npmpackage.info

Gathering detailed insights and metrics for onnxjs

Other packages similar to onnxjs

onnxjs-node

1.4.0

ONNXRuntime backend for ONNX.js

onnxjs-voka

0.1.8

A Javascript library for running ONNX models on browsers and on Node.js

onnxjs-tensor-checks-disabled

0.1.8

A Javascript library for running ONNX models on browsers and on Node.js

@s9y/onnxjs-dev

0.1.8

A Javascript library for running ONNX models on browsers and on Node.js

Gathering detailed insights and metrics for onnxjs

onnxjs

ONNX.js: run ONNX models using JavaScript

0.1.8

1,774

NOASSERTION

TypeScript

3.48 MB

234,506 4.2

Installations

npm install onnxjs

Developer Guide

BETA

Typescript

Yes

Module System

CommonJS, UMD

Node Version

12.18.0

NPM Version

6.14.4 Score

58.5

Supply Chain

99.3

Quality

Maintenance

100

Vulnerability

98.2

License

Pull Requests

Open

17

Total

197

Closed

31

Merged

149

Issues

Open

68

Total

122

Closed

54

Releases

ONNX.js v0.1.8

v0.1.8

Published on 28 Aug 2020

ONNX.js v0.1.7

v0.1.7

Published on 01 Jun 2019

ONNX.js v0.1.6

v0.1.6

Published on 26 Apr 2019

ONNX.js v0.1.5

v0.1.5

Published on 23 Mar 2019

ONNX.js v0.1.4

v0.1.4

Published on 04 Mar 2019

ONNX.js v0.1.3

v0.1.3

Published on 26 Jan 2019

View all 9 releases

Contributors

10,000

Unable to fetch Contributors

View all 10,000 contributors

Languages

TypeScript

C++

JavaScript

PureBasic

TypeScript (93%)

C++ (4.22%)

JavaScript (2.34%)

C (0.44%)

PureBasic (0.01%)

Developer

Microsoft

Download Statistics

Total Downloads

234,506

Last Day

Last Week

876

Last Month

4,589

Last Year

67,208

GitHub Statistics

1,774 Stars

148 Commits

127 Forks

39 Watching

31 Branches

10,000 Contributors

Maintainers

Package Meta Information

Latest Version

0.1.8

Package Id

onnxjs@0.1.8

Unpacked Size

3.48 MB

Size

745.94 kB

File Count

484

NPM Version

6.14.4

Node Version

12.18.0

Total Downloads

Cumulative downloads

Total Downloads

234,506

Last day

-77.6%

Compared to previous day

Last week

-17.7%

876

Compared to previous week

Last month

-10.4%

4,589

Compared to previous month

Last year

43.2%

67,208

Compared to previous year

Daily Downloads

Weekly Downloads

Monthly Downloads

Yearly Downloads

Versions

ONNX.js

ONNX.js is a Javascript library for running ONNX models on browsers and on Node.js.

ONNX.js has adopted WebAssembly and WebGL technologies for providing an optimized ONNX model inference runtime for both CPUs and GPUs.

Why ONNX models

The Open Neural Network Exchange (ONNX) is an open standard for representing machine learning models. The biggest advantage of ONNX is that it allows interoperability across different open source AI frameworks, which itself offers more flexibility for AI frameworks adoption. See Getting ONNX Models.

Why ONNX.js

With ONNX.js, web developers can score pre-trained ONNX models directly on browsers with various benefits of reducing server-client communication and protecting user privacy, as well as offering install-free and cross-platform in-browser ML experience.

ONNX.js can run on both CPU and GPU. For running on CPU, WebAssembly is adopted to execute the model at near-native speed. Furthermore, ONNX.js utilizes Web Workers to provide a "multi-threaded" environment to parallelize data processing. Empirical evaluation shows very promising performance gains on CPU by taking full advantage of WebAssembly and Web Workers. For running on GPUs, a popular standard for accessing GPU capabilities - WebGL is adopted. ONNX.js has further adopted several novel optimization techniques for reducing data transfer between CPU and GPU, as well as some techniques to reduce GPU processing cycles to further push the performance to the maximum.

See Compatibility and Operators Supported for a list of platforms and operators ONNX.js currently supports.

