# Problem on deploying LPD model in python **URL:** \ **Category:** TAO Toolkit\ **Created:** [April 26, 2021, 1:11pm UTC](https://forums.developer.nvidia.com/t/problem-on-deploying-lpd-model-in-python/176294 "2021-04-26T13:11:38Z")\ **Posts on this page:** 6\ **Page:** 1
**Author:** ![3204657659](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@3204657659](https://forums.developer.nvidia.com/u/3204657659)\ **Post date:** [April 26, 2021, 1:11pm UTC](https://forums.developer.nvidia.com/t/problem-on-deploying-lpd-model-in-python/176294/1 "2021-04-26T13:11:39Z")
Hi, I am deploying LPD model in python but the results I got are wrong. The document says the output is four normalized bounding-box parameters (xc, yc, w, h) and confidence value per output class. I think the bounding-box parameters shouldn’t be bigger than 1 but most of my results are bigger than 1. I think perhaps my inputs are wrong or misunderstand something. I checked my inputs and the input images are satisified: - Color Images of resolution 640 X 480 X 3 (W x H x C)(RGB) - Channel Ordering of the Input: NCHW, where N = Batch Size, C = number of channels (3), H = Height of images (480), W = Width of the images (640) - Input scale: 1/255.0 The model is usa\_pruned.etlt downed from NGC and convertered to usa\_pruned\_int8.trt. ---
**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:** [April 26, 2021, 2:15pm UTC](https://forums.developer.nvidia.com/t/problem-on-deploying-lpd-model-in-python/176294/2 "2021-04-26T14:15:22Z")
Can `detectnet_v2 infer` or `deepstream` works well when you deploy the LPD model? ---
**Author:** ![3204657659](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@3204657659](https://forums.developer.nvidia.com/u/3204657659)\ **Post date:** [April 26, 2021, 2:41pm UTC](https://forums.developer.nvidia.com/t/problem-on-deploying-lpd-model-in-python/176294/3 "2021-04-26T14:41:22Z")
I didn’t try that. I directly deploy the LPD model in python. ---
**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:** [April 26, 2021, 3:51pm UTC](https://forums.developer.nvidia.com/t/problem-on-deploying-lpd-model-in-python/176294/4 "2021-04-26T15:51:36Z")
Refer to [Run PeopleNet with tensorrt - #21 by carlos.alvarez](https://forums.developer.nvidia.com/t/run-peoplenet-with-tensorrt/128000/21) ---
**Author:** ![3204657659](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@3204657659](https://forums.developer.nvidia.com/u/3204657659)\ **Post date:** [April 28, 2021, 2:21am UTC](https://forums.developer.nvidia.com/t/problem-on-deploying-lpd-model-in-python/176294/5 "2021-04-28T02:21:46Z")
It solved my problem! Thank you! ---
**Author:** ![TomNVIDIA](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/tomnvidia/32/14181_2.png) [@TomNVIDIA](https://forums.developer.nvidia.com/u/TomNVIDIA)\ **Post date:** [October 12, 2021, 4:23pm UTC](https://forums.developer.nvidia.com/t/problem-on-deploying-lpd-model-in-python/176294/6 "2021-10-12T16:23:50Z")
Closed on October 12, 2021, 4:23pm UTC