# sed4onnx
Simple ONNX constant encoder/decoder.
https://github.com/PINTO0309/simple-onnx-processing-tools
[](https://pepy.tech/project/sed4onnx)  [](https://pypi.org/project/sed4onnx/) [](https://github.com/PINTO0309/sed4onnx/actions?query=workflow%3ACodeQL)
<p align="center">
<img src="https://user-images.githubusercontent.com/33194443/170163328-b680be10-7f98-4a61-8d49-e28423046297.png" />
</p>
## Key concept
- Since the constant values in the JSON files generated by **[onnx2json](https://github.com/PINTO0309/onnx2json)** are Base64-encoded values, ASCII <-> Base64 conversion is required when rewriting JSON constant values.
- After writing the converted Base64 strings to JSON using this tool, **[json2onnx](https://github.com/PINTO0309/json2onnx)** can be used to regenerate the constant-modified ONNX file.
## 1. Setup
### 1-1. HostPC
```bash
### option
$ echo export PATH="~/.local/bin:$PATH" >> ~/.bashrc \
&& source ~/.bashrc
### run
$ pip install -U sed4onnx
```
### 1-2. Docker
https://github.com/PINTO0309/simple-onnx-processing-tools#docker
## 2. CLI Usage
```
$ sed4onnx -h
usage:
sed4onnx [-h]
-cs CONSTANT_STRING
[-d {float16,float32,float64,uint8,int8,int16,int32,int64,string}]
[-m {encode,decode}]
optional arguments:
-h, --help
show this help message and exit.
-cs CONSTANT_STRING, --constant_string CONSTANT_STRING
Strings to be encoded and decoded for ONNX constants.
-d {float16,float32,float64,uint8,int8,int16,int32,int64,string}, \
--dtype {float16,float32,float64,uint8,int8,int16,int32,int64,string}
Data type.
-m {encode,decode}, --mode {encode,decode}
encode: Converts the string specified in constant_string to a Base64 format string
that can be embedded in ONNX constants.
decode: Converts a Base64 string specified in constant_string to ASCII like
Numpy string or pure string.
```
## 3. In-script Usage
```python
>>> from sed4onnx import encode
>>> from sed4onnx import decode
>>> help(encode)
Help on function encode in module sed4onnx.onnx_constant_encoder_decoder:
encode(constant_string: str) -> str
Parameters
----------
constant_string: str
ASCII string to be encoded.
dtype: str
'float16' or 'float32' or 'float64' or 'uint8'
or 'int8' or 'int16' or 'int32' or 'int64' or 'string'
Returns
-------
encoded_string: str
Base64-encoded ASCII string.
>>> help(decode)
Help on function decode in module sed4onnx.onnx_constant_encoder_decoder:
decode(constant_string: str, dtype: str) -> numpy.ndarray
Parameters
----------
constant_string: str
Base64 string to be decoded.
dtype: str
'float16' or 'float32' or 'float64' or 'uint8'
or 'int8' or 'int16' or 'int32' or 'int64' or 'string'
Returns
-------
decoded_ndarray: np.ndarray
Base64-decoded numpy.ndarray.
