PaddlePaddle
SMOKE static model export to ONNX
Dear Author.
Hello! I have encountered a problem. I am using the SMOKE model and following the instructions in README.MD to export the model as a static diagram model. However, the following error occurs when converting the static diagram model to ONNX model.
Configuration environment.
onnx=1.9.0 onnxruntime=1.9.0 paddle2onnx=0.8.2 paddledet=2.3.0 paddlepaddle-gpu=2.2.0
Error message
/home/lee/.conda/envs/paddle/lib/python3.8/site-packages/onnx/mapping.py:27: DeprecationWarning: `np.object` is a deprecated alias for the builtin `object`. To silence this warning, use `object` by itself. Doing this will not modify any behavior and is safe.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
int(TensorProto.STRING): np.dtype(np.object)
/home/lee/.conda/envs/paddle/lib/python3.8/site-packages/paddle2onnx/constant/dtypes.py:45: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
np.bool: core.VarDesc.VarType.BOOL,
/home/lee/.conda/envs/paddle/lib/python3.8/site-packages/paddle2onnx/constant/dtypes.py:46: DeprecationWarning: `np.float` is a deprecated alias for the builtin `float`. To silence this warning, use `float` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.float64` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
core.VarDesc.VarType.FP32: np.float,
/home/lee/.conda/envs/paddle/lib/python3.8/site-packages/paddle2onnx/constant/dtypes.py:51: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
core.VarDesc.VarType.BOOL: np.bool
Traceback (most recent call last):
File "/home/lee/.conda/envs/paddle/bin/paddle2onnx", line 8, in <module>
sys.exit(main())
File "/home/lee/.conda/envs/paddle/lib/python3.8/site-packages/paddle2onnx/command.py", line 148, in main
program2onnx(
File "/home/lee/.conda/envs/paddle/lib/python3.8/site-packages/paddle2onnx/command.py", line 114, in program2onnx
p2o.program2onnx(
File "/home/lee/.conda/envs/paddle/lib/python3.8/site-packages/paddle2onnx/convert.py", line 79, in program2onnx
export_onnx(paddle_graph, save_file, opset_version, enable_onnx_checker, operator_export_type)
File "/home/lee/.conda/envs/paddle/lib/python3.8/site-packages/paddle2onnx/convert.py", line 33, in export_onnx
onnx_graph = ONNXGraph.build(paddle_graph, opset_version, operator_export_type, verbose)
File "/home/lee/.conda/envs/paddle/lib/python3.8/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/lee/.conda/envs/paddle/lib/python3.8/site-packages/paddle2onnx/graph/onnx_graph.py", line 79, in __init__
self.update_opset_version()
File "/home/lee/.conda/envs/paddle/lib/python3.8/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/lee/.conda/envs/paddle/lib/python3.8/site-packages/paddle2onnx/op_mapper/op_mapper.py", line 127, in get_recommend_opset_version
recommend_opset_version = OpMapper.check_support_status(node_map, opset_version, True)
File "/home/lee/.conda/envs/paddle/lib/python3.8/site-packages/paddle2onnx/op_mapper/op_mapper.py", line 168, in check_support_status
raise NotImplementedError(error_info)
NotImplementedError:
There's 9 ops are not supported yet
=========== while ===========
=========== set_value ===========
=========== crop_tensor ===========
=========== logical_not ===========
=========== less_than ===========
=========== select_input ===========
=========== conditional_block ===========
=========== index_select ===========
=========== atan ===========
This error indicates that nine operators are not supported. After checking the list of operators, I found only 'conditional-block', 'set-value', and 'while', 'select-input' and 'crop-tensor' are not available. Here are the commands I used for the conversion.
paddle2onnx --model_dir /media/lee/DATA/project/gitproject/models/PaddleCV/3d_vision/SMOKE/inference_model --model_filename inference.pdmodel --params_filename inference.pdiparams --opset_version 11 --save_file smoke.onnx
How should I solve such a situation? I look forward to your reply!
Sorry, we still do not support the conversion of this model, we will provide support as soon as possible. In addition, why did you convert this model to ONNX? If used for deployment, welcome to use PaddleInference or PaddleLIte for deployment.
@yeliang2258 Thank you for your suggestion. I'll try to use PaddleInference and PaddleLIte to convert. As you said, it is needed to deploy to a lab development board for doing experimental design.
