Very simple NCHW and NHWC conversion tool for ONNX. Change to the specified input order for each and every input OP. Also, change the channel order of RGB and BGR. Simple Channel Converter for ONNX.

Last update: Dec 22, 2022

Related tags

Overview

scc4onnx

Very simple NCHW and NHWC conversion tool for ONNX. Change to the specified input order for each and every input OP. Also, change the channel order of RGB and BGR. Simple Channel Converter for ONNX.

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

Key concept

Allow the user to specify the name of the input OP to change the input order.
All number of dimensions can be freely changed, not only 4 dimensions such as NCHW and NHWC.
Simply rewrite the input order of the input OP to the specified order and extrapolate Transpose after the input OP so that it does not affect the processing of subsequent OPs.
Allows the user to change the channel order of RGB and BGR by specifying options.

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 scc4onnx

1-2. Docker

### docker pull
$ docker pull pinto0309/scc4onnx:latest

### docker build
$ docker build -t pinto0309/scc4onnx:latest .

### docker run
$ docker run --rm -it -v `pwd`:/workdir pinto0309/scc4onnx:latest
$ cd /workdir

2. CLI Usage

$ scc4onnx -h

usage:
  scc4onnx [-h]
  --input_onnx_file_path INPUT_ONNX_FILE_PATH
  --output_onnx_file_path OUTPUT_ONNX_FILE_PATH
  [--input_op_names_and_order_dims INPUT_OP_NAME ORDER_DIM]
  [--channel_change_inputs INPUT_OP_NAME DIM]
  [--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.

  --input_op_names_and_order_dims INPUT_OP_NAME ORDER_DIM
      Specify the name of the input_op to be dimensionally changed and the order of the
      dimensions after the change.
      The name of the input_op to be dimensionally changed can be specified multiple times.

      e.g.
      --input_op_names_and_order_dims aaa [0,3,1,2] \
      --input_op_names_and_order_dims bbb [0,2,3,1] \
      --input_op_names_and_order_dims ccc [0,3,1,2,4,5]

  --channel_change_inputs INPUT_OP_NAME DIM
      Change the channel order of RGB and BGR.
      If the original model is RGB, it is transposed to BGR.
      If the original model is BGR, it is transposed to RGB.
      It can be selectively specified from among the OP names specified
      in --input_op_names_and_order_dims.
      OP names not specified in --input_op_names_and_order_dims are ignored.
      Multiple times can be specified as many times as the number of OP names specified
      in --input_op_names_and_order_dims.
      --channel_change_inputs op_name dimension_number_representing_the_channel
      dimension_number_representing_the_channel must specify the dimension position before
      the change in input_op_names_and_order_dims.
      For example, dimension_number_representing_the_channel is 1 for NCHW and 3 for NHWC.

      e.g.
      --channel_change_inputs aaa 3 \
      --channel_change_inputs bbb 1 \
      --channel_change_inputs ccc 5

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

3. In-script Usage

$ python
>>> from scc4onnx import order_conversion
>>> help(order_conversion)
Help on function order_conversion in module scc4onnx.onnx_input_order_converter:

order_conversion(
  input_op_names_and_order_dims: Union[dict, NoneType] = None,
  channel_change_inputs: Union[dict, NoneType] = None,
  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
    ----------
    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.
    
    input_op_names_and_order_dims: Optional[dict]
        Specify the name of the input_op to be dimensionally changed and
        the order of the dimensions after the change.
        The name of the input_op to be dimensionally changed
        can be specified multiple times.
    
        e.g.
        input_op_names_and_order_dims = {
            "input_op_name1": [0,3,1,2],
            "input_op_name2": [0,2,3,1],
            "input_op_name3": [0,3,1,2,4,5],
        }
    
    channel_change_inputs: Optional[dict]
        Change the channel order of RGB and BGR.
        If the original model is RGB, it is transposed to BGR.
        If the original model is BGR, it is transposed to RGB.
        It can be selectively specified from among the OP names
        specified in input_op_names_and_order_dims.
        OP names not specified in input_op_names_and_order_dims are ignored.
        Multiple times can be specified as many times as the number
        of OP names specified in input_op_names_and_order_dims.
        channel_change_inputs = {"op_name": dimension_number_representing_the_channel}
        dimension_number_representing_the_channel must specify
        the dimension position after the change in input_op_names_and_order_dims.
        For example, dimension_number_representing_the_channel is 1 for NCHW and 3 for NHWC.
    
        e.g.
        channel_change_inputs = {
            "aaa": 1,
            "bbb": 3,
            "ccc": 2,
        }
    
    non_verbose: Optional[bool]
        Do not show all information logs. Only error logs are displayed.
        Default: False
    
    Returns
    -------
    order_converted_graph: onnx.ModelProto
        Order converted onnx ModelProto

4. CLI Execution

$ scc4onnx \
--input_onnx_file_path crestereo_next_iter2_240x320.onnx \
--output_onnx_file_path crestereo_next_iter2_240x320_ord.onnx \
--input_op_names_and_order_dims left [0,2,3,1] \
--input_op_names_and_order_dims right [0,2,3,1] \
--channel_change_inputs left 1 \
--channel_change_inputs right 1

