Paddle2ONNX - LodTensorArray is not supported

[bpkrishnan]

问题描述 / Problem Description

While converting KIE-RE model to ONNX got LodTensorArray is not supported error. How to solve this or when it will be fixed in the new versions?

运行环境 / Runtime Environment

• OS: Colab
• Paddle: 2.6.1
• PaddleOCR: 2.8.0

复现代码 / Reproduction Code

paddle2onnx --model_dir ./inference/re_vi_layoutxlm_xfund_infer \
--model_filename inference.pdmodel \
--params_filename inference.pdiparams \
--save_file ./inference/re_onnx/model.onnx \
--opset_version 11 \
--enable_onnx_checker True

完整报错 / Complete Error Message

[Paddle2ONNX] Start to parse PaddlePaddle model...
[Paddle2ONNX] Model file path: ./inference/re_vi_layoutxlm_xfund_infer/inference.pdmodel
[Paddle2ONNX] Parameters file path: ./inference/re_vi_layoutxlm_xfund_infer/inference.pdiparams
[Paddle2ONNX] Start to parsing Paddle model...
[Paddle2ONNX] LodTensorArray is not supported.
[Paddle2ONNX] Oops, there are some operators not supported yet, including bilinear_tensor_product,conditional_block,empty,lod_array_length,select_input,tensor_array_to_tensor,while,write_to_array,
[ERROR] Due to the unsupported operators, the conversion is aborted.


--------------------------------------
C++ Traceback (most recent call last):
--------------------------------------
0   paddle2onnx::Export(char const*, char const*, char**, int*, int, bool, bool, bool, bool, bool, paddle2onnx::CustomOp*, int, char const*, char**, int*, char const*, bool*, bool, char**, int)

----------------------
Error Message Summary:
----------------------
FatalError: `Process abort signal` is detected by the operating system.
  [TimeInfo: *** Aborted at 1718027421 (unix time) try "date -d @1718027421" if you are using GNU date ***]
  [SignalInfo: *** SIGABRT (@0xd54a) received by PID 54602 (TID 0x7951b0225000) from PID 54602 ***]

可能解决方案 / Possible solutions

附件 / Appendix

[GreatV]

You need to submit an issue to paddle2onnx.