Hi all,
For Object detection model ,model config has objective set which defines what objectives is this network being trained for. For object detection networks, set it to learn cov and bbox. cov {} bbox { scale: 35.0 offset: 0.5
} These parameters should not be altered for the current training pipeline.
But my question is for cov they are not mentioning anything then how model will learn for cov and if i have to alter these values then how to alter.