# LayoutLMv3 Onnx Conversion

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Flayoutlmv3-onnx-conversion%2F37126%3E%5C
**Category:** 🤗Transformers\
**Created:** [April 19, 2023, 3:30pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Flayoutlmv3-onnx-conversion%2F37126 "2023-04-19T15:30:37Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![uyousafzai](https://avatars.discourse-cdn.com/v4/letter/u/b9e5f3/32.png) [@uyousafzai](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fuyousafzai)%5C
**Post date:** [April 19, 2023, 3:30pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Flayoutlmv3-onnx-conversion%2F37126%2F1 "2023-04-19T15:30:38Z")

</div>

Apologies for missing something very obvious but I am just getting started with ONNX and don’t understand many of the errors and problems leading upto converting finetuned local models to ONNX format.

Currently trying to export a finetuned model of [layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base), however I encounter a similar error as mentioned above in this [post #23166](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Flayoutlmv3-transformers-onnx%2F23166)

x----------------------------------Configuration Details----------------------------------x  
transformers = 4.28.1  
Python = 3.8.10  
torch = 1.12.0  
onnx = 1.13.1  
CPU Only  
x----------------------------------Error Trace----------------------------------x  
Local PyTorch model found.  
Framework not requested. Using torch to export to ONNX.  
Using framework PyTorch: 1.12.0+cu102  
Traceback (most recent call last):  
File “/usr/lib/python3.8/runpy.py”, line 194, in \_run\_module\_as\_main  
return \_run\_code(code, main\_globals, None,  
File “/usr/lib/python3.8/runpy.py”, line 87, in \_run\_code  
exec(code, run\_globals)  
File “/usr/local/lib/python3.8/dist-packages/transformers/onnx/ **main**.py”, line 240, in   
main()  
File “/usr/local/lib/python3.8/dist-packages/transformers/onnx/ **main**.py”, line 232, in main  
export\_with\_transformers(args)  
File “/usr/local/lib/python3.8/dist-packages/transformers/onnx/ **main**.py”, line 165, in export\_with\_transformers  
onnx\_inputs, onnx\_outputs = export(  
File “/usr/local/lib/python3.8/dist-packages/transformers/onnx/convert.py”, line 346, in export  
return export\_pytorch(preprocessor, model, config, opset, output, tokenizer=tokenizer, device=device)  
File “/usr/local/lib/python3.8/dist-packages/transformers/onnx/convert.py”, line 143, in export\_pytorch  
model\_inputs = config.generate\_dummy\_inputs(preprocessor, framework=TensorType.PYTORCH)  
File “/usr/local/lib/python3.8/dist-packages/transformers/models/layoutlmv3/configuration\_layoutlmv3.py”, line 263, in generate\_dummy\_inputs  
setattr(processor.feature\_extractor, “apply\_ocr”, False)  
AttributeError: ‘LayoutLMv3TokenizerFast’ object has no attribute ‘feature\_extractor’

Am I missing something very obvious?

---

<div class="post-metadata">

**Author:** ![uyousafzai](https://avatars.discourse-cdn.com/v4/letter/u/b9e5f3/32.png) [@uyousafzai](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fuyousafzai)%5C
**Post date:** [April 20, 2023, 12:01pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Flayoutlmv3-onnx-conversion%2F37126%2F2 "2023-04-20T12:01:21Z")

</div>

This issue is solved by using the recommended `optimum.exporters.onnx` the details of using this library for exporting can be found at the following [Optimum Link](https://huggingface.co/docs/optimum/main/en/exporters/onnx/usage_guides/export_a_model#selecting-a-task)