重新训练 Tensorflow 对象检测 API [英] Retrain Tensorflow Object detection API

问题描述

我已阅读有关如何使用 TensorFlow 对象检测 API 训练新类的教程.但是我想要做的是在预训练模型的已经训练好的类中添加一个新类.

I have read tutorials on how to train a new class using TensorFlow Object Detection API. But what I want to do is to add a new class to the already trained classes of a pre-trained model.

例如:MS-COCO 预训练模型有 90 个类.我想再添加一个类并检测 91 个类的对象.

For example : MS-COCO pre-trained model has 90 classes. I want to add one more class and detect objects for 91 classes.

推荐答案

Tensorflow 对象检测 API 支持从预训练的 MS COCO 检查点开始.只需设置

Tensorflow object detection API supports starting from a pre-trained MS COCO checkpoint. Just set

fine_tune_checkpoint: "/usr/home/username/tmp/model.ckpt-#####"
from_detection_checkpoint: true

在您的检测管道中.(官方参考:https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/configuring_jobs.md)

In your detection pipeline. (Official reference: https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/configuring_jobs.md)

您应该将带有额外类的图像添加到 coco 数据集并针对所有 91 个类进行微调，否则您的网络可能会忘记之前学到的内容而只检测新对象.

You should add the images with your extra class to the coco dataset and finetune for all 91 classes, or your network might forget what it learned previously and only detect the new object.

这篇关于重新训练 Tensorflow 对象检测 API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！