TensorFlow 对象检测 API - 对象检测 api 中的损失意味着什么? [英] TensorFlow Object Detection API - what do the losses mean in the object detection api?
问题描述
以下每个损失是什么意思?(在 TensorFlow 对象检测 API 中,同时训练基于 FasterRCNN 的模型)
What do each for the following losses mean? (in the TensorFlow Object detection API, while training FasterRCNN based models)
损失/BoxClassifierLoss/classification_loss/mul_1
Loss/BoxClassifierLoss/classification_loss/mul_1
损失/BoxClassifierLoss/localization_loss/mul_1
Loss/BoxClassifierLoss/localization_loss/mul_1
损失/RPNLoss/localization_loss/mul_1
Loss/RPNLoss/localization_loss/mul_1
损失/RPNLoss/objectness_loss/mul_1
Loss/RPNLoss/objectness_loss/mul_1
clone_loss_1
clone_loss_1
推荐答案
Region Proposal Network 的损失:
The losses for the Region Proposal Network:
Loss/RPNLoss/localization_loss/mul_1:定位损失或 RPN 边界框回归量的损失
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:对边界框是感兴趣的对象还是背景进行分类的分类器的损失
Loss/RPNLoss/objectness_loss/mul_1: Loss of the Classifier that classifies if a bounding box is an object of interest or background
最终分类器的损失:
Loss/BoxClassifierLoss/classification_loss/mul_1:将检测到的物体分类为各种类别的损失:猫、狗、飞机等
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:定位损失或边界框回归量的损失
Loss/BoxClassifierLoss/localization_loss/mul_1: Localization Loss or the Loss of the Bounding Box regressor
这篇关于TensorFlow 对象检测 API - 对象检测 api 中的损失意味着什么?的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!