https://github.com/pinto0309/sng4onnx

A simple tool that automatically generates and assigns an OP name to each OP in an old format ONNX file.
https://github.com/pinto0309/sng4onnx

deep-learning machine-learning model-converter onnx

Last synced: 7 months ago
JSON representation

A simple tool that automatically generates and assigns an OP name to each OP in an old format ONNX file.

• Host: GitHub
• URL: https://github.com/pinto0309/sng4onnx
• Owner: PINTO0309
• License: mit
• Created: 2022-10-13T14:40:02.000Z (about 3 years ago)
• Default Branch: main
• Last Pushed: 2024-04-22T12:52:43.000Z (over 1 year ago)
• Last Synced: 2024-05-01T15:19:58.492Z (over 1 year ago)
• Topics: deep-learning, machine-learning, model-converter, onnx
• Language: Python
• Homepage:
• Size: 11.7 KB
• Stars: 1
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# sng4onnx

A simple tool that automatically generates and assigns an OP name to each OP in an old format ONNX file.  

**S**imple op **N**ame **G**enerator for **ONNX**.

https://github.com/PINTO0309/simple-onnx-processing-tools

[![Downloads](https://static.pepy.tech/personalized-badge/sng4onnx?period=total&units=none&left_color=grey&right_color=brightgreen&left_text=Downloads)](https://pepy.tech/project/sng4onnx) ![GitHub](https://img.shields.io/github/license/PINTO0309/sng4onnx?color=2BAF2B) [![PyPI](https://img.shields.io/pypi/v/sng4onnx?color=2BAF2B)](https://pypi.org/project/sng4onnx/) [![CodeQL](https://github.com/PINTO0309/sng4onnx/workflows/CodeQL/badge.svg)](https://github.com/PINTO0309/sng4onnx/actions?query=workflow%3ACodeQL)



  



# Key concept

- [x] Automatically generates and assigns an OP name to each OP in an old format ONNX file.

## 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 sng4onnx

```

### 1-2. Docker

https://github.com/PINTO0309/simple-onnx-processing-tools#docker

## 2. CLI Usage

```

$ sng4onnx -h

usage:

  sng4onnx [-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 sng4onnx import generate

>>> help(generate)

Help on function generate in module sng4onnx.onnx_opname_generator:

generate(

    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

$ sng4onnx \

--input_onnx_file_path emotion-ferplus-8.onnx \

--output_onnx_file_path emotion-ferplus-8_renamed.onnx

```

## 5. In-script Execution

```python

from sng4onnx import generate

onnx_graph = generate(

  input_onnx_file_path="fusionnet_180x320.onnx",

  output_onnx_file_path="fusionnet_180x320_renamed.onnx",

)

```

## 6. Sample

https://github.com/onnx/models/blob/main/vision/classification/resnet/model/resnet18-v1-7.onnx

### Before

![image](https://user-images.githubusercontent.com/33194443/195632927-75c76b9a-a14b-411c-8932-f114dc2b9f29.png)

### After

![image](https://user-images.githubusercontent.com/33194443/195633029-86b0ebec-3df5-4dc4-b0ec-079f4f063e46.png)

## 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