paddle2onnx报错

[CV-deeplearning]

请将下面信息填写完整，便于我们快速解决问题，谢谢！

基于paddle ocr训练的表格识别模型，转成onnx时报错！！！ 用paddle训练的表格识别模型，转onnx时报错，难道是不支持GRU操作。

更多信息 :

• 用于部署的推理引擎:tensorRT
• 为什么需要转换为ONNX格式：用tensorRT加速
• Paddle2ONNX版本:2.1.1
• 你的联系方式(Email/Wechat/Phone):[email protected]

---

Traceback (most recent call last): File "/home/work/anaconda3/envs/torch16_py37/bin/paddle2onnx", line 8, in sys.exit(main()) File "/home/work/anaconda3/envs/torch16_py37/lib/python3.7/site-packages/paddle2onnx/command.py", line 184, in main input_shape_dict=input_shape_dict) File "/home/work/anaconda3/envs/torch16_py37/lib/python3.7/site-packages/paddle2onnx/command.py", line 148, in program2onnx operator_export_type=operator_export_type) File "/home/work/anaconda3/envs/torch16_py37/lib/python3.7/site-packages/paddle2onnx/convert.py", line 84, in program2onnx enable_onnx_checker, operator_export_type) File "/home/work/anaconda3/envs/torch16_py37/lib/python3.7/site-packages/paddle2onnx/convert.py", line 34, in export_onnx operator_export_type, verbose) File "/home/work/anaconda3/envs/torch16_py37/lib/python3.7/site-packages/paddle2onnx/graph/onnx_graph.py", line 240, in build onnx_graph = ONNXGraph(paddle_graph, opset_version=opset_version, operator_export_type=operator_export_type) File "/home/work/anaconda3/envs/torch16_py37/lib/python3.7/site-packages/paddle2onnx/graph/onnx_graph.py", line 79, in init self.update_opset_version() File "/home/work/anaconda3/envs/torch16_py37/lib/python3.7/site-packages/paddle2onnx/graph/onnx_graph.py", line 194, in update_opset_version self.opset_version = OpMapper.get_recommend_opset_version(node_map, self.opset_version) File "/home/work/anaconda3/envs/torch16_py37/lib/python3.7/site-packages/paddle2onnx/op_mapper/op_mapper.py", line 129, in get_recommend_opset_version node_map, opset_version, True) File "/home/work/anaconda3/envs/torch16_py37/lib/python3.7/site-packages/paddle2onnx/op_mapper/op_mapper.py", line 174, in check_support_status raise NotImplementedError(error_info) NotImplementedError: There's 7 ops are not supported yet =========== select_input =========== =========== lod_array_length =========== =========== write_to_array =========== =========== tensor_array_to_tensor =========== =========== one_hot_v2 =========== =========== while =========== =========== conditional_block ===========

其他信息