forked from docs/doc-exports
Lai, Weijian
4e4b2d5f6d
Reviewed-by: Hasko, Vladimir <vladimir.hasko@t-systems.com> Co-authored-by: Lai, Weijian <laiweijian4@huawei.com> Co-committed-by: Lai, Weijian <laiweijian4@huawei.com>
25 lines
3.1 KiB
HTML
25 lines
3.1 KiB
HTML
<a name="EN-US_TOPIC_0000001910014914"></a><a name="EN-US_TOPIC_0000001910014914"></a>
|
|
|
|
<h1 class="topictitle1">Introduction to Inference</h1>
|
|
<div id="body0000001194025777"><p id="EN-US_TOPIC_0000001910014914__p8060118">After an AI model is developed, you can use it to create an AI application and quickly deploy the application as an inference service. The AI inference capabilities can be integrated into your IT platform by calling APIs.</p>
|
|
<div class="fignone" id="EN-US_TOPIC_0000001910014914__fig167677115620"><span class="figcap"><b>Figure 1 </b>Inference</span><br><span><img id="EN-US_TOPIC_0000001910014914__image26762710562" src="figure/en-us_image_0000001910055054.png" height="194.51250000000002" width="523.6875" title="Click to enlarge" class="imgResize"></span></div>
|
|
<ul id="EN-US_TOPIC_0000001910014914__ul13876134314564"><li id="EN-US_TOPIC_0000001910014914__li187604365614">Develop a model: Models can be developed in ModelArts or your local development environment. A locally developed model must be uploaded to OBS.</li><li id="EN-US_TOPIC_0000001910014914__li1951184495718">Create an AI application: Import the model file and inference file to the ModelArts model repository and manage them by version. Use these files to build an executable AI application.</li><li id="EN-US_TOPIC_0000001910014914__li1488075619596">Deploy as a service: Deploy the AI application as a container instance in the resource pool and register inference APIs that can be accessed externally.</li><li id="EN-US_TOPIC_0000001910014914__li12701249702">Perform inference: Add the function of calling the inference APIs to your application to integrate AI inference into the service process.</li></ul>
|
|
<div class="section" id="EN-US_TOPIC_0000001910014914__section5706068262"><a name="EN-US_TOPIC_0000001910014914__section5706068262"></a><a name="section5706068262"></a><h4 class="sectiontitle">Deploying an AI Application as a Service</h4><div class="p" id="EN-US_TOPIC_0000001910014914__p174291244142614">After an AI application is created, you can deploy it as a service on the <strong id="EN-US_TOPIC_0000001910014914__b26141829163014">Deploy</strong> page. ModelArts supports the following deployment types:<ul id="EN-US_TOPIC_0000001910014914__ul513792174813"><li id="EN-US_TOPIC_0000001910014914__li201378274813"><a href="inference-modelarts-0018.html">Real-time service</a><p id="EN-US_TOPIC_0000001910014914__p1048214501539">Deploy an AI application as a web service with real-time test UI and monitoring supported.</p>
|
|
</li><li id="EN-US_TOPIC_0000001910014914__li108427135482"><a href="inference-modelarts-0040.html">Batch service</a><p id="EN-US_TOPIC_0000001910014914__p133061721175912">Deploy an AI application as a batch service that performs inference on batch data and automatically stops after data processing is complete.</p>
|
|
</li></ul>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
<div>
|
|
<div class="familylinks">
|
|
<div class="parentlink"><strong>Parent topic:</strong> <a href="modelarts_77_0149.html">Inference Deployment</a></div>
|
|
</div>
|
|
</div>
|
|
|
|
|
|
<script language="JavaScript">
|
|
<!--
|
|
image_size('.imgResize');
|
|
var msg_imageMax = "view original image";
|
|
var msg_imageClose = "close";
|
|
//--></script> |