TensorFlow Object Detection API - what do the losses mean in the object detection api?

이양규 picture 이양규 · Jan 5, 2018 · Viewed 7.6k times · Source

What do each for the following losses mean? (in the TensorFlow Object detection API, while training FasterRCNN based models)

Loss/BoxClassifierLoss/classification_loss/mul_1

Loss/BoxClassifierLoss/localization_loss/mul_1

Loss/RPNLoss/localization_loss/mul_1

Loss/RPNLoss/objectness_loss/mul_1

clone_loss_1

Answer

Rohit Gupta picture Rohit Gupta · Feb 2, 2018

The losses for the Region Proposal Network:

Loss/RPNLoss/localization_loss/mul_1: Localization Loss or the Loss of the Bounding Box regressor for the RPN

Loss/RPNLoss/objectness_loss/mul_1: Loss of the Classifier that classifies if a bounding box is an object of interest or background

The losses for the Final Classifier:

Loss/BoxClassifierLoss/classification_loss/mul_1: Loss for the classification of detected objects into various classes: Cat, Dog, Airplane etc

Loss/BoxClassifierLoss/localization_loss/mul_1: Localization Loss or the Loss of the Bounding Box regressor