```
## 4. CLI Execution
```bash
$ sed4onnx \
--constant_string [-1,3,224,224] \
--dtype int64 \
--mode encode
$ sed4onnx \
--constant_string '//////////8DAAAAAAAAAOAAAAAAAAAA4AAAAAAAAAA=' \
--dtype int64 \
--mode decode
```
## 5. In-script Execution
```python
from sed4onnx import encode
from sed4onnx import decode
base64_string = encode(
constant_string='[-1,3,224,224]',
dtype='int64',
)
numpy_ndarray = decode(
constant_string='//////////8DAAAAAAAAAOAAAAAAAAAA4AAAAAAAAAA=',
dtype='int64',
)
```
## 6. Sample
```bash
$ sed4onnx \
--constant_string [-1,3,224,224] \
--dtype int64 \
--mode encode
//////////8DAAAAAAAAAOAAAAAAAAAA4AAAAAAAAAA=
$ sed4onnx \
--constant_string '//////////8DAAAAAAAAAOAAAAAAAAAA4AAAAAAAAAA=' \
--dtype int64 \
--mode decode
[-1,3,224,224]
```
## 7. Reference
1. https://github.com/onnx/onnx/blob/main/docs/Operators.md
2. https://docs.nvidia.com/deeplearning/tensorrt/onnx-graphsurgeon/docs/index.html
3. https://github.com/NVIDIA/TensorRT/tree/main/tools/onnx-graphsurgeon
4. https://github.com/PINTO0309/simple-onnx-processing-tools
5. https://github.com/PINTO0309/PINTO_model_zoo
## 8. Issues
https://github.com/PINTO0309/simple-onnx-processing-tools/issues
Raw data
{
"_id": null,
"home_page": "https://github.com/PINTO0309/sed4onnx",
"name": "sed4onnx",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.6",
"maintainer_email": "",
"keywords": "",
"author": "Katsuya Hyodo",
"author_email": "rmsdh122@yahoo.co.jp",
"download_url": "https://files.pythonhosted.org/packages/6e/c5/2fe3b9c5c966512a75284f90d662af516b2e1d03a33f93c368d8a0bfabae/sed4onnx-1.0.5.tar.gz",
"platform": "linux",
"description": "# sed4onnx\nSimple ONNX constant encoder/decoder.\n\nhttps://github.com/PINTO0309/simple-onnx-processing-tools\n\n[](https://pepy.tech/project/sed4onnx)  [](https://pypi.org/project/sed4onnx/) [](https://github.com/PINTO0309/sed4onnx/actions?query=workflow%3ACodeQL)\n\n<p align=\"center\">\n <img src=\"https://user-images.githubusercontent.com/33194443/170163328-b680be10-7f98-4a61-8d49-e28423046297.png\" />\n</p>\n\n## Key concept\n- Since the constant values in the JSON files generated by **[onnx2json](https://github.com/PINTO0309/onnx2json)** are Base64-encoded values, ASCII <-> Base64 conversion is required when rewriting JSON constant values.\n- After writing the converted Base64 strings to JSON using this tool, **[json2onnx](https://github.com/PINTO0309/json2onnx)** can be used to regenerate the constant-modified ONNX file.\n\n## 1. Setup\n### 1-1. HostPC\n```bash\n### option\n$ echo export PATH=\"~/.local/bin:$PATH\" >> ~/.bashrc \\\n&& source ~/.bashrc\n\n### run\n$ pip install -U sed4onnx\n```\n### 1-2. Docker\nhttps://github.com/PINTO0309/simple-onnx-processing-tools#docker\n\n\n## 2. CLI Usage\n```\n$ sed4onnx -h\n\nusage:\n sed4onnx [-h]\n -cs CONSTANT_STRING\n [-d {float16,float32,float64,uint8,int8,int16,int32,int64,string}]\n [-m {encode,decode}]\n\noptional arguments:\n -h, --help\n show this help message and exit.\n\n -cs CONSTANT_STRING, --constant_string CONSTANT_STRING\n Strings to be encoded and decoded for ONNX constants.\n\n -d {float16,float32,float64,uint8,int8,int16,int32,int64,string}, \\\n --dtype {float16,float32,float64,uint8,int8,int16,int32,int64,string}\n Data type.\n\n -m {encode,decode}, --mode {encode,decode}\n encode: Converts the string specified in constant_string to a Base64 format string\n that can be embedded in ONNX constants.\n decode: Converts a Base64 string specified in constant_string to ASCII like\n Numpy string or pure string.