Added (hidden) converter team page. (#16507)

Co-authored-by: MaanavD <maanavdalal@microsoft.com>
This commit is contained in:
Maanav Dalal 2023-07-03 13:28:11 -07:00 committed by GitHub
parent 310599fce7
commit 2bec00816b
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
3 changed files with 121 additions and 3 deletions

View file

@ -23,4 +23,4 @@ jobs:
run: bundle exec jekyll build --drafts
- name: Check for broken links
run: |
bundle exec htmlproofer --assume_extension --checks_to_ignore ImageCheck,ScriptCheck --only_4xx --http_status_ignore 429,403 --allow_hash_href --url_ignore "https://onnxruntime.ai/docs/reference/api/c-api.html,https://www.onnxruntime.ai/docs/reference/execution-providers/TensorRT-ExecutionProvider.html#c-api-example,https://www.onnxruntime.ai/docs/resources/graph-optimizations.html,onnxruntime/capi/onnxruntime_pybind11_state.html" --log-level :info ./_site
bundle exec htmlproofer --assume_extension --checks_to_ignore ImageCheck,ScriptCheck --only_4xx --http_status_ignore 429,403 --allow_hash_href --url_ignore "https://onnxruntime.ai/docs/reference/api/c-api.html,https://www.onnxruntime.ai/docs/reference/execution-providers/TensorRT-ExecutionProvider.html#c-api-example,https://www.onnxruntime.ai/docs/resources/graph-optimizations.html,onnxruntime/capi/onnxruntime_pybind11_state.html,https://github.com/microsoft/onnx-converters-private/" --log-level :info ./_site

View file

@ -40,7 +40,7 @@ A [demonstration](https://github.com/amd/RyzenAI-cloud-to-client-demo) is availa
## Install
### AMD Adaptable SoC Installation
For AMD Adaptable SoC targets, a pre-built package is provided to deploy ONNX models on embedded Linux. Users should refer to the standard Vitis AI [Target Setup Instructions](https://xilinx.github.io/Vitis-AI/docs/board_setup/board_setup.html) to enable Vitis AI on the target. Once Vitis AI has been enabled on the target, the developer can refer to [this section](https://docs.xilinx.com/r/en-US/ug1414-vitis-ai/Programming-with-VOE) of the Vitis AI documentation for installation and API details.
For AMD Adaptable SoC targets, a pre-built package is provided to deploy ONNX models on embedded Linux. Users should refer to the standard Vitis AI [Target Setup Instructions](https://xilinx.github.io/Vitis-AI/3.0/html/docs/workflow.html) to enable Vitis AI on the target. Once Vitis AI has been enabled on the target, the developer can refer to [this section](https://docs.xilinx.com/r/en-US/ug1414-vitis-ai/Programming-with-VOE) of the Vitis AI documentation for installation and API details.
For more complete examples, developers should refer to [ONNX Runtime Vitis AI Execution Provider examples](https://github.com/Xilinx/Vitis-AI/tree/master/examples/vai_library/samples_onnx).
@ -124,7 +124,7 @@ In the current release (3.0), the Vitis AI Quantizer supports quantization of Py
With the future release of Vitis AI 3.5, available mid 2023, the Vitis AI Quantizer will enable parsing and quantization of ONNX models, enabling an end-to-end ONNX model -> ONNX Runtime workflow. Also, in a future release, the Vitis AI ONNX Runtime Execution Provider will support on-the-fly quantization, enabling direct deployment of FP32 ONNX models.
See [Vitis AI Model Quantization](https://xilinx.github.io/Vitis-AI/docs/workflow-model-development.html#model-quantization) for details.
See [Vitis AI Model Quantization](https://xilinx.github.io/Vitis-AI/3.0/html/docs/workflow-model-development.html#model-quantization) for details.
### Olive

