[Paddle2ONNX] LodTensorArray is not supported.

[Jinjie0721]

问题描述
对paddleDetection中的swin 模型 faster_rcnn_swin_tiny_fpn_3x_coco.yml 导出模型权重，想转化为onnx 格式，但是paddle2onnx 报错不支持LodTensorArray 算子,有其他方法可以进行转化吗

更多信息 :

• 用于部署的推理引擎: TensorRT 8
• Paddle2ONNX版本: 1.0.9

报错截图

其他信息

[bpkrishnan]

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?

Logged an issue in paddle also

Runtime Environment
OS: Colab
Paddle: 2.6.1
PaddleOCR: 2.8.0

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

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 ***]