Classification

Navigate back: Modules

What is Classification?

Classification categorizes images into several preset classes by users. Classification predicts probabilites that a given image belongs to each class, and then choose the heighest score's class as the image's category.

Workflow for Classification

The workflow of Classification is not much different from the basic's. Make sure you have first read Common workflow. This section offers only Classification -specific workflow.

1. Construct handles of model file and inspection results through Classification's handle construction.
2. (Optional) Check Classification's class information.
3. (Optional) Check Inspection options and set new values.
   • Additional scores
   • Classification's forward time limit
4. Allocate memory on cpu and gpu through Memory-allocation functions.
5. Inspect images through Classification's inspection functions.
6. Retrieve inspection results through Classification's inspection results.
7. Destruct handles of model file and inspection results through Classification's handle destruction.
   

Examples

• ExampleClsErrorHandling.cpp
• ExampleClsRuntime.cpp
• ExampleClsRuntimeSimple.cpp
• ExampleClsRuntimeBatchInspection.cpp