sne4onnx 1.0.2

A very simple tool for situations where optimization with onnx-simplifier would exceed the Protocol Buffers upper file size limit of 2GB, or simply to separate onnx files to any size you want. Simple Network Extraction for ONNX.

sne4onnx

A very simple tool for situations where optimization with onnx-simplifier would exceed the Protocol Buffers upper file size limit of 2GB, or simply to separate onnx files to any size you want. Simple Network Extraction for ONNX.

Key concept

• If INPUT OP name and OUTPUT OP name are specified, the onnx graph within the range of the specified OP name is extracted and .onnx is generated.

1. Setup

1-1. HostPC

### option
$ echo export PATH="~/.local/bin:$PATH" >> ~/.bashrc \
&& source ~/.bashrc

### run
$ pip install -U onnx \
&& pip install -U sne4onnx

1-2. Docker

### docker pull
$ docker pull pinto0309/sne4onnx:latest

### docker build
$ docker build -t pinto0309/sne4onnx:latest .

### docker run
$ docker run --rm -it -v `pwd`:/workdir pinto0309/sne4onnx:latest
$ cd /workdir

2. CLI Usage

$ sne4onnx -h

usage:
    sne4onnx [-h] \
    --input_onnx_file_path INPUT_ONNX_FILE_PATH \
    --output_onnx_file_path OUTPUT_ONNX_FILE_PATH \
    --input_op_names INPUT_OP_NAMES \
    --output_op_names OUTPUT_OP_NAMES

optional arguments:
  -h, --help
        show this help message and exit
  --input_onnx_file_path INPUT_ONNX_FILE_PATH
        Input onnx file path.
  --output_onnx_file_path OUTPUT_ONNX_FILE_PATH
        Output onnx file path.
  --input_op_names INPUT_OP_NAMES
        List of OP names to specify for the input layer of the model.
        Specify the name of the OP, separated by commas.
        e.g. --input_op_names aaa,bbb,ccc
  --output_op_names OUTPUT_OP_NAMES
        List of OP names to specify for the output layer of the model.
        Specify the name of the OP, separated by commas.
        e.g. --output_op_names ddd,eee,fff

3. In-script Usage

$ python
>>> from sne4onnx import extraction
>>> help(extraction)

Help on function extraction in module sne4onnx.onnx_network_extraction:

extraction(
    input_onnx_file_path: str,
    output_onnx_file_path: str,
    input_op_names: List[str],
    output_op_names: List[str]
)

    Parameters
    ----------
    input_onnx_file_path: str
        Input onnx file path.

    output_onnx_file_path: str
        Output onnx file path.

    input_op_names: List[str]
        List of OP names to specify for the input layer of the model.
        Specify the name of the OP, separated by commas.
        e.g. ['aaa','bbb','ccc']

    output_op_names: List[str]
        List of OP names to specify for the output layer of the model.
        Specify the name of the OP, separated by commas.
        e.g. ['ddd','eee','fff']

4. CLI Execution

$ sne4onnx \
--input_onnx_file_path input.onnx \
--output_onnx_file_path output.onnx \
--input_op_names aaa,bbb,ccc \
--output_op_names ddd,eee,fff

5. In-script Execution

from sne4onnx import extraction

extraction(
  input_onnx_file_path='input.onnx',
  output_onnx_file_path='output.onnx',
  input_op_names=['aaa', 'bbb', 'ccc'],
  output_op_names=['ddd', 'eee', 'fff'],
)

6. Samples

6-1. Pre-extraction

6-2. Extraction

$ sne4onnx \
--input_onnx_file_path hitnet_sf_finalpass_720x1280.onnx \
--output_onnx_file_path hitnet_sf_finalpass_720x960_head.onnx \
--input_op_names 0,1 \
--output_op_names 497,785

6-3. Extracted

7. Reference

1. https://github.com/onnx/onnx/blob/main/docs/PythonAPIOverview.md
2. https://github.com/PINTO0309/snd4onnx
3. https://github.com/PINTO0309/scs4onnx
4. https://github.com/PINTO0309/snc4onnx