\n```\n\n## 3. In-script Usage\n```python\n>>> from sed4onnx import encode\n>>> from sed4onnx import decode\n>>> help(encode)\n\nHelp on function encode in module sed4onnx.onnx_constant_encoder_decoder:\n\nencode(constant_string: str) -> str\n\n Parameters\n ----------\n constant_string: str\n ASCII string to be encoded.\n\n dtype: str\n 'float16' or 'float32' or 'float64' or 'uint8'\n or 'int8' or 'int16' or 'int32' or 'int64' or 'string'\n\n Returns\n -------\n encoded_string: str\n Base64-encoded ASCII string.\n\n\n>>> help(decode)\nHelp on function decode in module sed4onnx.onnx_constant_encoder_decoder:\n\ndecode(constant_string: str, dtype: str) -> numpy.ndarray\n\n Parameters\n ----------\n constant_string: str\n Base64 string to be decoded.\n\n dtype: str\n 'float16' or 'float32' or 'float64' or 'uint8'\n or 'int8' or 'int16' or 'int32' or 'int64' or 'string'\n\n Returns\n -------\n decoded_ndarray: np.ndarray\n Base64-decoded numpy.ndarray.\n```\n\n## 4. CLI Execution\n```bash\n$ sed4onnx \\\n--constant_string [-1,3,224,224] \\\n--dtype int64 \\\n--mode encode\n\n$ sed4onnx \\\n--constant_string '//////////8DAAAAAAAAAOAAAAAAAAAA4AAAAAAAAAA=' \\\n--dtype int64 \\\n--mode decode\n```\n\n## 5. In-script Execution\n```python\nfrom sed4onnx import encode\nfrom sed4onnx import decode\n\nbase64_string = encode(\n constant_string='[-1,3,224,224]',\n dtype='int64',\n)\n\nnumpy_ndarray = decode(\n constant_string='//////////8DAAAAAAAAAOAAAAAAAAAA4AAAAAAAAAA=',\n dtype='int64',\n)\n```\n\n## 6. Sample\n```bash\n$ sed4onnx \\\n--constant_string [-1,3,224,224] \\\n--dtype int64 \\\n--mode encode\n\n//////////8DAAAAAAAAAOAAAAAAAAAA4AAAAAAAAAA=\n\n\n$ sed4onnx \\\n--constant_string '//////////8DAAAAAAAAAOAAAAAAAAAA4AAAAAAAAAA=' \\\n--dtype int64 \\\n--mode decode\n\n[-1,3,224,224]\n```\n\n## 7. Reference\n1. https://github.com/onnx/onnx/blob/main/docs/Operators.md\n2. https://docs.nvidia.com/deeplearning/tensorrt/onnx-graphsurgeon/docs/index.html\n3. https://github.com/NVIDIA/TensorRT/tree/main/tools/onnx-graphsurgeon\n4. https://github.com/PINTO0309/simple-onnx-processing-tools\n5. https://github.com/PINTO0309/PINTO_model_zoo\n\n## 8. Issues\nhttps://github.com/PINTO0309/simple-onnx-processing-tools/issues\n",
"bugtrack_url": null,
"license": "MIT License",
"summary": "Simple ONNX constant encoder/decoder.",
"version": "1.0.5",
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"md5": "38bcb04e3d08c9b03c6799d4b370746f",
"sha256": "db80a1c229d7783bed1c88efc868867bd0dfe7180605546d0b05f8aa15c2a50e"
},
"downloads": -1,
"filename": "sed4onnx-1.0.5-py3-none-any.whl",
"has_sig": false,
"md5_digest": "38bcb04e3d08c9b03c6799d4b370746f",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.6",
"size": 5681,
"upload_time": "2022-12-30T15:59:42",
"upload_time_iso_8601": "2022-12-30T15:59:42.440545Z",
"url": "https://files.pythonhosted.org/packages/c2/37/0dd964355edff208522bbe978e82c5eefc1105536afd52a41ce9063b7812/sed4onnx-1.0.5-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"md5": "00d2f56978d41cc0f0d957b9c87d9d5c",
"sha256": "14949a1adfc7287ed9857be6a623f73700c26b27cfeb7f76975aac689557f62b"
},
"downloads": -1,
"filename": "sed4onnx-1.0.5.tar.gz",
"has_sig": false,
"md5_digest": "00d2f56978d41cc0f0d957b9c87d9d5c",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.6",
"size": 4874,
"upload_time": "2022-12-30T15:59:43",
"upload_time_iso_8601": "2022-12-30T15:59:43.788060Z",
"url": "https://files.pythonhosted.org/packages/6e/c5/2fe3b9c5c966512a75284f90d662af516b2e1d03a33f93c368d8a0bfabae/sed4onnx-1.0.5.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2022-12-30 15:59:43",
"github": true,
"gitlab": false,
"bitbucket": false,
"github_user": "PINTO0309",
"github_project": "sed4onnx",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "sed4onnx"
}
JSON