Benchmarks

Benchmarks have been run against the most prominent open source solutions in the same market. Below are the results collected for Chrome and Edge browsers on one sample machine (computations run on both CPU and GPU):

alt text

NOTE:

Keras.js doesn't support WebGL usage on Edge

Keras.js and TensorFlow.js don't support WebAssembly usage on any browser

The specs of the machine that was used to perform the benchmarking is listed below:

OS: Microsoft Windows 10 Enterprise Insider Preview

Model: HP Z240 Tower Workstation

Processor: Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz, 3401 Mhz, 4 Core(s), 8 Logical Processor(s)

Installed Physical Memory (RAM): 32.0 GB

GPU make / Chip type: AMD FirePro W2100 / AMD FirePro SDI (0x6608)

GPU Memory (approx.): 18.0 GB

Demo

ONNX.js demo website shows the capabilities of ONNX.js. Check the code.

Getting Started

There are multiple ways to use ONNX.js in a project:

Using `<script>` tag

This is the most straightforward way to use ONNX.js. The following HTML example shows how to use it:

1<html>
2  <head> </head>
3
4  <body>
5    <!-- Load ONNX.js -->
6    <script src="https://cdn.jsdelivr.net/npm/onnxjs/dist/onnx.min.js"></script>
7    <!-- Code that consume ONNX.js -->
8    <script>
9      // create a session
10      const myOnnxSession = new onnx.InferenceSession();
11      // load the ONNX model file
12      myOnnxSession.loadModel("./my-model.onnx").then(() => {
13        // generate model input
14        const inferenceInputs = getInputs();
15        // execute the model
16        myOnnxSession.run(inferenceInputs).then((output) => {
17          // consume the output
18          const outputTensor = output.values().next().value;
19          console.log(`model output tensor: ${outputTensor.data}.`);
20        });
21      });
22    </script>
23  </body>
24</html>

Refer to browser/Add for an example.

Using NPM and bundling tools

Modern browser based applications are usually built by frameworks like Angular, React, Vue.js and so on. This solution usually builds the source code into one or more bundle file(s). The following TypeScript example shows how to use ONNX.js in an async context:

Import Tensor and InferenceSession.

1import { Tensor, InferenceSession } from "onnxjs";

Create an instance of InferenceSession.

1const session = new InferenceSession();

Load the ONNX.js model

1// use the following in an async method
2const url = "./data/models/resnet/model.onnx";
3await session.loadModel(url);

Create your input Tensor(s) similar to the example below. You need to do any pre-processing required by your model at this stage. For that refer to the documentation of the model you have:

1// creating an array of input Tensors is the easiest way. For other options see the API documentation
2const inputs = [
3  new Tensor(new Float32Array([1.0, 2.0, 3.0, 4.0]), "float32", [2, 2]),
4];

Run the model with the input Tensors. The output Tensor(s) are available once the run operation is complete:

1// run this in an async method:
2const outputMap = await session.run(inputs);
3const outputTensor = outputMap.values().next().value;

More verbose examples on how to use ONNX.js are located under the examples folder. For further info see Examples

Running in Node.js

ONNX.js can run in Node.js as well. This is usually for testing purpose. Use the require() function to load ONNX.js:

1require("onnxjs");

You can also use NPM package onnxjs-node, which offers a Node.js binding of ONNXRuntime.

1require("onnxjs-node");

See usage of onnxjs-node.

Refer to node/Add for a detailed example.

Documents

Developers

For information on ONNX.js development, please check Development

For API reference, please check API.

Getting ONNX models

You can get ONNX models easily in multiple ways:

Choose a pre-trained ONNX model from the ONNX Model Zoo
Convert models from mainstream frameworks, e.g. PyTorch, TensorFlow and Keras, by following ONNX tutorials
Use your data to generate a customized ONNX model from Azure Custom Vision service
Train a custom model in AzureML and save it in the ONNX format

Learn more about ONNX

Compatibility

Desktop Platforms

OS/Browser	Chrome	Edge	FireFox	Safari	Opera	Electron	Node.js
Windows 10	:heavy_check_mark:	:heavy_check_mark:	:heavy_check_mark:	-	:heavy_check_mark:	:heavy_check_mark:	:heavy_check_mark:
macOS	:heavy_check_mark:	-	:heavy_check_mark:	:heavy_check_mark:	:heavy_check_mark:	:heavy_check_mark:	:heavy_check_mark:
Ubuntu LTS 18.04	:heavy_check_mark:	-	:heavy_check_mark:	-	:heavy_check_mark:	:heavy_check_mark:	:heavy_check_mark:

