2023
Extracting Processed Frames After Inference in Nvidia DeepStream Efficiently DeepStream SDK gstreamer , python , deepstream	9	473	February 12, 2025
How to append DeepStream Metadata in Python without using Streammux / nvinfer for parallel branch? DeepStream SDK	20	1026	March 12, 2024
Get different results between .onnx python and .engine nvinfer DeepStream SDK	7	631	September 22, 2023
How to do inference with "Preprocessed Tensor input mode" with nvinfer plugin DeepStream SDK deepstream61	1	507	May 29, 2023
Create a simple replacement of gst-nvinfer DeepStream SDK	7	1173	August 31, 2021
Nvdspreprocess + nvinfer(unet) ，model output error DeepStream SDK deepstream	8	690	May 11, 2024
Image processing before preprocessing in nvinfer DeepStream SDK jetson , deepstream	4	173	December 30, 2024
Multiple "nvinfer" elements: More detailed Python Binding example application DeepStream SDK camera , jetson-inference , gstreamer	1	446	December 16, 2020

How to get the input of nvinfer in deepstream python app?

Related topics