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

api object tensorflow detection
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

Related questions

How should I deal with object hierarchies in a RESTful API?

I am currently designing the API for an existing PHP application, and to this end am investigating REST as a sensible architectural approach. I believe I have a reasonable grasp of the key concepts, but I'm struggling to find anybody …

Read More
Get data from an array of stdClass object

I'm trying to retrieve the value of the field from the Vimeo Api, I've tried all possible solutions mentioned here. Can someone tell me how to retrieve the thumnail and url from the thumbnails and urls object respectively? array(1) { [0]=> …

Read More
No 'Access-Control-Allow-Origin' header is present on the requested resource—when trying to get data from a REST API

I'm trying to fetch some data from the REST API of HP Alm. It works pretty well with a small curl script - I get my data. Now doing that with JavaScript, fetch and ES6 (more or less) seems to …

Read More