Back to Details

azure-custom-vision

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Azure AI Custom Vision Skill

Azure AI Custom Vision Skill

This skill provides expert guidance for Azure AI Custom Vision. Covers best practices, decision making, limits & quotas, security, integrations & coding patterns, and deployment. It combines local quick-reference content with remote documentation fetching capabilities.
本Skill为Azure AI Custom Vision提供专家指导，涵盖最佳实践、决策制定、限制与配额、安全、集成与编码模式以及部署相关内容。它结合了本地快速参考内容与远程文档获取功能。

How to Use This Skill

如何使用本Skill

IMPORTANT for Agent: Use the Category Index below to locate relevant sections. For categories with line ranges (e.g., 
L35-L120
), use 
read_file
with the specified lines. For categories with file links (e.g., 
[security.md](security.md)
), use 
read_file
on the linked reference file
IMPORTANT for Agent: If 
metadata.generated_at
is more than 3 months old, suggest the user pull the latest version from the repository. If 
mcp_microsoftdocs
tools are not available, suggest the user install it: Installation Guide
This skill requires network access to fetch documentation content:
  • Preferred: Use 
    mcp_microsoftdocs:microsoft_docs_fetch
    with query string 
    from=learn-agent-skill
    . Returns Markdown.
  • Fallback: Use 
    fetch_webpage
    with query string 
    from=learn-agent-skill&accept=text/markdown
    . Returns Markdown.
Agent 重要提示：使用下方的分类索引查找相关章节。对于带有行范围的分类（例如
L35-L120
），使用
read_file
工具读取指定行内容。对于带有文件链接的分类（例如
[security.md](security.md)
），使用
read_file
工具读取链接的参考文件
Agent 重要提示：如果
metadata.generated_at
的时间超过3个月，建议用户从仓库拉取最新版本。如果
mcp_microsoftdocs
工具不可用，建议用户安装该工具：安装指南
本Skill需要网络访问权限来获取文档内容：
  • 推荐方式：使用
    mcp_microsoftdocs:microsoft_docs_fetch
    工具，携带查询参数
    from=learn-agent-skill
    ，返回Markdown格式内容。
  • 备选方式：使用
    fetch_webpage
    工具，携带查询参数
    from=learn-agent-skill&accept=text/markdown
    ，返回Markdown格式内容。

Category Index

分类索引

CategoryLinesDescription
Best PracticesL34-L39Improving Custom Vision model quality with better data collection/labeling strategies and using Smart Labeler to speed and automate image annotation
Decision MakingL40-L45Guidance on selecting the best Custom Vision domain for your scenario and planning migrations from Custom Vision to other Azure or third‑party vision services.
Limits & QuotasL46-L50Details on Custom Vision usage limits per pricing tier, including training/prediction quotas, project and image caps, and how limits affect model training and deployment.
SecurityL51-L57Managing Custom Vision security: encryption with customer-managed keys, secure data handling/export/deletion, and configuring Azure RBAC roles and permissions.
Integrations & Coding PatternsL58-L68Using Custom Vision models and APIs in apps: exporting via SDK, running ONNX/TensorFlow in Windows ML/Python, calling classification/detection APIs, and integrating with Azure Storage.
DeploymentL69-L73Deploying Custom Vision models: copying/backing up projects across regions and exporting models for offline, edge, and mobile (TensorFlow, ONNX, iOS/Android) use.
分类行范围描述
最佳实践L34-L39通过更优的数据收集/标注策略提升Custom Vision模型质量，以及使用Smart Labeler加速并自动化图像标注
决策制定L40-L45指导如何为你的场景选择最佳Custom Vision领域，以及规划从Custom Vision迁移到其他Azure或第三方视觉服务的方案。
限制与配额L46-L50各定价层的Custom Vision使用限制详情，包括训练/预测配额、项目和图像上限，以及这些限制对模型训练和部署的影响。
安全L51-L57管理Custom Vision安全：使用客户管理密钥进行加密、安全的数据处理/导出/删除，以及配置Azure RBAC角色和权限。
集成与编码模式L58-L68在应用中使用Custom Vision模型和API：通过SDK导出模型、在Windows ML/Python中运行ONNX/TensorFlow模型、调用分类/检测API，以及与Azure Storage集成。
部署L69-L73部署Custom Vision模型：跨区域复制/备份项目，以及导出模型用于离线、边缘和移动（TensorFlow、ONNX、iOS/Android）场景。

Best Practices

最佳实践

TopicURL
Apply Custom Vision data strategies to improve modelshttps://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/getting-started-improving-your-classifier
Speed up Custom Vision labeling with Smart Labelerhttps://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/suggested-tags
主题链接
应用Custom Vision数据策略提升模型质量https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/getting-started-improving-your-classifier
使用Smart Labeler加速Custom Vision标注https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/suggested-tags

Decision Making

决策制定

TopicURL
Plan migration from Custom Vision to alternative serviceshttps://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/migration-options
Choose the right Custom Vision domain for your projecthttps://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/select-domain
主题链接
规划从Custom Vision迁移到替代服务的方案https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/migration-options
为你的项目选择合适的Custom Vision领域https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/select-domain

Limits & Quotas

限制与配额

TopicURL
Review Custom Vision limits and quotas by tierhttps://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/limits-and-quotas
主题链接
按层级查看Custom Vision限制与配额https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/limits-and-quotas

Security

安全

TopicURL
Configure customer-managed keys for Custom Vision encryptionhttps://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/encrypt-data-at-rest
View, export, and delete Custom Vision data securelyhttps://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/export-delete-data
Configure Azure RBAC roles for Custom Vision projectshttps://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/role-based-access-control
主题链接
为Custom Vision加密配置客户管理密钥https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/encrypt-data-at-rest
安全查看、导出和删除Custom Vision数据https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/export-delete-data
为Custom Vision项目配置Azure RBAC角色https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/role-based-access-control

Integrations & Coding Patterns

集成与编码模式

TopicURL
Integrate Custom Vision ONNX models with Windows ML appshttps://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/custom-vision-onnx-windows-ml
Run exported Custom Vision TensorFlow models in Pythonhttps://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/export-model-python
Export Custom Vision models programmatically with SDKhttps://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/export-programmatically
Use Custom Vision SDK for image classificationhttps://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/quickstarts/image-classification
Call Custom Vision object detection APIs with SDKhttps://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/quickstarts/object-detection
Integrate Custom Vision with Azure Storage queues and blobshttps://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/storage-integration
Use Custom Vision prediction API to test imageshttps://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/use-prediction-api
主题链接
将Custom Vision ONNX模型与Windows ML应用集成https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/custom-vision-onnx-windows-ml
在Python中运行导出的Custom Vision TensorFlow模型https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/export-model-python
通过SDK以编程方式导出Custom Vision模型https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/export-programmatically
使用Custom Vision SDK进行图像分类https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/quickstarts/image-classification
使用SDK调用Custom Vision目标检测APIhttps://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/quickstarts/object-detection
将Custom Vision与Azure Storage队列和Blob集成https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/storage-integration
使用Custom Vision预测API测试图像https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/use-prediction-api

Deployment

部署

TopicURL
Copy and back up Custom Vision projects across regionshttps://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/copy-move-projects
Export Custom Vision models for offline and mobile usehttps://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/export-your-model
主题链接
跨区域复制和备份Custom Vision项目https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/copy-move-projects
导出Custom Vision模型用于离线和移动场景https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/export-your-model