118
onnx/converterteam.html Normal file
View file

@ -0,0 +1,118 @@
<!DOCTYPE html>
<html lang="en">
<head>
<script type="text/javascript" src="https://js.monitor.azure.com/scripts/c/ms.analytics-web-3.min.js">
</script>
<script type="text/javascript">
const analytics = new oneDS.ApplicationInsights();
var config = {
instrumentationKey: "360b0e675e0044398fd28c8bdf711b8e-1fe5434d-ee99-4837-99cc-a3a16462d82d-7262",
channelConfiguration: { // Post channel configuration
eventsLimitInMem: 50
},
propertyConfiguration: { // Properties Plugin configuration
env: "PPE" // Environment can be set to PPE or PROD as needed.
},
webAnalyticsConfiguration: { // Web Analytics Plugin configuration
//urlCollectQuery:true,
autoCapture: {
scroll: true,
pageView: true,
onLoad: true,
onUnload: true,
click: true,
resize: true,
jsError: true
}
}
};
//Initialize SDK
analytics.initialize(config, []);
</script>
<meta charset="UTF-8">
<meta http-equiv="X-UA-Compatible" content="IE=edge">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<link rel="icon" href="https://onnx.ai/images/onnx-favicon.png" type="image/gif" sizes="16x16">
<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/bootstrap@5.2.3/dist/css/bootstrap.min.css"
integrity="sha384-rbsA2VBKQhggwzxH7pPCaAqO46MgnOM80zW1RWuH61DGLwZJEdK2Kadq2F9CUG65" crossorigin="anonymous">
<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/bootstrap-icons@1.10.2/font/bootstrap-icons.css"
integrity="sha384-b6lVK+yci+bfDmaY1u0zE8YYJt0TZxLEAFyYSLHId4xoVvsrQu3INevFKo+Xir8e" crossorigin="anonymous">
<title>ONNX Converters Team</title>
</head>
<body>
<section class="hero bg-white">
<div class="px-4 py-5 text-center">
<img class="d-block mx-auto mb-4"
src="https://upload.wikimedia.org/wikipedia/commons/c/c0/ONNX_logo_main.png" alt="ONNX Logo" width="232"
height="59.5">
<h1 class="display-5 fw-bold text-body-emphasis">ONNX Converters Team</h1>
<div class="col-lg-6 mx-auto">
<p class="lead mb-4">Welcome to the landing page for the ONNX Converters Team at Microsoft. <br/> We hope your stay is
short and that you quickly get what you need!</p>
</div>
</div>
</section>
<section class="bg-dark text-light">
<div class="px-4 py-5 text-center">
<h1 class="display-5 fw-bold text-body-emphasis">Issue Submission</h1>
<div class="container">
<p class="lead">
Have an issue converting a PyTorch or TensorFlow model to ONNX model? <br />Submit an issue to get help ASAP.
</p>
<hr class="my-5">
<div class="row">
<div class="col-4 px-4">
<h3>Microsoft Internal (<span class="text-primary">Private</span>)</h3>
<p>If the issue contains information that cannot be disclosed publicly, <em><strong>and</strong></em> you're internal to Microsoft, file an issue internally:</p>
<div class="d-grid gap-2">
<a href="https://repos.opensource.microsoft.com/link" type="button" class="btn rounded-0 btn-primary btn-lg px-4 gap-3">
<i class="bi bi-1-circle-fill"></i> Link GitHub Account
</a>
<em>AND</em>
<a href="https://github.com/microsoft/onnx-converters-private/issues/new/choose" type="button" class="btn rounded-0 btn-primary btn-lg px-4 gap-3">
<i class="bi bi-2-circle-fill"></i> File Internally
</a>
</div>
</div>
<div class="col-4 px-4">
<h3>General Issue (<span class="text-primary">Public</span>)</h3>
<p>Have an issue that can be publicly disclosed on GitHub? File the issue upstream:</p>
<div class="d-grid gap-2">
<a href="https://aka.ms/pytorch/new-onnx-issue" type="button" class="btn rounded-0 btn-primary btn-lg px-4 gap-3">
<i class="bi bi-github"></i> PyTorch Issue
</a>
<em>OR</em>
<a href="https://aka.ms/tensorflow/new-onnx-issue" type="button" class="btn rounded-0 btn-primary btn-lg px-4 gap-3 ">
<i class="bi bi-github"></i> TensorFlow Issue
</a>
</div>
</div>
<div class="col-4 px-4">
<h3>External Partner (<span class="text-primary">Private</span>)</h3>
<p>If you're external to Microsoft and the issue contains information that cannot be disclosed publicly, use the following link to template an email, and send it to the below DRI:</p>
<div class="d-grid gap-2">
<a href="https://gist.github.com/MaanavD/6bd2a4f89518d53723d304084f118f07" type="button" class="btn rounded-0 btn-primary btn-lg px-4 gap-3">
<i class="bi bi-1-circle-fill"></i> Fill Out Template
</a>
<em>AND</em>
<a href="mailto:maanavdalal@mirosoft.com" type="button" class="btn rounded-0 btn-primary btn-lg px-4 gap-3">
<i class="bi bi-2-circle-fill"></i> Email it to the DRI
</a>
</div>
</div>
</div>
</div>
</div>
</section>
<footer class="py-5 text-center text-secondary">
© Microsoft. All rights reserved.
</footer>
</body>
<script src="https://cdn.jsdelivr.net/npm/bootstrap@5.2.3/dist/js/bootstrap.bundle.min.js"
integrity="sha384-kenU1KFdBIe4zVF0s0G1M5b4hcpxyD9F7jL+jjXkk+Q2h455rYXK/7HAuoJl+0I4"
crossorigin="anonymous"></script>
</html>