# Pytorch/tflite models

Source: https://forum.modalai.com/topic/826/pytorch-tflite-models
Category: General Questions (https://forum.modalai.com/category/2/general-questions)
Posted: 2022-03-30 16:57:47 UTC by sarahl
Replies: 4 · Views: 1364

## sarahl · 2022-03-30 16:57:47 UTC

Hi, I've been able to run custom mobilenet tflite models via voxl-tflite-server, but when trying to run a Pytorch Yolov5s model ported to tflite, I get the error: 

Resolved reporter
ERROR: Didn't find op for builtin opcode 'RESIZE_NEAREST_NEIGHBOR' version '3'

ERROR: Registration failed.

Failed to construct interpreter

It seems like this op is only supported for newer version of TF. Will there be support for this in voxl-tflite-server soon? I noticed the docs say it needs TF<=2.2.3 for now, but I was wondering if this was going to be updated. 

I think the conversion produces an ONNX model as an intermediate step- is there a way to run an ONNX model on Voxl1? Alternately, is there a way to run Pytorch models with hardware acceleration? I've tried running CPU models on Pytorch via docker, but keep encountering issues or the board crashing.

## Reply by Guest · 2022-03-31 15:56:04 UTC

Hey @sarahl,

On voxl, we are limited to TF v2.2.3 due to the need for a newer glibc/gcc toolchain. This is not likely to change, but you could use the docker strategy with a current  [TF](https://gitlab.com/voxl-public/voxl-sdk/third-party/qrb5165-tflite) version and newer gcc to get around this. 

We have not done any testing with Pytorch, but for ONNX support you can look into the [Qualcomm Neural Processing SDK](https://developer.qualcomm.com/software/qualcomm-neural-processing-sdk), as this supports Tensorflow, Caffe, and ONNX models.

## Reply by sarahl · 2022-03-31 17:07:24 UTC

Hi @Matt-Turi thanks for the information! On M0054/rb5, are you still also limited to tf v2.2.3? Also, can the same GPU/hardware acceleration used in the voxl-tflite-server be done at the docker level? Same question also regarding using the qualcomm neural processing sdk?

## Reply by Guest · 2022-03-31 17:30:31 UTC

On the qrb5165/M0054 platforms, we are using tensorflow v2.8.0.

For hardware acceleration within a docker, this would require exposing the gpu/other accelerator drivers to the running docker, which I have not done before. However, the qualcomm neural processing sdk will have direct access to hardware accelerators if setup correctly.

## Reply by sansoy · 2024-01-02 20:29:47 UTC

@sarahl Hi Sara,  Could you share any info, like a colab notebook or whatever, on how you trained a tflite that works on the voxls as i've had zero luck even though my trained models work on my linux and mac systems.   I created a yolov5 and quantized it and it inferered correctly.    I also was able to convert a yolov8 model to tflite using ultralytics converter.   I also retrained my own moblie ssd model and quantized it and they all infer correctly except on the voxl2.