onnxconverter-common | Common utilities for ONNX converters | Machine Learning library

by microsoft Python Version: 1.14.0 License: MIT

X-Ray Key Features Code Snippets(1)Community Discussions(1)Vulnerabilities Install Support

kandi X-RAY | onnxconverter-common Summary

onnxconverter-common is a Python library typically used in Artificial Intelligence, Machine Learning applications. onnxconverter-common has no bugs, it has no vulnerabilities, it has build file available, it has a Permissive License and it has low support. You can install using 'pip install onnxconverter-common' or download it from GitHub, PyPI.

The onnxconverter-common package provides common functions and utilities for use in converters from various AI frameworks to ONNX. It also enables the different converters to work together to convert a model from mixed frameworks, like a scikit-learn pipeline embedding a xgboost model.

Support

Quality

Security

License

Reuse

Support

onnxconverter-common has a low active ecosystem.

It has 170 star(s) with 58 fork(s). There are 16 watchers for this library.

There were 1 major release(s) in the last 12 months.

There are 6 open issues and 31 have been closed. On average issues are closed in 208 days. There are 5 open pull requests and 0 closed requests.

It has a neutral sentiment in the developer community.

The latest version of onnxconverter-common is 1.14.0

Quality

onnxconverter-common has 0 bugs and 0 code smells.

Security

onnxconverter-common has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.

onnxconverter-common code analysis shows 0 unresolved vulnerabilities.

There are 0 security hotspots that need review.

License

onnxconverter-common is licensed under the MIT License. This license is Permissive.

Permissive licenses have the least restrictions, and you can use them in most projects.

Reuse

onnxconverter-common releases are available to install and integrate.

Deployable package is available in PyPI.

Build file is available. You can build the component from source.

onnxconverter-common saves you 2291 person hours of effort in developing the same functionality from scratch.

It has 5005 lines of code, 516 functions and 27 files.

It has high code complexity. Code complexity directly impacts maintainability of the code.

Top functions reviewed by kandi - BETA

kandi has reviewed onnxconverter-common and discovered the below as its top functions. This is intended to give you an instant insight into onnxconverter-common implemented functionality, and help decide if they suit your requirements.

Transpose this node to the given list of nodes
Process inputs
Generate a new name for a given type or function
Apply a function to inputs
Creates a Tile operator
Return the name of the given op_type
Convert model to python code
Convert an ONNX field to a python object
Remove all files in a directory
Apply a fanin adjustment
Applies the convolutionalization to node_list
Calculates the output shape of an operator
Renames a single variable
Applies a parametric softplus operator
Applies crop height
Finds the solution for the given node
Apply a downsampling operator
Apply a pad operator
Convert float to float16 model
Apply a scaled tanh operator
Apply Cast operator
Create a new ONNX node
Apply the permutation to node_list
Processes a transpose squeeze
Apply the adjoints to the node list
Apply a split operator

Get all kandi verified functions for this library.

onnxconverter-common Key Features

No Key Features are available at this moment for onnxconverter-common.

onnxconverter-common Examples and Code Snippets

How to convert Tensorflow 2.* trained with Keras model to .onnx format?

Python

Lines of Code : 3

License : Strong Copyleft (CC BY-SA 4.0)

Copy

pip install git+https://github.com/microsoft/onnxconverter-common
pip install git+https://github.com/onnx/keras-onnx

Community Discussions

Trending Discussions on onnxconverter-common

Why keras2onnx.convert_keras() function keeps getting me error "'KerasTensor' object has no attribute 'graph'"

QUESTION

Why keras2onnx.convert_keras() function keeps getting me error "'KerasTensor' object has no attribute 'graph'"

Asked 2021-Mar-10 at 15:00

I have a trained model (Which I trained myself), which is a .h5 format, It works fine by itself, but I need to convert it to .onnx format for deploying it inside Unity Engine, I searched how to convert .h5 models to .onnx format and stumbled upon keras2onnx library, and following some tutorials I got this:

...

ANSWER

Answered 2021-Mar-10 at 15:00

Not directly answer's your question, but a workaround:
You could try using the tf2onnx package for conversion.

The flow is to:

Export the model to Saved Model format.
Convert exported Saved Model to ONNX.

I had success converting the provided .h5 model:

Source https://stackoverflow.com/questions/66560370

Community Discussions, Code Snippets contain sources that include Stack Exchange Network

Vulnerabilities

No vulnerabilities reported

Install onnxconverter-common

You can install using 'pip install onnxconverter-common' or download it from GitHub, PyPI.
You can use onnxconverter-common like any standard Python library. You will need to make sure that you have a development environment consisting of a Python distribution including header files, a compiler, pip, and git installed. Make sure that your pip, setuptools, and wheel are up to date. When using pip it is generally recommended to install packages in a virtual environment to avoid changes to the system.

Support

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.microsoft.com. When you submit a pull request, a CLA-bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., label, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA. This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.

Find more information at: