为图像模型评分Score Image Model

本文介绍 Azure 机器学习设计器(预览版)中的一个模块。This article describes a module in Azure Machine Learning designer (preview).

对输入图像数据使用此模块可以通过已定型图像模型生成预测。Use this module to generate predictions using a trained image model on input image data.

如何配置“为图像模型评分”模块How to configure Score Image Model

  1. 将“为图像模型评分”模块添加到管道。Add the Score Image Model module to your pipeline.

  2. 连接已定型图像模型和包含输入图像数据的数据集。Attach a trained image model and a dataset containing input image data.

    数据应为 ImageDirectory 类型。The data should be of type ImageDirectory. 若要详细了解如何获取图像目录,请参阅转换为图像目录模块。Refer to Convert to Image Directory module for more information about how to get a image directory. 输入数据集的架构通常还应与用于训练模型的数据的架构相匹配。The schema of the input dataset should also generally match the schema of the data used to train the model.

  3. 提交管道。Submit the pipeline.

结果Results

使用为图像模型评分模块生成一组分数后,若要生成一组用于评估模型准确性(性能)的指标,可以将此模块和评分数据集连接到评估模型After you have generated a set of scores using Score Image Model, to generate a set of metrics used for evaluating the model's accuracy (performance), you can connect this module and the scored dataset to Evaluate Model,

将评分发布为 Web 服务Publish scores as a web service

评分的一个常见用途是在预测 Web 服务中返回输出。A common use of scoring is to return the output as part of a predictive web service. 有关详细信息,请参阅此教程,了解如何在 Azure 机器学习设计器中基于管道部署实时终结点。For more information, see this tutorial on how to deploy a real-time endpoint based on a pipeline in Azure Machine Learning designer.

后续步骤Next steps

请参阅 Azure 机器学习的可用模块集See the set of modules available to Azure Machine Learning.