|
1 | 1 | ---
|
2 |
| -title: "Quickstart: Build a classifier with the Custom Vision website" |
| 2 | +title: "Quickstart: Build an image classifier model with the Custom Vision portal" |
3 | 3 | titleSuffix: Azure Cognitive Services
|
4 |
| -description: In this quickstart, you'll learn how to use the Custom Vision website to create, train, and test an image classification model. |
| 4 | +description: In this quickstart, you'll learn how to use the Custom Vision web portal to create, train, and test an image classification model. |
5 | 5 | services: cognitive-services
|
6 | 6 | author: PatrickFarley
|
7 | 7 | manager: nitinme
|
8 | 8 | ms.service: cognitive-services
|
9 | 9 | ms.subservice: custom-vision
|
10 | 10 | ms.topic: quickstart
|
11 |
| -ms.date: 09/27/2021 |
| 11 | +ms.date: 02/02/2022 |
12 | 12 | ms.author: pafarley
|
13 | 13 | ms.custom: cog-serv-seo-aug-2020, mode-other
|
14 | 14 | keywords: image recognition, image recognition app, custom vision
|
15 | 15 | ---
|
16 | 16 |
|
17 |
| -# Quickstart: Build a classifier with the Custom Vision website |
| 17 | +# Quickstart: Build an image classifier model with the Custom Vision web portal |
18 | 18 |
|
19 |
| -In this quickstart, you'll learn how to use the Custom Vision website to create an image classification model. Once you build a model, you can test it with new images and eventually integrate it into your own image recognition app. |
| 19 | +In this quickstart, you'll learn how to use the Custom Vision web portal to create an image classifier model. Once you build a model, you can test it with new images and eventually integrate it into your own image recognition app. |
20 | 20 |
|
21 | 21 | If you don't have an Azure subscription, create a [free account](https://azure.microsoft.com/free/cognitive-services/) before you begin.
|
22 | 22 |
|
@@ -44,11 +44,11 @@ In your web browser, navigate to the [Custom Vision web page](https://customvisi
|
44 | 44 | 1. Enter a name and a description for the project. Then select a Resource Group. If your signed-in account is associated with an Azure account, the Resource Group dropdown will display all of your Azure Resource Groups that include a Custom Vision Service Resource.
|
45 | 45 |
|
46 | 46 | > [!NOTE]
|
47 |
| - > If no resource group is available, please confirm that you have logged into [customvision.ai](https://customvision.ai) with the same account as you used to log into the [Azure portal](https://portal.azure.com/). Also, please confirm you have selected the same "Directory" in the Custom Vision website as the directory in the Azure portal where your Custom Vision resources are located. In both sites, you may select your directory from the drop down account menu at the top right corner of the screen. |
| 47 | + > If no resource group is available, please confirm that you have logged into [customvision.ai](https://customvision.ai) with the same account as you used to log into the [Azure portal](https://portal.azure.com/). Also, please confirm you have selected the same "Directory" in the Custom Vision web portal as the directory in the Azure portal where your Custom Vision resources are located. In both sites, you may select your directory from the drop down account menu at the top right corner of the screen. |
48 | 48 |
|
49 | 49 | 1. Select __Classification__ under __Project Types__. Then, under __Classification Types__, choose either **Multilabel** or **Multiclass**, depending on your use case. Multilabel classification applies any number of your tags to an image (zero or more), while multiclass classification sorts images into single categories (every image you submit will be sorted into the most likely tag). You'll be able to change the classification type later if you want to.
|
50 | 50 |
|
51 |
| -1. Next, select one of the available domains. Each domain optimizes the classifier for specific types of images, as described in the following table. You will be able to change the domain later if you wish. |
| 51 | +1. Next, select one of the available domains. Each domain optimizes the classifier for specific types of images, as described in the following table. You can change the domain later if you wish. |
52 | 52 |
|
53 | 53 | |Domain|Purpose|
|
54 | 54 | |---|---|
|
@@ -108,13 +108,13 @@ After training has completed, the model's performance is estimated and displayed
|
108 | 108 |
|
109 | 109 | ## Manage training iterations
|
110 | 110 |
|
111 |
| -Each time you train your classifier, you create a new _iteration_ with its own updated performance metrics. You can view all of your iterations in the left pane of the **Performance** tab. You'll also find the **Delete** button, which you can use to delete an iteration if it's obsolete. When you delete an iteration, you delete any images that are uniquely associated with it. |
| 111 | +Each time you train your classifier, you create a new _iteration_ with updated performance metrics. You can view all of your iterations in the left pane of the **Performance** tab. You'll also find the **Delete** button, which you can use to delete an iteration if it's obsolete. When you delete an iteration, you delete any images that are uniquely associated with it. |
112 | 112 |
|
113 | 113 | See [Use your model with the prediction API](./use-prediction-api.md) to learn how to access your trained models programmatically.
|
114 | 114 |
|
115 | 115 | ## Next steps
|
116 | 116 |
|
117 |
| -In this quickstart, you learned how to create and train an image classification model using the Custom Vision website. Next, get more information on the iterative process of improving your model. |
| 117 | +In this quickstart, you learned how to create and train an image classification model using the Custom Vision web portal. Next, get more information on the iterative process of improving your model. |
118 | 118 |
|
119 | 119 | > [!div class="nextstepaction"]
|
120 | 120 | > [Test and retrain a model](test-your-model.md)
|
|
0 commit comments