A very simple tool to rewrite parameters such as attributes and constants for OPs in ONNX models. Simple Attribute and Constant Modifier for ONNX.

Last update: May 15, 2022

Related tags

Overview

sam4onnx

A very simple tool to rewrite parameters such as attributes and constants for OPs in ONNX models. Simple Attribute and Constant Modifier for ONNX.

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

Key concept

Specify an arbitrary OP name and Constant type INPUT name or an arbitrary OP name and Attribute name, and pass the modified constants to rewrite the parameters of the relevant OP.
Two types of input are accepted: .onnx file input and onnx.ModelProto format objects.
To design the operation to be simple, only a single OP can be specified.
Attributes and constants are forcibly rewritten, so the integrity of the entire graph is not checked in detail.

1. Setup

1-1. HostPC

### 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 sam4onnx

1-2. Docker

### docker pull
$ docker pull pinto0309/sam4onnx:latest

### docker build
$ docker build -t pinto0309/sam4onnx:latest .

### docker run
$ docker run --rm -it -v `pwd`:/workdir pinto0309/sam4onnx:latest
$ cd /workdir

2. CLI Usage

$ sam4onnx -h

usage:
    sam4onnx [-h]
    --input_onnx_file_path INPUT_ONNX_FILE_PATH
    --output_onnx_file_path OUTPUT_ONNX_FILE_PATH
    [--op_name OP_NAME]
    [--attributes NAME DTYPE VALUE]
    [--input_constants NAME DTYPE VALUE]
    [--non_verbose]

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.

  --op_name OP_NAME
        OP name of the attributes to be changed.
        When --attributes is specified, --op_name must always be specified.
        e.g. --op_name aaa

  --attributes NAME DTYPE VALUE
        Parameter to change the attribute of the OP specified in --op_name.
        If the OP specified in --op_name has no attributes,
        it is ignored. attributes can be specified multiple times.
        --attributes name dtype value dtype is one of
        "float32" or "float64" or "int32" or "int64" or "str".
        https://github.com/onnx/onnx/blob/main/docs/Operators.md

        e.g.
        --attributes alpha float32 [[1.0]]
        --attributes beta float32 [1.0]
        --attributes transA int64 0
        --attributes transB int64 0

  --input_constants NAME DTYPE VALUE
        Specifies the name of the constant to be changed.
        If you want to change only the constant,
        you do not need to specify --op_name and --attributes.
        input_constants can be specified multiple times.
        --input_constants constant_name numpy.dtype value

        e.g.
        --input_constants constant_name1 int64 0
        --input_constants constant_name2 float32 [[1.0,2.0,3.0],[4.0,5.0,6.0]]

  --non_verbose
        Do not show all information logs. Only error logs are displayed.

3. In-script Usage

$ python
>>> from sam4onnx import modify
>>> help(modify)
Help on function modify in module sam4onnx.onnx_attr_const_modify:

modify(
    input_onnx_file_path: Union[str, NoneType] = '',
    output_onnx_file_path: Union[str, NoneType] = '',
    onnx_graph: Union[onnx.onnx_ml_pb2.ModelProto, NoneType] = None,
    op_name: Union[str, NoneType] = '',
    attributes: Union[dict, NoneType] = None,
    input_constants: Union[dict, NoneType] = None,
    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.

    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.

    op_name: Optional[str]
        OP name of the attributes to be changed.
        When --attributes is specified, --op_name must always be specified.
        Default: ''
        https://github.com/onnx/onnx/blob/main/docs/Operators.md

    attributes: Optional[dict]
        Specify output attributes for the OP to be generated.
        See below for the attributes that can be specified.

        {"attr_name1": numpy.ndarray, "attr_name2": numpy.ndarray, ...}

        e.g. attributes =
            {
                "alpha": np.asarray(1.0, dtype=np.float32),
                "beta": np.asarray(1.0, dtype=np.float32),
                "transA": np.asarray(0, dtype=np.int64),
                "transB": np.asarray(0, dtype=np.int64)
            }
        Default: None
        https://github.com/onnx/onnx/blob/main/docs/Operators.md

    input_constants: Optional[dict]
        Specifies the name of the constant to be changed.
        If you want to change only the constant,
        you do not need to specify --op_name and --attributes.
        {"constant_name1": numpy.ndarray, "constant_name2": numpy.ndarray, ...}

        e.g.
        input_constants =
            {
                "constant_name1": np.asarray(0, dtype=np.int64),
                "constant_name2": np.asarray([[1.0,2.0,3.0],[4.0,5.0,6.0]], dtype=np.float32)
            }
        Default: None
        https://github.com/onnx/onnx/blob/main/docs/Operators.md

    non_verbose: Optional[bool]
        Do not show all information logs. Only error logs are displayed.
        Default: False

