https://github.com/pinto0309/sde4onnx
Simple doc_string eraser for ONNX.
https://github.com/pinto0309/sde4onnx
deep-learning machine-learning model-converter onnx
Last synced: 7 months ago
JSON representation
Simple doc_string eraser for ONNX.
- Host: GitHub
- URL: https://github.com/pinto0309/sde4onnx
- Owner: PINTO0309
- License: mit
- Created: 2022-10-15T04:52:32.000Z (about 3 years ago)
- Default Branch: main
- Last Pushed: 2022-10-15T05:59:23.000Z (about 3 years ago)
- Last Synced: 2024-10-29T08:21:11.536Z (12 months ago)
- Topics: deep-learning, machine-learning, model-converter, onnx
- Language: Python
- Homepage:
- Size: 14.6 KB
- Stars: 1
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# sde4onnx
**S**imple **D**oc_string **E**raser for **O**NNX.
https://github.com/PINTO0309/simple-onnx-processing-tools
[](https://pepy.tech/project/sde4onnx)  [](https://pypi.org/project/sde4onnx/) [](https://github.com/PINTO0309/sde4onnx/actions?query=workflow%3ACodeQL)
# Key concept
- [x] doc_string eraser for ONNX. e.g. Hagging Face Stable Diffusion ONNX.
## 1. Setup
### 1-1. HostPC
```bash
### 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 -U sde4onnx
```
### 1-2. Docker
https://github.com/PINTO0309/simple-onnx-processing-tools#docker
## 2. CLI Usage
```
$ sde4onnx -h
usage:
sde4onnx [-h]
-if INPUT_ONNX_FILE_PATH
[-of OUTPUT_ONNX_FILE_PATH]
[-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.
-n, --non_verbose
Do not show all information logs. Only error logs are displayed.
```
## 3. In-script Usage
```python
>>> from sde4onnx import erase
>>> help(erase)
Help on function erase in module sde4onnx.onnx_opname_generator:
erase(
input_onnx_file_path: Union[str, NoneType] = '',
onnx_graph: Union[onnx.onnx_ml_pb2.ModelProto, NoneType] = None,
output_onnx_file_path: Union[str, NoneType] = '',
non_verbose: 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: ''
non_verbose: Optional[bool]
Do not show all information logs. Only error logs are displayed.
Default: False
Returns
-------
renamed_graph: onnx.ModelProto
Renamed onnx ModelProto.
```
## 4. CLI Execution
```bash
$ sde4onnx \
--input_onnx_file_path vae_encoder.onnx \
--output_onnx_file_path vae_encoder_erased.onnx
```
## 5. In-script Execution
```python
from sde4onnx import erase
onnx_graph = erase(
input_onnx_file_path="vae_encoder.onnx",
output_onnx_file_path="vae_encoder_erased.onnx",
)
```
## 6. Sample
https://huggingface.co/bes-dev/stable-diffusion-v1-4-onnx/resolve/main/vae_encoder.onnx
### Before
### After
## 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