# DL4J for wear OS

**URL:** <https://community.konduit.ai/t/dl4j-for-wear-os/651>\
**Category:** Feature Request\
**Created:** [June 25, 2020, 1:19pm UTC](https://community.konduit.ai/t/dl4j-for-wear-os/651 "2020-06-25T13:19:00Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![pengyuan-zhou](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/pengyuan-zhou/32/357_2.png) [@pengyuan-zhou](https://community.konduit.ai/u/pengyuan-zhou)\
**Post date:** [June 25, 2020, 1:19pm UTC](https://community.konduit.ai/t/dl4j-for-wear-os/651/1 "2020-06-25T13:19:00Z")

</div>

Hi all,

Is there a lite version of DL4J for wearable devices? Something like tensorflow lite that can import pretrained model and only conducts inference?

Thanks.  
BR,  
Pengyuan

---

<div class="post-metadata">

**Author:** ![treo](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/treo/32/47_2.png) [@treo](https://community.konduit.ai/u/treo)\
**Post date:** [June 26, 2020, 9:20am UTC](https://community.konduit.ai/t/dl4j-for-wear-os/651/2 "2020-06-26T09:20:32Z")

</div>

Depending on the type of wearable device you use, it is already possible to use dl4j as is.

As for wearOS in particular, I haven’t tried it myself yet. In theory the android version of dl4j might be able to just work.

Have you tried to use it with wearOS and ran into problems?

---

<div class="post-metadata">

**Author:** ![pengyuan-zhou](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/pengyuan-zhou/32/357_2.png) [@pengyuan-zhou](https://community.konduit.ai/u/pengyuan-zhou)\
**Post date:** [June 26, 2020, 12:05pm UTC](https://community.konduit.ai/t/dl4j-for-wear-os/651/3 "2020-06-26T12:05:20Z")

</div>

Nope, I’m new to DL4J and still scanning over the related codes to plan a proper structure before start coding.  
Is the `TransferLearning API` that I should look into for model import?  
Thanks 🙂

---

<div class="post-metadata">

**Author:** ![treo](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/treo/32/47_2.png) [@treo](https://community.konduit.ai/u/treo)\
**Post date:** [June 26, 2020, 12:19pm UTC](https://community.konduit.ai/t/dl4j-for-wear-os/651/4 "2020-06-26T12:19:04Z")

</div>

If you are looking for model import, you should probably look into [deeplearning4j-examples/tensorflow-keras-import-examples at master · eclipse/deeplearning4j-examples · GitHub](https://github.com/eclipse/deeplearning4j-examples/tree/master/tensorflow-keras-import-examples)

---

<div class="post-metadata">

**Author:** ![pengyuan-zhou](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/pengyuan-zhou/32/357_2.png) [@pengyuan-zhou](https://community.konduit.ai/u/pengyuan-zhou)\
**Post date:** [June 26, 2020, 12:31pm UTC](https://community.konduit.ai/t/dl4j-for-wear-os/651/5 "2020-06-26T12:31:46Z")

</div>

fantastic! thanks! This looks like I can literally do federated learning using Tensorflow as the server side and DL4J as the client