    Returns
    -------
    modified_graph: onnx.ModelProto
        Mddified onnx ModelProto

4. CLI Execution

$ sam4onnx \
--op_name Transpose_17 \
--input_onnx_file_path input.onnx \
--output_onnx_file_path output.onnx \
--attributes perm int64 [0,1]

5. In-script Execution

from sam4onnx import modify

modified_graph = modify(
    onnx_graph=graph,
    input_constants={"241": np.asarray([1], dtype=np.int64)},
    non_verbose=True,
)

6. Sample

6-1. Transpose - update `perm`

$ sam4onnx \
--op_name Transpose_17 \
--input_onnx_file_path hitnet_sf_finalpass_720x1280_nonopt.onnx \
--output_onnx_file_path hitnet_sf_finalpass_720x1280_nonopt_mod.onnx \
--attributes perm int64 [0,1]

6-2. Mul - update `Constant (170)` - From: `2`, To: `1`

$ sam4onnx \
--input_onnx_file_path hitnet_sf_finalpass_720x1280_nonopt.onnx \
--output_onnx_file_path hitnet_sf_finalpass_720x1280_nonopt_mod.onnx \
--input_constants 170 float32 1

6-3. Reshape - update `Constant (241)` - From: `[-1]`, To: `[1]`

$ sam4onnx \
--input_onnx_file_path hitnet_sf_finalpass_720x1280_nonopt.onnx \
--output_onnx_file_path hitnet_sf_finalpass_720x1280_nonopt_mod.onnx \
--input_constants 241 int64 [1]

7. Issues

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

You might also like...

Simple ONNX operation generator. Simple Operation Generator for ONNX.

sog4onnx Simple ONNX operation generator. Simple Operation Generator for ONNX. https://github.com/PINTO0309/simple-onnx-processing-tools Key concept V

6 May 15, 2022

Implementation of Common Image Evaluation Metrics by Sayed Nadim (sayednadim.github.io). The repo is built based on full reference image quality metrics such as L1, L2, PSNR, SSIM, LPIPS. and feature-level quality metrics such as FID, IS. It can be used for evaluating image denoising, colorization, inpainting, deraining, dehazing etc. where we have access to ground truth.

Image Quality Evaluation Metrics Implementation of some common full reference image quality metrics. The repo is built based on full reference image q

10 Jan 1, 2023

Milano is a tool for automating hyper-parameters search for your models on a backend of your choice.

Milano (This is a research project, not an official NVIDIA product.) Documentation https://nvidia.github.io/Milano Milano (Machine learning autotuner

147 Dec 17, 2022

CBREN: Convolutional Neural Networks for Constant Bit Rate Video Quality Enhancement

CBREN This is the Pytorch implementation for our IEEE TCSVT paper : CBREN: Convolutional Neural Networks for Constant Bit Rate Video Quality Enhanceme

3 Nov 4, 2022

ONNX Runtime Web demo is an interactive demo portal showing real use cases running ONNX Runtime Web in VueJS.

ONNX Runtime Web demo is an interactive demo portal showing real use cases running ONNX Runtime Web in VueJS. It currently supports four examples for you to quickly experience the power of ONNX Runtime Web.

58 Dec 18, 2022

ONNX-GLPDepth - Python scripts for performing monocular depth estimation using the GLPDepth model in ONNX

18 Nov 6, 2022

ONNX-PackNet-SfM: Python scripts for performing monocular depth estimation using the PackNet-SfM model in ONNX

Python scripts for performing monocular depth estimation using the PackNet-SfM model in ONNX

14 Dec 9, 2022

Quickly comparing your image classification models with the state-of-the-art models (such as DenseNet, ResNet, ...)

