# Tvm export onnx format model

**URL:** <https://discuss.tvm.apache.org/t/tvm-export-onnx-format-model/13396>\
**Category:** Questions\
**Created:** [August 24, 2022, 6:28am UTC](https://discuss.tvm.apache.org/t/tvm-export-onnx-format-model/13396 "2022-08-24T06:28:28Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![gxxxh](https://discuss.tvm.apache.org/user_avatar/discuss.tvm.apache.org/gxxxh/32/4141_2.png) [@gxxxh](https://discuss.tvm.apache.org/u/gxxxh)\
**Post date:** [August 24, 2022, 6:28am UTC](https://discuss.tvm.apache.org/t/tvm-export-onnx-format-model/13396/1 "2022-08-24T06:28:28Z")

</div>

I am trying to using TVM to tuning models on a arm SOC. The SOC can run the model a spectial hardware, which can accelerate the inference process. However, the hardware needs a special model format which can only be converted from caffe1.0 model. The SOC also provides a cross complier to complie its program. So, I hope to know that is there a way for tvm to export the tuned model into onnx or caffe model?I found that there is a repository called Relay2Onnx but I didn’t find how to use it. And in the source code tvm, the “/python/relay/frontedn”, it seems that there are only methods to import instead of export.