A very simple script that only initializes the batch size of ONNX. Simple Batchsize Initialization for ONNX.
https://github.com/PINTO0309/simple-onnx-processing-tools
- Initializes the ONNX batch size with the specified characters.
- This tool is not a panacea and may fail to initialize models with very complex structures. For example, there is an ONNX that contains a
Reshapethat involves a batch size, or aGemmthat contains a batch output other than 1 in the output result. - A
Reshapein a graph cannot contain more than two undefined shapes, such as-1orNorNoneorunk_*. Therefore, before initializing the batch size with this tool, make sure that theReshapedoes not already contain one or more-1dimensions. If it already contains undefined dimensions, it may be possible to successfully initialize the batch size by pre-writing the undefined dimensions of the relevantReshapeto static values using sam4onnx.
### option
$ echo export PATH="~/.local/bin:$PATH" >> ~/.bashrc \
&& source ~/.bashrc
### run
$ pip install -U onnx \
&& python3 -m pip install -U onnx_graphsurgeon --index-url https://pypi.ngc.nvidia.com \
&& pip install --no-deps -U onnx-simplifier \
&& pip install -U sbi4onnxhttps://github.com/PINTO0309/simple-onnx-processing-tools#docker
$ sbi4onnx -h
usage:
sbi4onnx [-h]
-if INPUT_ONNX_FILE_PATH
-of OUTPUT_ONNX_FILE_PATH
-ics INITIALIZATION_CHARACTER_STRING
[-dos]
[-n]
optional arguments:
-h, --help
show this help message and exit.
-if INPUT_ONNX_FILE_PATH, --input_onnx_file_path INPUT_ONNX_FILE_PATH
Input onnx file path.
-of OUTPUT_ONNX_FILE_PATH, --output_onnx_file_path OUTPUT_ONNX_FILE_PATH
Output onnx file path.
-ics INITIALIZATION_CHARACTER_STRING, --initialization_character_string INITIALIZATION_CHARACTER_STRING
String to initialize batch size. "-1" or "N" or "xxx", etc...
Default: '-1'
-dos, --disable_onnxsim
Suppress the execution of onnxsim on the backend and dare to leave redundant processing.
-n, --non_verbose
Do not show all information logs. Only error logs are displayed.
>>> from sbi4onnx import initialize
>>> help(initialize)
Help on function initialize in module sbi4onnx.onnx_batchsize_initialize:
initialize(
input_onnx_file_path: Union[str, NoneType] = '',
onnx_graph: Union[onnx.onnx_ml_pb2.ModelProto, NoneType] = None,
output_onnx_file_path: Union[str, NoneType] = '',
initialization_character_string: Union[str, NoneType] = '-1',
non_verbose: Union[bool, NoneType] = False,
disable_onnxsim: Union[bool, NoneType] = False,
) -> onnx.onnx_ml_pb2.ModelProto
Parameters
----------
input_onnx_file_path: Optional[str]
Input onnx file path.
Either input_onnx_file_path or onnx_graph must be specified.
Default: ''
onnx_graph: Optional[onnx.ModelProto]
onnx.ModelProto.
Either input_onnx_file_path or onnx_graph must be specified.
onnx_graph If specified, ignore input_onnx_file_path and process onnx_graph.
output_onnx_file_path: Optional[str]
Output onnx file path. If not specified, no ONNX file is output.
Default: ''
initialization_character_string: Optional[str]
String to initialize batch size. "-1" or "N" or "xxx", etc...
Default: '-1'
disable_onnxsim: Optional[bool]
Suppress the execution of onnxsim on the backend and dare to leave redundant processing.
Default: False
non_verbose: Optional[bool]
Do not show all information logs. Only error logs are displayed.
Default: False
Returns
-------
changed_graph: onnx.ModelProto
Changed onnx ModelProto.$ sbi4onnx \
--input_onnx_file_path whenet_224x224.onnx \
--output_onnx_file_path whenet_Nx224x224.onnx \
--initialization_character_string N
$ sbi4onnx \
--input_onnx_file_path whenet_224x224.onnx \
--output_onnx_file_path whenet_Nx224x224.onnx \
--initialization_character_string -1
$ sbi4onnx \
--input_onnx_file_path whenet_224x224.onnx \
--output_onnx_file_path whenet_Nx224x224.onnx \
--initialization_character_string abcdefgfrom sbi4onnx import initialize
onnx_graph = initialize(
input_onnx_file_path="whenet_224x224.onnx",
output_onnx_file_path="whenet_Nx224x224.onnx",
initialization_character_string="abcdefg",
)
# or
onnx_graph = initialize(
onnx_graph=graph,
initialization_character_string="abcdefg",
)
- https://github.com/onnx/onnx/blob/main/docs/Operators.md
- https://docs.nvidia.com/deeplearning/tensorrt/onnx-graphsurgeon/docs/index.html
- https://github.com/NVIDIA/TensorRT/tree/main/tools/onnx-graphsurgeon
- https://github.com/PINTO0309/simple-onnx-processing-tools
- https://github.com/PINTO0309/PINTO_model_zoo
https://github.com/PINTO0309/simple-onnx-processing-tools/issues
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent