https://github.com/pinto0309/snd4onnx
Simple node deletion tool for onnx.
https://github.com/pinto0309/snd4onnx
cli model-converter models onnx onnxruntime python
Last synced: about 1 year ago
JSON representation
Simple node deletion tool for onnx.
- Host: GitHub
- URL: https://github.com/pinto0309/snd4onnx
- Owner: PINTO0309
- License: mit
- Created: 2022-04-01T10:16:29.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2022-09-08T10:48:29.000Z (almost 4 years ago)
- Last Synced: 2025-04-20T09:39:44.615Z (about 1 year ago)
- Topics: cli, model-converter, models, onnx, onnxruntime, python
- Language: Python
- Homepage:
- Size: 64.5 KB
- Stars: 7
- Watchers: 3
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# snd4onnx
Simple node deletion tool for onnx. I only test very miscellaneous and limited patterns as a hobby. There are probably a large number of bugs. Pull requests are welcome.
https://github.com/PINTO0309/simple-onnx-processing-tools
[](https://pepy.tech/project/snd4onnx)  [](https://pypi.org/project/snd4onnx/) [](https://github.com/PINTO0309/snd4onnx/actions?query=workflow%3ACodeQL)
## 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 snd4onnx
```
### 1-2. Docker
https://github.com/PINTO0309/simple-onnx-processing-tools#docker
## 2. CLI Usage
```
$ snd4onnx -h
usage:
snd4onnx [-h]
-rn REMOVE_NODE_NAMES [REMOVE_NODE_NAMES ...]
-if INPUT_ONNX_FILE_PATH
-of OUTPUT_ONNX_FILE_PATH
[-n]
optional arguments:
-h, --help
show this help message and exit.
-rn REMOVE_NODE_NAMES [REMOVE_NODE_NAMES ...], --remove_node_names REMOVE_NODE_NAMES [REMOVE_NODE_NAMES ...]
ONNX node name to be deleted.
-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 snd4onnx import remove
>>> help(remove)
Help on function remove in module snd4onnx.onnx_remove_node:
remove(
remove_node_names: List[str],
input_onnx_file_path: Union[str, NoneType] = '',
output_onnx_file_path: Union[str, NoneType] = '',
onnx_graph: Union[onnx.onnx_ml_pb2.ModelProto, NoneType] = None,
non_verbose: Union[bool, NoneType] = False
) -> onnx.onnx_ml_pb2.ModelProto
Parameters
----------
remove_node_names: List[str]
List of OP names to be deleted.
e.g. remove_node_names = ['op_name1', 'op_name2', 'op_name3', ...]
input_onnx_file_path: Optional[str]
Input onnx file path.
Either input_onnx_file_path or onnx_graph must be specified.
output_onnx_file_path: Optional[str]
Output onnx file path.
If output_onnx_file_path is not specified, no .onnx file is output.
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.
non_verbose: Optional[bool]
Do not show all information logs. Only error logs are displayed.
Default: False
Returns
-------
removed_graph: onnx.ModelProto
OP removed onnx ModelProto.
```
## 4. CLI Execution
```bash
$ snd4onnx \
--remove_node_names node_name_a node_name_b \
--input_onnx_file_path input.onnx \
--output_onnx_file_path output.onnx
```
## 5. In-script Execution
```python
from snd4onnx import remove
onnx_graph = remove(
remove_node_names=['node_name_a', 'node_name_b'],
input_onnx_file_path='input.onnx',
)
# or
onnx_graph = remove(
remove_node_names=['node_name_a', 'node_name_b'],
onnx_graph=graph,
)
```
## 6. Sample
### 6-1. sample.1
|Before|After|
|:-:|:-:|
|||
### 6-2. sample.2
|Before|After|
|:-:|:-:|
|||
### 6-3. sample.3
|Before|After|
|:-:|:-:|
|||
### 6-4. sample.4
|Before|After|
|:-:|:-:|
|||
### 6-5. sample.5
|Before|After|
|:-:|:-:|
|||
## 7. Reference
1. https://docs.nvidia.com/deeplearning/tensorrt/onnx-graphsurgeon/docs/index.html
2. https://github.com/NVIDIA/TensorRT/tree/main/tools/onnx-graphsurgeon
3. https://github.com/PINTO0309/scs4onnx
4. https://github.com/PINTO0309/sne4onnx
5. https://github.com/PINTO0309/snc4onnx
6. https://github.com/PINTO0309/sog4onnx
7. https://github.com/PINTO0309/PINTO_model_zoo
## 8. Issues
https://github.com/PINTO0309/simple-onnx-processing-tools/issues