What Should I Do If an Error Occurs During Service Deployment

Before deploying a model as a service, you need to compile the configuration file and inference code based on the trained model.

If the confi.json configuration file or the customize_service.py inference code is missing in the model storage path, an error is displayed, as shown in the following figure.

Solutions:

Write the configuration file and inference code, and save them to the OBS directory where the model to be deployed resides. For details, see Introduction to Model Package Specifications.

Figure 1 Error