Image Classification Project Killer in PyTorch This repo is designed for those who want to start their experiments two days before the deadline and ki

349 Dec 8, 2022

Ranger deep learning optimizer rewrite to use newest components

Ranger21 - integrating the latest deep learning components into a single optimizer Ranger deep learning optimizer rewrite to use newest components Ran

266 Dec 28, 2022

Releases(1.0.12)

1.0.12(Jan 2, 2023)
What's Changed

Support for models with custom domains by @PINTO0309 in https://github.com/PINTO0309/sam4onnx/pull/2

New Contributors

@PINTO0309 made their first contribution in https://github.com/PINTO0309/sam4onnx/pull/2

Full Changelog: https://github.com/PINTO0309/sam4onnx/compare/1.0.11...1.0.12
Source code(tar.gz)
Source code(zip)

1.0.11(Sep 8, 2022)

Add short form parameter

$ sam4onnx -h

usage:
    sam4onnx [-h]
    -if INPUT_ONNX_FILE_PATH
    -of OUTPUT_ONNX_FILE_PATH
    [-on OP_NAME]
    [-a NAME DTYPE VALUE]
    [-da DELETE_ATTRIBUTES [DELETE_ATTRIBUTES ...]]
    [-ic NAME DTYPE VALUE]
    [-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.

  -on OP_NAME, --op_name OP_NAME
    OP name of the attributes to be changed.
    When --attributes is specified, --op_name must always be specified.
    e.g. --op_name aaa

  -a ATTRIBUTES ATTRIBUTES ATTRIBUTES, --attributes ATTRIBUTES ATTRIBUTES ATTRIBUTES
    Parameter to change the attribute of the OP specified in --op_name.
    If the OP specified in --op_name has no attributes,
    it is ignored. attributes can be specified multiple times.
    --attributes name dtype value dtype is one of
    "float32" or "float64" or "int32" or "int64" or "str".
    https://github.com/onnx/onnx/blob/main/docs/Operators.md

    e.g.
    --attributes alpha float32 [[1.0]]
    --attributes beta float32 [1.0]
    --attributes transA int64 0
    --attributes transB int64 0

  -da DELETE_ATTRIBUTES [DELETE_ATTRIBUTES ...], --delete_attributes DELETE_ATTRIBUTES [DELETE_ATTRIBUTES ...]
    Parameter to delete the attribute of the OP specified in --op_name.
    If the OP specified in --op_name has no attributes,
    it is ignored. delete_attributes can be specified multiple times.
    --delete_attributes name1 name2 name3
    https://github.com/onnx/onnx/blob/main/docs/Operators.md

    e.g. --delete_attributes alpha beta

  -ic INPUT_CONSTANTS INPUT_CONSTANTS INPUT_CONSTANTS, --input_constants INPUT_CONSTANTS INPUT_CONSTANTS INPUT_CONSTANTS
    Specifies the name of the constant to be changed.
    If you want to change only the constant,
    you do not need to specify --op_name and --attributes.
    input_constants can be specified multiple times.
    --input_constants constant_name numpy.dtype value

    e.g.
    --input_constants constant_name1 int64 0
    --input_constants constant_name2 float32 [[1.0,2.0,3.0],[4.0,5.0,6.0]]
    --input_constants constant_name3 float32 [\'-Infinity\']

  -n, --non_verbose
    Do not show all information logs. Only error logs are displayed.

Source code(tar.gz)
Source code(zip)

1.0.10(Aug 7, 2022)
Supports the specification of -np.inf, -np.inf, "Infinity", and "-Infinity"

Source code(tar.gz)
Source code(zip)
1.0.9(Jul 17, 2022)
Support for constant rewriting when the same constant is shared. Valid only when op_name is specified. Generates a new constant that is different from the shared constant.

Reshape_156 onnx::Reshape_391 int64 [1, -1, 85]

Reshape_174 onnx::Reshape_391 int64 [1, -1, 85]

sam4onnx \ --input_onnx_file_path yolov7-tiny_test_sim.onnx \ --output_onnx_file_path yolov7-tiny_test_sim_mod.onnx \ --op_name Reshape_156 \ --input_constants onnx::Reshape_391 int64 [1,14400,85]

Reshape_156 onnx::Reshape_391 int64 [1, -1, 85] -> Reshape_156 onnx::Reshape_391_mod_3 int64 [1, 14400, 85]

Reshape_174 onnx::Reshape_391 int64 [1, -1, 85]

Source code(tar.gz)
Source code(zip)
1.0.8(Jun 7, 2022)
string attributes bug fixes

Source code(tar.gz)
Source code(zip)
1.0.7(May 25, 2022)
Security update

README update

Source code(tar.gz)
Source code(zip)
1.0.6(May 15, 2022)
eval() -> ast.literal_eval()

Source code(tar.gz)
Source code(zip)
1.0.5(May 12, 2022)
Fixed a bug that caused rewriting of direct constants to fail

Source code(tar.gz)
Source code(zip)
1.0.4(May 5, 2022)
Support for deletion of attributes

Source code(tar.gz)
Source code(zip)
1.0.3(May 5, 2022)
Support for additional attributes

Note that the correct attribute set according to the OP's opset is not checked, so any attribute can be added.