Mobile Platforms

OS/Browser	Chrome	Edge	FireFox	Safari	Opera
iOS	:heavy_check_mark:	:heavy_check_mark:	:heavy_check_mark:	:heavy_check_mark:	:heavy_check_mark:
Android	:heavy_check_mark:	:heavy_check_mark:	Coming soon	-	:heavy_check_mark:

Operators

ONNX.js currently supports most operators in ai.onnx operator set v7 (opset v7). See operators.md for a complete, detailed list of which ONNX operators are supported by the 3 available builtin backends (cpu, wasm, and webgl).

Support for ai.onnx.ml operators is coming soon. operators-ml.md has the most recent status of ai.onnx.ml operators.

Contribute

We’d love to embrace your contribution to ONNX.js. Please refer to CONTRIBUTING.md.

Thanks

Thanks to BrowserStack for providing cross browser testing support.

License

Licensed under the MIT License.

No vulnerabilities found.

10

Binary-Artifacts

Determines if the project has generated executable (binary) artifacts in the source repository.

10

Security-Policy

Determines if the project has published a security policy.

9

License

Determines if the project has defined a license.

8

Code-Review

Determines if the project requires human code review before pull requests (aka merge requests) are merged.

0

Maintained

Determines if the project is "actively maintained".

0

CII-Best-Practices

Determines if the project has an OpenSSF (formerly CII) Best Practices Badge.

0

Fuzzing

Determines if the project uses fuzzing.

0

SAST

Determines if the project uses static code analysis.

0

Vulnerabilities

Determines if the project has open, known unfixed vulnerabilities.

