Model Deployment


(1) Configuration: provide necessary information in the inference configuration panel, and click the launch button to start the inference engine.

(2) Import & Export: export your inference configuration to a .prototxt file. Import your .prototxt file, and regain inference configuration.

(3) Inference: load an image and inference will be automatically executed. Or add multiple images to do a batch inference.

(4) View switch: Switch to "MView" and view all inference results in a glance. Switch to "SView" to view details of one specific inference.

A lot more functions are under development.