Thank you very much for using Paddle. We have prepared a simple survey questionnaire (can be completed in half a minute). If you have time, please help us to complete the survey and help Paddle2ONNX to be better, thank you. https://iwenjuan.baidu.com/?code=ibd2b1
There's 5 ops are not supported yet =========== crop_tensor =========== =========== while =========== =========== select_input =========== =========== conditional_block =========== =========== set_value ===========
Any plan to do this?
Sorry, we still do not support the conversion of this model, we will provide support as soon as possible. In addition, why did you convert this model to ONNX? If used for deployment, welcome to use PaddleInference or PaddleLIte for deployment.
We want to use the openvino hardware acceloration，So onnx is a must.
Dear Author. Hello! I have encountered a problem. I am using the SMOKE model and following the instructions in README.MD to export the model as a static diagram model. However, the following error occurs when converting the static diagram model to ONNX model. Configuration environment.
onnx=1.9.0 onnxruntime=1.9.0 paddle2onnx=0.8.2 paddledet=2.3.0 paddlepaddle-gpu=2.2.0Error message/home/lee/.conda/envs/paddle/lib/python3.8/site-packages/onnx/mapping.py:27: DeprecationWarning: `np.object` is a deprecated alias for the builtin `object`. To silence this warning, use `object` by itself. Doing this will not modify any behavior and is safe. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations int(TensorProto.STRING): np.dtype(np.object) /home/lee/.conda/envs/paddle/lib/python3.8/site-packages/paddle2onnx/constant/dtypes.py:45: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations np.bool: core.VarDesc.VarType.BOOL, /home/lee/.conda/envs/paddle/lib/python3.8/site-packages/paddle2onnx/constant/dtypes.py:46: DeprecationWarning: `np.float` is a deprecated alias for the builtin `float`. To silence this warning, use `float` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.float64` here. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations core.VarDesc.VarType.FP32: np.float, /home/lee/.conda/envs/paddle/lib/python3.8/site-packages/paddle2onnx/constant/dtypes.py:51: DeprecationWarning: `np.bool` is a deprecated alias for the builtin `bool`. To silence this warning, use `bool` by itself. Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.bool_` here. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations core.VarDesc.VarType.BOOL: np.bool Traceback (most recent call last): File "/home/lee/.conda/envs/paddle/bin/paddle2onnx", line 8, in <module> sys.exit(main()) File "/home/lee/.conda/envs/paddle/lib/python3.8/site-packages/paddle2onnx/command.py", line 148, in main program2onnx( File "/home/lee/.conda/envs/paddle/lib/python3.8/site-packages/paddle2onnx/command.py", line 114, in program2onnx p2o.program2onnx( File "/home/lee/.conda/envs/paddle/lib/python3.8/site-packages/paddle2onnx/convert.py", line 79, in program2onnx export_onnx(paddle_graph, save_file, opset_version, enable_onnx_checker, operator_export_type) File "/home/lee/.conda/envs/paddle/lib/python3.8/site-packages/paddle2onnx/convert.py", line 33, in export_onnx onnx_graph = ONNXGraph.build(paddle_graph, opset_version, operator_export_type, verbose) File "/home/lee/.conda/envs/paddle/lib/python3.8/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/lee/.conda/envs/paddle/lib/python3.8/site-packages/paddle2onnx/graph/onnx_graph.py", line 79, in __init__ self.update_opset_version() File "/home/lee/.conda/envs/paddle/lib/python3.8/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/lee/.conda/envs/paddle/lib/python3.8/site-packages/paddle2onnx/op_mapper/op_mapper.py", line 127, in get_recommend_opset_version recommend_opset_version = OpMapper.check_support_status(node_map, opset_version, True) File "/home/lee/.conda/envs/paddle/lib/python3.8/site-packages/paddle2onnx/op_mapper/op_mapper.py", line 168, in check_support_status raise NotImplementedError(error_info) NotImplementedError: There's 9 ops are not supported yet =========== while =========== =========== set_value =========== =========== crop_tensor =========== =========== logical_not =========== =========== less_than =========== =========== select_input =========== =========== conditional_block =========== =========== index_select =========== =========== atan ===========This error indicates that nine operators are not supported. After checking the list of operators, I found only 'conditional-block', 'set-value', and 'while', 'select-input' and 'crop-tensor' are not available. Here are the commands I used for the conversion.
paddle2onnx --model_dir /media/lee/DATA/project/gitproject/models/PaddleCV/3d_vision/SMOKE/inference_model --model_filename inference.pdmodel --params_filename inference.pdiparams --opset_version 11 --save_file smoke.onnxHow should I solve such a situation? I look forward to your reply!
Have you already converted SMOKE model to ONNX successfully?
