saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-19 19:00:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update winarm.html (#18103)

Browse source 
updated winarm to use qnn EP

### Description
<!-- Describe your changes. -->



### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->
This commit is contained in:
Jeff Mendenhall 2023-10-25 17:11:37 -07:00 committed by GitHub
parent b56dc722b5
commit 9f877ef2bc
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 8 additions and 32 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

40
winarm.html
View file

@ -101,19 +101,10 @@
<p>Follow these steps to setup your device to use ONNX Runtime (ORT) with the built
in NPU:
<ol>
<li><a href="https://developer.qualcomm.com/software/qualcomm-neural-processing-sdk/windows-on-snapdragon"
target="_blank">Request access</a> to the Neural Processing SDK for
Windows on Snapdragon. Qualcomm may reach out to you via email with further
registration instructions for approval. </li>
<li>Once approved, you will receive an email with links to download SNPE.
<ol type="a">
<li>Select the SNPE link which takes you to a Qualcomm login and
download page. </li>
<li>Select the <i>Snapdragon_NPE_SDK.WIN.1.0 Installer</i> link,
download and install.</li>
</ol>
<li><a href="https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.Snpe"
target="_blank">Download</a> and install the ONNX Runtime with SNPE
<li><a href="https://qpm.qualcomm.com/main/tools/details/qualcomm_ai_engine_direct"
target="_blank">Download</a> the Qualcomm AI Engine Direct SDK (QNN SDK) </li>
<li><a href="https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.QNN"
target="_blank">Download</a> and install the ONNX Runtime with QNN
package</li>
<li>Start using the ONNX Runtime API in your application.</li>
</ol>
@ -122,29 +113,14 @@
<p><a href="https://onnx.ai" target="_blank">ONNX</a> is a standard format for
representing ML models authored in frameworks like PyTorch, TensorFlow, and
others. ONNX Runtime can run any ONNX model, however to make use of the NPU, you
currently need to use the following steps:
<ul>
<li>Run the tools provided in the SNPE SDK on your model to generate a binary
file.</li>
<li>Include the contents of the binary file as a node in the ONNX graph.</li>
</ul>
currently need to quantize the ONNX model to QDQ model.
<p>See our <a
href="https://github.com/microsoft/onnxruntime-inference-examples/tree/main/c_sharp/Snpe_EP/vgg16_image_classification"
href="https://github.com/microsoft/onnxruntime-inference-examples/tree/main/c_cxx/QNN_EP/mobilenetv2_classification"
target="_blank">C# tutorial<a> for an example of how this is done.</p>
<p>Many models can be optimized for the NPU using this process. Even if a model
cannot be optimized for NPU by the SNPE SDK, it can still be run by ONNX Runtime
cannot be optimized for NPU, it can still be run by ONNX Runtime
on the CPU.</p>
<br />
<h2 class="blue-text">Tutorials</h2>
<ul>
<li><a href="https://github.com/microsoft/onnxruntime-inference-examples/tree/main/c_sharp/Snpe_EP/vgg16_image_classification"
target="_blank">C# Image classification with VGG16 using ONNX Runtime
with SNPE<a></li>
<li><a href="https://github.com/microsoft/onnxruntime-inference-examples/tree/main/c_cxx/Snpe_EP"
target="_blank">C++ image classification with Inception v3 using ONNX
Runtime with SNPE<a></li>
</ul>
<br />
<h2 class="blue-text">Getting help</h2>
<p>For help with ONNX Runtime, you can <a
href="https://github.com/microsoft/onnxruntime/discussions"
@ -181,4 +157,4 @@
</body>
</html>f
</html>f