Whether the hard example mining algorithm can be customized

[tangming1996]

kubectl create -f - <<EOF apiVersion: sedna.io/v1alpha1 kind: JointInferenceService metadata: name: helmet-detection-inference-example namespace: default spec: edgeWorker: model: name: "helmet-detection-inference-little-model" hardExampleMining: name: "IBT" parameters: - key: "threshold_img" value: "0.9" - key: "threshold_box" value: "0.9" template: spec: ... ...

Can the hardExampleMining field be customized, and if so, how do I configure it？

[Louisxxr]

Same question of you Actually, I don't know the so-called "IBT" hard-example-mining algorithm Can anyone hit me?

[MooreZheng]

One can replace algorithms by first registering in the ClassFactory and then updating the yaml. An example for a similar purpose is provided in ianvs for your reference. In the ianvs example, the yaml name (algorithm.yaml) is not the same as Sedna, but the overall idea is consistent.