The figure below shows the addition of the attribute perm to Reshape, which does not originally exist.

Source code(tar.gz)
Source code(zip)
1.0.2(May 3, 2022)
Performance Improvement

Source code(tar.gz)
Source code(zip)
1.0.1(Apr 16, 2022)
Small fixes

Source code(tar.gz)
Source code(zip)
1.0.0(Apr 15, 2022)
Initial release

Source code(tar.gz)
Source code(zip)

Owner

Katsuya Hyodo

Hobby programmer. Intel Software Innovator Program member.

GitHub Repository

Job-Recommend-Competition - Vectorwise Interpretable Attentions for Multimodal Tabular Data

SiD - Simple Deep Model Vectorwise Interpretable Attentions for Multimodal Tabul

40 Dec 22, 2022

Pytorch implementation for "Large-Scale Long-Tailed Recognition in an Open World" (CVPR 2019 ORAL)

Large-Scale Long-Tailed Recognition in an Open World [Project] [Paper] [Blog] Overview Open Long-Tailed Recognition (OLTR) is the author's re-implemen

761 Dec 26, 2022

Programming with Neural Surrogates of Programs

0 Dec 12, 2021

Image-to-Image Translation with Conditional Adversarial Networks (Pix2pix) implementation in keras

pix2pix-keras Pix2pix implementation in keras. Original paper: Image-to-Image Translation with Conditional Adversarial Networks (pix2pix) Paper Author

141 Dec 30, 2022

Kaggle DSTL Satellite Imagery Feature Detection

206 Oct 29, 2022

Element selection for functional materials discovery by integrated machine learning of atomic contributions to properties

Element selection for functional materials discovery by integrated machine learning of atomic contributions to properties 8.11.2021 Andrij Vasylenko I

4 Dec 20, 2022

AI Flow is an open source framework that bridges big data and artificial intelligence.

Flink AI Flow Introduction Flink AI Flow is an open source framework that bridges big data and artificial intelligence. It manages the entire machine

144 Dec 30, 2022

Impelmentation for paper Feature Generation and Hypothesis Verification for Reliable Face Anti-Spoofing

FGHV Impelmentation for paper Feature Generation and Hypothesis Verification for Reliable Face Anti-Spoofing Requirements Python 3.6 Pytorch 1.5.0 Cud

5 Jun 02, 2022

Phy-Q: A Benchmark for Physical Reasoning

Phy-Q: A Benchmark for Physical Reasoning Cheng Xue*, Vimukthini Pinto*, Chathura Gamage* Ekaterina Nikonova, Peng Zhang, Jochen Renz School of Comput

29 Dec 19, 2022

Code for the tech report Toward Training at ImageNet Scale with Differential Privacy

Differentially private Imagenet training Code for the tech report Toward Training at ImageNet Scale with Differential Privacy by Alexey Kurakin, Steve

29 Nov 03, 2022

Official code repository for the publication "Latent Equilibrium: A unified learning theory for arbitrarily fast computation with arbitrarily slow neurons"

Latent Equilibrium: A unified learning theory for arbitrarily fast computation with arbitrarily slow neurons This repository contains the code to repr

3 Aug 04, 2022

[CVPR 2022 Oral] Versatile Multi-Modal Pre-Training for Human-Centric Perception

Versatile Multi-Modal Pre-Training for Human-Centric Perception Fangzhou Hong1 Liang Pan1 Zhongang Cai1,2,3 Ziwei Liu1* 1S-Lab, Nanyang Technologic

96 Jan 03, 2023

This repository contains the source code for the paper "DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networks",

DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networks Project Page | Video | Presentation | Paper | Data L

281 Dec 22, 2022

A Domain-Agnostic Benchmark for Self-Supervised Learning

DABS: A Domain Agnostic Benchmark for Self-Supervised Learning This repository contains the code for DABS, a benchmark for domain-agnostic self-superv

81 Dec 09, 2022

Angora is a mutation-based fuzzer. The main goal of Angora is to increase branch coverage by solving path constraints without symbolic execution.

Angora Angora is a mutation-based coverage guided fuzzer. The main goal of Angora is to increase branch coverage by solving path constraints without s

833 Jan 07, 2023

To propose and implement a multi-class classification approach to disaster assessment from the given data set of post-earthquake satellite imagery.

2 Jan 05, 2022

Planner_backend - Academic planner application designed for students and counselors.

Planner (backend) Academic planner application designed for students and advisors.

2 Dec 31, 2021