# Doing tlt inference only with tensorrt

**URL:** <https://forums.developer.nvidia.com/t/doing-tlt-inference-only-with-tensorrt/185039>\
**Category:** TAO Toolkit\
**Created:** [July 29, 2021, 2:40am UTC](https://forums.developer.nvidia.com/t/doing-tlt-inference-only-with-tensorrt/185039 "2021-07-29T02:40:26Z")\
**Posts on this page:** 1\
**Showing post:** 3

<div class="post-metadata">

**Author:** ![Morganh](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/morganh/32/9748_2.png) [@Morganh](https://forums.developer.nvidia.com/u/Morganh)\
**Post date:** [July 29, 2021, 6:56am UTC](https://forums.developer.nvidia.com/t/doing-tlt-inference-only-with-tensorrt/185039/3 "2021-07-29T06:56:54Z")

</div>

Refer to

> [@Inferring Yolo\_v3.trt model in python](https://forums.developer.nvidia.com/t/inferring-yolo-v3-trt-model-in-python/170418/):
>
> Hi i converted the yolov3-mobilenetv2 tlt model to trt engine with tlt-convertor. This trt engine giving good results with infering through tlt-infer and deepstream. Next I tried to infer the same TensorRT model via python standalone script.But when i infer with script, i got more false positives. Here i add my preprocesing and post processing script. can you ,let me know if any mistakes i need to correct here? Preprocessing steps def process\_image(self,arr): image\_resized=cv2.resize(a…

> [@How to run purpose built model Peoplenet on Jetson Nano in my own application?](https://forums.developer.nvidia.com/t/how-to-run-purpose-built-model-peoplenet-on-jetson-nano-in-my-own-application/127895/3):
>
> Thanks, for the reference. The code you referred has the post processing step telling how to parse the output from model. I implemented this in my application and when I run inference on a sample image, the confidence value coming from the model is 0 at all positions. With respect to preprocessing, I am multiplying the image with scale factor 0.00392156 and converting to RGB color space. I am attaching the source code here, kindly let me know if I miss anything. [inferPeopleNet.cpp](https://forums.developer.nvidia.com/uploads/short-url/hdwVKHkhREUeEwQ16Fl0yRUn2Gs.cpp) (8.0 KB)

> [@Run PeopleNet with tensorrt](https://forums.developer.nvidia.com/t/run-peoplenet-with-tensorrt/128000/6):
>
> In detectnet\_v2 pre-processing for 3 channels, please refer to below. a = np.asarray(img).astype(np.float32) a= a.transpose(2, 0, 1) / 255.0

---

_[View the full topic](https://forums.developer.nvidia.com/t/doing-tlt-inference-only-with-tensorrt/185039)._