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

**URL:** <https://forums.developer.nvidia.com/t/how-to-get-the-input-of-nvinfer-in-deepstream-python-app/214559>\
**Category:** DeepStream SDK\
**Tags:** opencv, python\
**Created:** [May 16, 2022, 12:01pm UTC](https://forums.developer.nvidia.com/t/how-to-get-the-input-of-nvinfer-in-deepstream-python-app/214559 "2022-05-16T12:01:34Z")\
**Posts on this page:** 1\
**Showing post:** 7

<div class="post-metadata">

**Author:** ![kesong](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/kesong/32/101255_2.png) [@kesong](https://forums.developer.nvidia.com/u/kesong)\
**Post date:** [May 18, 2022, 9:34am UTC](https://forums.developer.nvidia.com/t/how-to-get-the-input-of-nvinfer-in-deepstream-python-app/214559/7 "2022-05-18T09:34:42Z")

</div>

Hope is helps for inference accuracy:

> [@DeepStream SDK FAQ](https://forums.developer.nvidia.com/t/deepstream-sdk-faq/80236/21):
>
> [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 training and inference outside DeepStream 15.2 nvinfer When deploying a ONNX model to DeepStream with nvinfer plugin, confirm below nvinfer parameters are set correctly to align with the corresponding settings in Training 15.2.1 Input scale & offset 1). net-scale-factor = 2). offsets The usage of t…

---

_[View the full topic](https://forums.developer.nvidia.com/t/how-to-get-the-input-of-nvinfer-in-deepstream-python-app/214559)._