Open iazdan opened 2 years ago
It's not supported
Will support for pp-structure to onnx model be added anytime soon? If not, could you please provide some guidelines on how to convert to onnx?
I ran into the same problem. Will you please share a workaround?
I got a same problem!!
How to use onnx model for pp table model?
Please fill in the information below so that we can solve the problem quickly, Thanks !
Describe the bug A clear and concise description of what the bug is.
I get the below error while converting the table recognition model. Does anyone know how to resolve this error?
Informations (please complete the following information):
Screenshots
Additional context Traceback (most recent call last): File "bin/paddle2onnx", line 33, in sys.exit(load_entry_point('paddle2onnx==0.9.3', 'console_scripts', 'paddle2onnx')()) File "/lib/python3.8/site-packages/paddle2onnx/command.py", line 273, in main program2onnx( File "/lib/python3.8/site-packages/paddle2onnx/command.py", line 200, in program2onnx p2o.program2onnx( File "lib/python3.8/site-packages/paddle2onnx/convert.py", line 95, in program2onnx return export_onnx( File "/paddle/lib/python3.8/site-packages/paddle2onnx/convert.py", line 35, in export_onnx onnx_graph = ONNXGraph.build(paddle_graph, opset_version, File "lib/python3.8/site-packages/paddle2onnx/graph/onnx_graph.py", line 323, in build onnx_graph = ONNXGraph( File "/lib/python3.8/site-packages/paddle2onnx/graph/onnx_graph.py", line 85, in init self.update_opset_version() File "/lib/python3.8/site-packages/paddle2onnx/graph/onnx_graph.py", line 202, in update_opset_version self.opset_version = OpMapper.get_recommend_opset_version( File "/lib/python3.8/site-packages/paddle2onnx/op_mapper/op_mapper.py", line 128, in get_recommend_opset_version recommend_opset_version = OpMapper.check_support_status( File "/lib/python3.8/site-packages/paddle2onnx/op_mapper/op_mapper.py", line 174, in check_support_status raise NotImplementedError(error_info) NotImplementedError: There's 6 ops are not supported yet =========== tensor_array_to_tensor =========== =========== while =========== =========== write_to_array =========== =========== select_input =========== =========== lod_array_length =========== =========== conditional_block ===========