# Zero copy with tensorflow

**URL:** <https://forums.developer.nvidia.com/t/zero-copy-with-tensorflow/79508>\
**Category:** Jetson AGX Xavier\
**Created:** [August 7, 2019, 11:57am UTC](https://forums.developer.nvidia.com/t/zero-copy-with-tensorflow/79508 "2019-08-07T11:57:12Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![jetsonxvr](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@jetsonxvr](https://forums.developer.nvidia.com/u/jetsonxvr)\
**Post date:** [August 7, 2019, 11:57am UTC](https://forums.developer.nvidia.com/t/zero-copy-with-tensorflow/79508/1 "2019-08-07T11:57:12Z")

</div>

Hi there,

I use some network which requires a lot of CPU \<-\> GPU transfers. AFAIK, CPU and GPU have unified (common) memory, so using a zero-copy technique is possible.

I’ve read a topic [url][https://devtalk.nvidia.com/default/topic/996820/jetson-tx1/zero-copy-for-tensorflow/[/url]](https://devtalk.nvidia.com/default/topic/996820/jetson-tx1/zero-copy-for-tensorflow/%5B/url%5D) about TX1, in which the answer states that a modification to a tensorflow sources is needed.  
This article [url][http://arrayfire.com/zero-copy-on-tegra-k1/[/url]](http://arrayfire.com/zero-copy-on-tegra-k1/%5B/url%5D) gives a drection in what modifications should be done.

But I already have a specific implementation by nvidia included in JetPack (I use v4.2).

Does this version use zero-copy?  
Is it planned to implement such an improvement in JetPack?  
Is it possible to get sources to modify it enabling zero-copy?

Does anyone succeed in implementing zero-copy on Jetson AGX Xavier?

Thanks in advance for answers.

---

<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 8, 2019, 8:16am UTC](https://forums.developer.nvidia.com/t/zero-copy-with-tensorflow/79508/2 "2019-08-08T08:16:14Z")

</div>

Hi,

Sorry that the implementation must be applied in the TensorFlow source.  
It’s recommended to file this request to the TensorFlow team directly.

For an alternative, you can try our Deepstream SDK which implements zero-copy technique between camera and inference instead:  
[url][https://developer.nvidia.com/deepstream-sdk[/url]](https://developer.nvidia.com/deepstream-sdk%5B/url%5D)

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 18, 2021, 6:24pm UTC](https://forums.developer.nvidia.com/t/zero-copy-with-tensorflow/79508/3 "2021-10-18T18:24:11Z")

</div>

Closed on October 18, 2021, 6:24pm UTC


