Tensorflow对象检测API中的图验证损失 [英] Plot validation loss in Tensorflow Object Detection API

问题描述

我正在使用Tensorflow对象检测API来检测和定位图像中的一个类对象.为此，我使用了预先训练的faster_rcnn_resnet50_coco_2018_01_28模型.

I'm using Tensorflow Object Detection API for detection and localization of one class object in images. For these purposes I use pre-trained faster_rcnn_resnet50_coco_2018_01_28 model.

在训练模型后，我想检测不足/过度拟合.我看到了训练损失，但在评估Tensorboard后仅显示了mAP和Precision指标，而没有损失.

I want to detect under/overfitting after training of the model. I see training loss, but after evaluating Tensorboard only shows mAP and Precision metrics and no loss.

是否也可以在Tensorboard上绘制验证损失?

Is this possible to plot a validation loss on Tensorboard too?

推荐答案

存在验证丢失.假设您使用的是最新的API，则损失"下的曲线是验证损失，而损失_1/2"下的曲线是训练损失.

There is validation loss. Assuming you're using the latest API, the curve under "loss" is validation loss while "loss_1/2" is the training loss.

这篇关于Tensorflow对象检测API中的图验证损失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！