# VOXL2 tflite custom models

Source: https://forum.modalai.com/topic/2493/voxl2-tflite-custom-models
Category: VOXL 2 and VOXL 2 Mini (https://forum.modalai.com/category/26/voxl-2-and-voxl-2-mini)
Tags: voxl-2
Posted: 2023-07-26 21:26:36 UTC by Jgaucin
Replies: 1 · Views: 701

## Jgaucin · 2023-07-26 21:26:36 UTC

Hello!

TL;DR – Does the VOXL2 have an EdgeTPU included in the hardware or is it just the name given to the DeepLab v3 model below? Also, how can I access the models in the VOXL2 in order to fine-tune or optimize for my specific needs?:

edgetpu_deeplab_321_os32_float16_quant.tflite

![VOXL2_dnn.png](https://forum.modalai.com/assets/uploads/files/1690405609668-voxl2_dnn.png) 

I wanted to make this post to ask about this and see if anyone has had the same experience and has any resources to accomplish this task. I have seen some forum posts of this being successfully done on VOXL however not any forum posts on the VOXL2 (qrb5165).

I found this article which has the performance of the models and a link to the segmentation model on Github. That Github repository PINTO_Model_Zoo also has a link to the EdgeTPU-DeepLab models trained on the Cityscapes dataset.

[link text](https://www.modalai.com/blogs/blog/run-five-simultaneous-neural-networks-on-voxl-2-with-tensorflow-lite)

[link text](https://github.com/tensorflow/models/blob/master/research/deeplab/g3doc/model_zoo.md#edgetpu-deeplab-models-on-cityscapes)

My understanding is that I can use a Deeplab v3 segmentation model compatible with TensorFlow Lite, which then needs to be quantized for best performance and to be compatible with the nnapi used by VOXL2. I am unsure of the role edgetpu plays in this process. I hope the documentation over this is made public soon to help in the start of this process.

Thank you as always!

## Reply by Moderator (ModalAI staff) · 2023-07-27 16:05:45 UTC

@Jgaucin voxl-tflite-server is just a wrapper for standard TensorFlow Lite that has been compiled with the proper configurations to take advantage of QRB5165.

[voxl-tflite-server](https://gitlab.com/voxl-public/voxl-sdk/services/voxl-tflite-server/-/tree/master) code

So, if you can achieve what you are trying to do using TensorFlow Lite on the desktop, then you should be able to bring over to VOXL 2 in a straightforward manner. 

The inference_worker function [here](https://gitlab.com/voxl-public/voxl-sdk/services/voxl-tflite-server/-/blob/master/src/main.cpp#L143) is where the models are processed