# ONNX export of quantized model

**URL:** <https://discuss.pytorch.org/t/onnx-export-of-quantized-model/76884>\
**Category:** quantization\
**Created:** [April 15, 2020, 3:14pm UTC](https://discuss.pytorch.org/t/onnx-export-of-quantized-model/76884 "2020-04-15T15:14:40Z")\
**Posts on this page:** 1\
**Showing post:** 24

<div class="post-metadata">

**Author:** ![ZyrianovS](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/zyrianovs/32/30350_2.png) [@ZyrianovS](https://discuss.pytorch.org/u/ZyrianovS)\
**Post date:** [July 9, 2021, 2:18am UTC](https://discuss.pytorch.org/t/onnx-export-of-quantized-model/76884/24 "2021-07-09T02:18:16Z")

</div>

UPD: Those additional biases set to `None` are becasue `torch.backends.quantized.engine` mismath with `torch.quantization.get_default_qat_qconfig`. When they match though (set to `qnnpack` in my case) I get  
`RuntimeError: Tried to trace < __torch__.torch.classes.quantized.Conv2dPackedParamsBase object at 0x52982b0> but it is not part of the active trace. Modules that are called during a trace must be registered as submodules of the thing being traced.`

---

_[View the full topic](https://discuss.pytorch.org/t/onnx-export-of-quantized-model/76884)._