# How to use tensorflow model in deepstream python

**URL:** <https://forums.developer.nvidia.com/t/how-to-use-tensorflow-model-in-deepstream-python/146441>\
**Category:** DeepStream SDK\
**Created:** [August 12, 2020, 2:01am UTC](https://forums.developer.nvidia.com/t/how-to-use-tensorflow-model-in-deepstream-python/146441 "2020-08-12T02:01:50Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![pijebom737](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@pijebom737](https://forums.developer.nvidia.com/u/pijebom737)\
**Post date:** [August 12, 2020, 2:01am UTC](https://forums.developer.nvidia.com/t/how-to-use-tensorflow-model-in-deepstream-python/146441/1 "2020-08-12T02:01:50Z")

</div>

Hi

I have a pb file from tensorflow

I want to know how can I use it in deepstream python app deepstream\_testx

Please provide detail steps.

Thank you.

---

<div class="post-metadata">

**Author:** ![AastaLLL](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/aastalll/32/14043_2.png) [@AastaLLL](https://forums.developer.nvidia.com/u/AastaLLL)\
**Post date:** [August 12, 2020, 4:31am UTC](https://forums.developer.nvidia.com/t/how-to-use-tensorflow-model-in-deepstream-python/146441/3 "2020-08-12T04:31:20Z")

</div>

Hi,

Please convert the frozen model into either _uff_ or _onnx_ format first.  
Then you can update the configure file in Deepstream python app for your model directly.  
For example:

> <https://github.com/NVIDIA-AI-IOT/deepstream_python_apps/blob/master/apps/deepstream-test1/dstest1_pgie_config.txt>

Thanks.

---

<div class="post-metadata">

**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, 4:16pm UTC](https://forums.developer.nvidia.com/t/how-to-use-tensorflow-model-in-deepstream-python/146441/5 "2021-10-12T16:16:56Z")

</div>

Closed on October 12, 2021, 4:16pm UTC


