# Are SELECT_TF_OPS supported on VOXL2?

Source: https://forum.modalai.com/topic/3030/are-select_tf_ops-supported-on-voxl2
Category: General Questions (https://forum.modalai.com/category/2/general-questions)
Tags: tflite, tflite-server, voxl2
Posted: 2024-01-18 22:00:25 UTC by eric
Replies: 1 · Views: 1497

## eric · 2024-01-18 22:00:25 UTC

I'm converting a custom keras model to tflite. Unfortunately, this model requires GatherND, which is not included in the built-in TF lite OPS.

If I add SELECT_TF_OPS to the supported ops list, then my custom TFlite model builds locally:
 
```
converter.target_spec.supported_ops = [
    tf.lite.OpsSet.TFLITE_BUILTINS,
    tf.lite.OpsSet.SELECT_TF_OPS
]
```

Will this model (with the SELECT_TF_OPS flag) work with tflite server for VOXL2, or can I only use the built-in tflite ops?

## Reply by Guest · 2024-01-26 00:20:23 UTC

@eric 

Sorry for the late response on this!!

Your best bet would be to just try it out, I can't say without trying it myself. It's possible it works, it's possible something fails. I've never had to deal with this so I can't say for certain.

It's also worth pointing out that `voxl-tflite-server` is more meant to be an example of how TFLite models can be run on VOXL and not an in-depth ML framework for deploying custom models. If `voxl-tflite-server` doesn't support it, by all means fork the repository and build out the functionality to be able to. Even better, make a pull request with that functionality and I'll test and approve it!

Hope this helps,

Thomas Patton