检测到您已登录华为云国际站账号，为了您更好的体验，建议您访问国际站服务网站 https://www.huaweicloud.com/intl/zh-cn
不再显示此消息
检测到您已登录华为云国际站账号，为了您更好的体验，建议您访问国际站服务网站 https://www.huaweicloud.com/intl/zh-cn
不再显示此消息
As a Chinese developed AI large language model, DeepSeek has risen to prominence in the AI field, leveraging its high performance, low cost, and multi-modal capabilities to demonstrate significant application potential across various sectors.
Parent topic: Using FunctionGraph to Deploy Stable Diffusion for AI Drawing
Using Existing Algorithms to Train Models You can quickly use a created algorithm to create a training job and build a model. Prerequisites Data has been prepared. Specifically, you have created an available dataset in ModelArts, or you have uploaded the dataset used for training
Using Custom Images to Train Models If the framework used for algorithm development is not a frequently-used framework, you can build an algorithm into a custom image and use the custom image to create a training job. Prerequisites Data has been prepared. Specifically, you have created
Creating a Data Processing Task You can create a data processing task to verify, cleanse, select, or augment existing data. Prerequisites Data has been prepared. Specifically, a dataset has been created or data has been uploaded to OBS. The OBS directory you use and ModelArts are
Using a custom image to create AI applications If you have developed a model using an AI engine that is not supported by ModelArts, to use this model to create AI applications, do as follows: Create a custom image, import the image to ModelArts, and use it to create AI applications
Configuring Speed Rules Context You can configure different speed rules to be referenced when business scenarios are configured. Speed rules can be created on the GUI. Procedure Sign in to the AICC as a tenant administrator, choose Configuration Center > Quality Management > Inspection
Configuring Silence Rules A silence rule regulates the silence duration in a conversation between an agent and customer. If the silence duration is too long, it may affect the satisfaction of the customer. Therefore, silence rules can be configured to review agents on the Inspection
Configuring Interruption Rules Context When an agent and a customer speak at the same time, the agent is regarded as interrupting the customer during the call. You can configure different interruption rules to be referenced when business scenarios are configured. In an interruption
Configuring Dialog Rules Context You can configure different dialog rules to be referenced when business scenarios are configured. For example, you can configure an agent introduction in a dialog rule for the return visit scenario, including the employee ID and thanks. The introduction
Notebook Cache Directory Alarm Reporting When creating a notebook instance, you can select CPU, GPU, or Ascend resources based on the service data volume. If you select GPU or Ascend resources, ModelArts mounts hard disks to the cache directory. You can use this directory to store
Preparing Image Classification Data Before using ModelArts ExeML to build a model, upload data to an OBS bucket. The OBS bucket and ModelArts must be in the same region. Requirements on Datasets Check that all images are undamaged and in a compatible format. The supported formats
Creating an Image Classification Project ModelArts ExeML supports sound classification, text classification, image classification, predictive analytics, and object detection projects. You can create any of them based on your needs. Perform the following operations to create an ExeML
Labeling Image Classification Data Model training requires a large number of labeled images. Therefore, before model training, add labels to the images that are not labeled. ModelArts allows you to add labels in batches by one click. You can also modify or delete labels that have
Creating an Object Detection Project ModelArts ExeML supports sound classification, text classification, image classification, predictive analytics, and object detection projects. You can create any of them based on your needs. Perform the following operations to create an ExeML project
Labeling Object Detection Data Before data labeling, consider how to design labels. The labels must correspond to the distinct characteristics of the detected images and are easy to identify (the detected object in an image is highly distinguished from the background). Each label
Creating a Predictive Analytics Project ModelArts ExeML supports sound classification, text classification, image classification, predictive analytics, and object detection projects. You can create any of them based on your needs. Perform the following operations to create an ExeML
Creating a Sound Classification Project ModelArts ExeML supports sound classification, text classification, image classification, predictive analytics, and object detection projects. You can create any of them based on your needs. Perform the following operations to create an ExeML
Labeling Sound Classification Data After a project is created, you will be redirected to the new-version ExeML and the project starts to run. When the data labeling phase changes to Awaiting operation, manually confirm data labeling in the dataset. You can also add or delete data
Creating a Text Classification Project ModelArts ExeML supports sound classification, text classification, image classification, predictive analytics, and object detection projects. You can create any of them based on your needs. Perform the following operations to create an ExeML
