This topic describes how to deploy a trained model as an online service.
Deployment methods
You can deploy a trained model by using the EASCMD client.
DSW contains a built-in EASCMD client for official DSW images. Path: /home/pai/bin. For more information, see Deploy model services by using EASCMD or DSW.
References
After the model service is deployed, you can go to the EAS-Online Model Services page to view the deployment status and manage the model service. For more information, see Model service deployment by using the PAI console.
Elastic Algorithm Service (EAS) provides multiple deployment methods. You can select a method based on your business requirements. For more information, see Overview.
After the model service is deployed, you can use an automatic stress testing tool to test model performance. For more information, see Automatic service stress testing.
If the processors provided by EAS cannot meet your model deployment requirements, you can create a custom processor based on the processor development standards. For more information, see Deploy services by using custom processors.