5. In-script Execution

from scc4onnx import order_conversion

order_converted_graph = order_conversion(
    onnx_graph=graph,
    input_op_names_and_order_dims={"left": [0,2,3,1], "right": [0,2,3,1]},
    channel_change_inputs={"left": 1, "right": 1},
    non_verbose=True,
)

6. Sample

6-1. Transpose only

$ scc4onnx \
--input_onnx_file_path crestereo_next_iter2_240x320.onnx \
--output_onnx_file_path crestereo_next_iter2_240x320_ord.onnx \
--input_op_names_and_order_dims left [0,2,3,1] \
--input_op_names_and_order_dims right [0,2,3,1]

6-2. Transpose + RGB<->BGR

$ scc4onnx \
--input_onnx_file_path crestereo_next_iter2_240x320.onnx \
--output_onnx_file_path crestereo_next_iter2_240x320_ord.onnx \
--input_op_names_and_order_dims left [0,2,3,1] \
--input_op_names_and_order_dims right [0,2,3,1] \
--channel_change_inputs left 1 \
--channel_change_inputs right 1

6-3. RGB<->BGR only

$ scc4onnx \
--input_onnx_file_path crestereo_next_iter2_240x320.onnx \
--output_onnx_file_path crestereo_next_iter2_240x320_ord.onnx \
--channel_change_inputs left 1 \
--channel_change_inputs right 1

7. Issues

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

Releases(1.0.5)

1.0.5(Sep 9, 2022)

Add short form parameter

$ scc4onnx -h

usage:
  scc4onnx [-h]
  -if INPUT_ONNX_FILE_PATH
  -of OUTPUT_ONNX_FILE_PATH
  [-ioo INPUT_OP_NAME ORDER_DIM]
  [-cci INPUT_OP_NAME DIM]
  [-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.

  -ioo INPUT_OP_NAMES_AND_ORDER_DIMS INPUT_OP_NAMES_AND_ORDER_DIMS, --input_op_names_and_order_dims INPUT_OP_NAMES_AND_ORDER_DIMS INPUT_OP_NAMES_AND_ORDER_DIMS
      Specify the name of the input_op to be dimensionally changed and the order of the
      dimensions after the change.
      The name of the input_op to be dimensionally changed can be specified multiple times.

      e.g.
      --input_op_names_and_order_dims aaa [0,3,1,2] \
      --input_op_names_and_order_dims bbb [0,2,3,1] \
      --input_op_names_and_order_dims ccc [0,3,1,2,4,5]

  -cci CHANNEL_CHANGE_INPUTS CHANNEL_CHANGE_INPUTS, --channel_change_inputs CHANNEL_CHANGE_INPUTS CHANNEL_CHANGE_INPUTS
      Change the channel order of RGB and BGR.
      If the original model is RGB, it is transposed to BGR.
      If the original model is BGR, it is transposed to RGB.
      It can be selectively specified from among the OP names specified
      in --input_op_names_and_order_dims.
      OP names not specified in --input_op_names_and_order_dims are ignored.
      Multiple times can be specified as many times as the number of OP names specified
      in --input_op_names_and_order_dims.
      --channel_change_inputs op_name dimension_number_representing_the_channel
      dimension_number_representing_the_channel must specify the dimension position before
      the change in input_op_names_and_order_dims.
      For example, dimension_number_representing_the_channel is 1 for NCHW and 3 for NHWC.

      e.g.
      --channel_change_inputs aaa 3 \
      --channel_change_inputs bbb 1 \
      --channel_change_inputs ccc 5

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

Full Changelog: https://github.com/PINTO0309/scc4onnx/compare/1.0.4...1.0.5

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

1.0.4(May 25, 2022)
Security update

README update

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

Source code(tar.gz)
Source code(zip)
1.0.2(May 10, 2022)
Modified to give op_name to extrapolated Transpose

e.g. input_order_convert_transpose_0, input_order_convert_transpose_1, ...

Source code(tar.gz)
Source code(zip)
1.0.1(Apr 19, 2022)
Code refactoring

Source code(tar.gz)
Source code(zip)
1.0.0(Apr 18, 2022)
Initial release

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

Python script for performing depth completion from sparse depth and rgb images using the msg_chn_wacv20. model in ONNX

ONNX msg_chn_wacv20 depth completion Python script for performing depth completion from sparse depth and rgb images using the msg_chn_wacv20 model in

19 Oct 22, 2022

A Planar RGB-D SLAM which utilizes Manhattan World structure to provide optimal camera pose trajectory while also providing a sparse reconstruction containing points, lines and planes, and a dense surfel-based reconstruction.

ManhattanSLAM Authors: Raza Yunus, Yanyan Li and Federico Tombari ManhattanSLAM is a real-time SLAM library for RGB-D cameras that computes the camera

117 Dec 28, 2022

Using Streamlit to host a multi-page tool with model specs and classification metrics, while also accepting user input values for prediction.