Reason

68 existing vulnerabilities detected

Details

Warn: Project is vulnerable to: GHSA-93q8-gq69-wqmw
Warn: Project is vulnerable to: GHSA-fwr7-v2mv-hh25
Warn: Project is vulnerable to: GHSA-qwcr-r2fm-qrc7
Warn: Project is vulnerable to: GHSA-grv7-fg5c-xmjg
Warn: Project is vulnerable to: GHSA-x9w5-v3q2-3rhw
Warn: Project is vulnerable to: GHSA-pxg6-pf52-xh8x
Warn: Project is vulnerable to: GHSA-3xgq-45jj-v275
Warn: Project is vulnerable to: GHSA-gxpj-cx7g-858c
Warn: Project is vulnerable to: GHSA-w573-4hg7-7wgq
Warn: Project is vulnerable to: GHSA-mpjm-v997-c4h4
Warn: Project is vulnerable to: GHSA-3p22-ghq8-v749
Warn: Project is vulnerable to: GHSA-77xc-hjv8-ww97
Warn: Project is vulnerable to: GHSA-mq8j-3h7h-p8g7
Warn: Project is vulnerable to: GHSA-p2jh-44qj-pf2v
Warn: Project is vulnerable to: GHSA-p7v2-p9m8-qqg7
Warn: Project is vulnerable to: GHSA-7x97-j373-85x5
Warn: Project is vulnerable to: GHSA-7m48-wc93-9g85
Warn: Project is vulnerable to: GHSA-qqvq-6xgj-jw8g
Warn: Project is vulnerable to: GHSA-r9p9-mrjm-926w
Warn: Project is vulnerable to: GHSA-434g-2637-qmqr
Warn: Project is vulnerable to: GHSA-49q7-c7j4-3p7m
Warn: Project is vulnerable to: GHSA-977x-g7h5-7qgw
Warn: Project is vulnerable to: GHSA-f7q4-pwc6-w24p
Warn: Project is vulnerable to: GHSA-fc9h-whq2-v747
Warn: Project is vulnerable to: GHSA-j4f2-536g-r55m
Warn: Project is vulnerable to: GHSA-r7qp-cfhv-p84w
Warn: Project is vulnerable to: GHSA-2j2x-2gpw-g8fm
Warn: Project is vulnerable to: GHSA-74fj-2j2h-c42q
Warn: Project is vulnerable to: GHSA-pw2r-vq6v-hr8c
Warn: Project is vulnerable to: GHSA-jchw-25xp-jwwc
Warn: Project is vulnerable to: GHSA-cxjh-pqwp-8mfp
Warn: Project is vulnerable to: GHSA-4q6p-r6v2-jvc5
Warn: Project is vulnerable to: GHSA-ww39-953v-wcq6
Warn: Project is vulnerable to: GHSA-pfrx-2q88-qq97
Warn: Project is vulnerable to: GHSA-rc47-6667-2j5j
Warn: Project is vulnerable to: GHSA-9c47-m6qq-7p4h
Warn: Project is vulnerable to: GHSA-7x7c-qm48-pq9c
Warn: Project is vulnerable to: GHSA-rc3x-jf5g-xvc5
Warn: Project is vulnerable to: GHSA-76p3-8jx3-jpfq
Warn: Project is vulnerable to: GHSA-3rfm-jhwj-7488
Warn: Project is vulnerable to: GHSA-hhq3-ff78-jv3g
Warn: Project is vulnerable to: GHSA-29mw-wpgm-hmr9
Warn: Project is vulnerable to: GHSA-35jh-r3h4-6jhm
Warn: Project is vulnerable to: GHSA-82v2-mx6x-wq7q
Warn: Project is vulnerable to: GHSA-952p-6rrq-rcjv
Warn: Project is vulnerable to: GHSA-f8q6-p94x-37v3
Warn: Project is vulnerable to: GHSA-xvch-5gv4-984h
Warn: Project is vulnerable to: GHSA-px4h-xg32-q955
Warn: Project is vulnerable to: GHSA-hj48-42vr-x3v9
Warn: Project is vulnerable to: GHSA-g6ww-v8xp-vmwg
Warn: Project is vulnerable to: GHSA-hrpp-h998-j3pp
Warn: Project is vulnerable to: GHSA-c2qf-rxjj-qqgw
Warn: Project is vulnerable to: GHSA-44c6-4v22-4mhx
Warn: Project is vulnerable to: GHSA-4x5v-gmq8-25ch
Warn: Project is vulnerable to: GHSA-wpg7-2c88-r8xv
Warn: Project is vulnerable to: GHSA-25hc-qcg6-38wj
Warn: Project is vulnerable to: GHSA-qm95-pgcg-qqfq
Warn: Project is vulnerable to: GHSA-cqmj-92xf-r6r9
Warn: Project is vulnerable to: GHSA-vx3p-948g-6vhq
Warn: Project is vulnerable to: GHSA-4wf5-vphf-c2xc
Warn: Project is vulnerable to: GHSA-662x-fhqg-9p8v
Warn: Project is vulnerable to: GHSA-394c-5j6w-4xmx
Warn: Project is vulnerable to: GHSA-78cj-fxph-m83p
Warn: Project is vulnerable to: GHSA-fhg7-m89q-25r3
Warn: Project is vulnerable to: GHSA-6fc8-4gx4-v693
Warn: Project is vulnerable to: GHSA-3h5v-q93c-6h6q
Warn: Project is vulnerable to: GHSA-72mh-269x-7mh5
Warn: Project is vulnerable to: GHSA-h4j5-c7cj-74xg

Score

4.2

/10

Last Scanned on 2024-12-23

The Open Source Security Foundation is a cross-industry collaboration to improve the security of open source software (OSS). The Scorecard provides security health metrics for open source projects.

Learn More

Other packages similar to onnxjs

Other packages similar to onnxjs

onnxjs

Installations

Developer Guide

Yes

CommonJS, UMD

12.18.0

6.14.4

Score

Pull Requests

17

197

31

149

Issues

68

122

54

Releases

Contributors

Unable to fetch Contributors

Languages

Developer

Microsoft

Download Statistics

GitHub Statistics

Maintainers

Package Meta Information

Total Downloads

234,506

Daily Downloads

Weekly Downloads

Monthly Downloads

Yearly Downloads

Dependencies

Dev Dependencies

ONNX.js

Why ONNX models

Why ONNX.js

Benchmarks

Demo

Getting Started

Using <script> tag

Using NPM and bundling tools

Running in Node.js

Documents

Developers

Getting ONNX models

Compatibility

Desktop Platforms

Mobile Platforms

Operators

Contribute

Thanks

License

10

10

9

8

0

0

0

0

0

4.2

/10

Using `<script>` tag