# How to deploy custom trained Mask RCNN on Jetson Nano?

**URL:** <https://forums.developer.nvidia.com/t/how-to-deploy-custom-trained-mask-rcnn-on-jetson-nano/210831>\
**Category:** Jetson Nano\
**Tags:** computer-vision-cv, cuda, python, jetson-inference, camera\
**Created:** [April 11, 2022, 7:57am UTC](https://forums.developer.nvidia.com/t/how-to-deploy-custom-trained-mask-rcnn-on-jetson-nano/210831 "2022-04-11T07:57:33Z")\
**Posts on this page:** 7\
**Page:** 1

<div class="post-metadata">

**Author:** ![muhammadsalam557](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@muhammadsalam557](https://forums.developer.nvidia.com/u/muhammadsalam557)\
**Post date:** [April 11, 2022, 7:57am UTC](https://forums.developer.nvidia.com/t/how-to-deploy-custom-trained-mask-rcnn-on-jetson-nano/210831/1 "2022-04-11T07:57:33Z")

</div>

Hi, I have trained MASKRCNN on a custom dataset. I am not understanding how to deploy this trained model on Nvidia Jetson Nano.

Kindly help me with authentic sources.

---

<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:** [April 11, 2022, 1:56pm UTC](https://forums.developer.nvidia.com/t/how-to-deploy-custom-trained-mask-rcnn-on-jetson-nano/210831/2 "2022-04-11T13:56:25Z")

</div>

Hi @muhammadsalam557,

Welcome to the NVIDIA Developer forums!. Your question belongs in the Jetson Nano Category. I will move it over for you.

Regards,  
Tom K

---

<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:** [April 12, 2022, 3:13am UTC](https://forums.developer.nvidia.com/t/how-to-deploy-custom-trained-mask-rcnn-on-jetson-nano/210831/4 "2022-04-12T03:13:41Z")

</div>

Hi,

May I know the model format of your Mask RCNN?  
If it is trained with TensorFlow 1.15.x, we have an example to run it with TensorRT as below:  
[https://github.com/NVIDIA/TensorRT/tree/main/samples/sampleUffMaskRCNN](https://github.com/NVIDIA/TensorRT/tree/main/samples/sampleUffMaskRCNN)

Thanks.

---

<div class="post-metadata">

**Author:** ![muhammadsalam557](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@muhammadsalam557](https://forums.developer.nvidia.com/u/muhammadsalam557)\
**Post date:** [April 12, 2022, 8:47am UTC](https://forums.developer.nvidia.com/t/how-to-deploy-custom-trained-mask-rcnn-on-jetson-nano/210831/5 "2022-04-12T08:47:42Z")

</div>

Thank you

---

<div class="post-metadata">

**Author:** ![muhammadsalam557](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@muhammadsalam557](https://forums.developer.nvidia.com/u/muhammadsalam557)\
**Post date:** [April 12, 2022, 8:48am UTC](https://forums.developer.nvidia.com/t/how-to-deploy-custom-trained-mask-rcnn-on-jetson-nano/210831/6 "2022-04-12T08:48:26Z")

</div>

I have used tensorflow==1.13.1.

---

<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:** [April 18, 2022, 2:28am UTC](https://forums.developer.nvidia.com/t/how-to-deploy-custom-trained-mask-rcnn-on-jetson-nano/210831/7 "2022-04-18T02:28:21Z")

</div>

Hi,

Do you have a .pb format model from TensorFlow 1.x?  
If yes, you should be able to run it with TensorRT with a similar flow as the tutorial: .pb - .uff - .trt

Thanks.

---

<div class="post-metadata">

**Author:** ![system](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/system/32/68080_2.png) [@system](https://forums.developer.nvidia.com/u/system)\
**Post date:** [May 11, 2022, 3:45am UTC](https://forums.developer.nvidia.com/t/how-to-deploy-custom-trained-mask-rcnn-on-jetson-nano/210831/9 "2022-05-11T03:45:50Z")

</div>

Closed on May 11, 2022, 3:45am UTC

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.