Predicitng_viability Using Streamlit to host a multi-page tool with model specs and classification metrics, while also accepting user input values for

1 Nov 8, 2021

Python project to take sound as input and output as RGB + Brightness values suitable for DMX

sound-to-light Python project to take sound as input and output as RGB + Brightness values suitable for DMX Current goals: Get one pixel working: Vary

1 Nov 17, 2021

Feed forward VQGAN-CLIP model, where the goal is to eliminate the need for optimizing the latent space of VQGAN for each input prompt

Feed forward VQGAN-CLIP model, where the goal is to eliminate the need for optimizing the latent space of VQGAN for each input prompt. This is done by

135 Dec 30, 2022

An executor that loads ONNX models and embeds documents using the ONNX runtime.

ONNXEncoder An executor that loads ONNX models and embeds documents using the ONNX runtime. Usage via Docker image (recommended) from jina import Flow

2 Mar 15, 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

A repository that shares tuning results of trained models generated by TensorFlow / Keras. Post-training quantization (Weight Quantization, Integer Quantization, Full Integer Quantization, Float16 Quantization), Quantization-aware training. TensorFlow Lite. OpenVINO. CoreML. TensorFlow.js. TF-TRT. MediaPipe. ONNX. [.tflite,.h5,.pb,saved_model,tfjs,tftrt,mlmodel,.xml/.bin, .onnx]

PINTO_model_zoo Please read the contents of the LICENSE file located directly under each folder before using the model. My model conversion scripts ar

2.4k Jan 5, 2023

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

18 Nov 6, 2022

Very simple NCHW and NHWC conversion tool for ONNX. Change to the specified input order for each and every input OP. Also, change the channel order of RGB and BGR. Simple Channel Converter for ONNX.

Related tags

Overview

scc4onnx

Key concept

1. Setup

1-1. HostPC

1-2. Docker

2. CLI Usage

3. In-script Usage

4. CLI Execution

5. In-script Execution

6. Sample

6-1. Transpose only

6-2. Transpose + RGB<->BGR

6-3. RGB<->BGR only

7. Issues

You might also like...

Python script for performing depth completion from sparse depth and rgb images using the msg_chn_wacv20. model in ONNX

A Planar RGB-D SLAM which utilizes Manhattan World structure to provide optimal camera pose trajectory while also providing a sparse reconstruction containing points, lines and planes, and a dense surfel-based reconstruction.

Using Streamlit to host a multi-page tool with model specs and classification metrics, while also accepting user input values for prediction.

Python project to take sound as input and output as RGB + Brightness values suitable for DMX

Feed forward VQGAN-CLIP model, where the goal is to eliminate the need for optimizing the latent space of VQGAN for each input prompt

An executor that loads ONNX models and embeds documents using the ONNX runtime.

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

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

Releases(1.0.5)

1.0.5(Sep 9, 2022)

1.0.4(May 25, 2022)

1.0.3(May 15, 2022)

1.0.2(May 10, 2022)

1.0.1(Apr 19, 2022)

1.0.0(Apr 18, 2022)

Owner

Katsuya Hyodo

Pytorch implementation of the paper "Topic Modeling Revisited: A Document Graph-based Neural Network Perspective"

Network Pruning That Matters: A Case Study on Retraining Variants (ICLR 2021)

implicit displacement field

Code release for NeRF (Neural Radiance Fields)

Python scripts form performing stereo depth estimation using the CoEx model in ONNX.

Learning from Synthetic Shadows for Shadow Detection and Removal [Inoue+, IEEE TCSVT 2020].

(under submission) Bayesian Integration of a Generative Prior for Image Restoration

SketchEdit: Mask-Free Local Image Manipulation with Partial Sketches

Code for the paper "Next Generation Reservoir Computing"

Discovering Dynamic Salient Regions with Spatio-Temporal Graph Neural Networks

Pytorch implementation of AngularGrad: A New Optimization Technique for Angular Convergence of Convolutional Neural Networks

CLIP: Connecting Text and Image (Learning Transferable Visual Models From Natural Language Supervision)

Repository containing the PhD Thesis "Formal Verification of Deep Reinforcement Learning Agents"

An implementation of MobileFormer

Non-Official Pytorch implementation of "Face Identity Disentanglement via Latent Space Mapping" https://arxiv.org/abs/2005.07728 Using StyleGAN2 instead of StyleGAN

HyperLib: Deep learning in the Hyperbolic space

Implementation of Memory-Compressed Attention, from the paper "Generating Wikipedia By Summarizing Long Sequences"

An Agnostic Computer Vision Framework - Pluggable to any Training Library: Fastai, Pytorch-Lightning with more to come

The official repo of the CVPR2021 oral paper: Representative Batch Normalization with Feature Calibration

Process text, including tokenizing and representing sentences as vectors and Applying some concepts like RNN, LSTM and GRU to create a classifier can detect the language in which a sentence is written from among 17 languages.