Tensorflow 对象检测未在自定义数据集上学习(猴子图像) [英] Tensorflow Object Detection not learning on custom dataset (Monkey Images)

问题描述

我在自定义数据集上尝试 tensorflow 对象检测，由于某种原因，我的模型没有学习任何东西这是我尝试过的列表

1. 我尝试从 Oxford-IIIT Pet Dataset 训练宠物数据集，如

   信息:我在谷歌可以平台上进行培训，如并且没有看到精度增加.

   编辑 2

   链接到数据集.我没有使用这个数据集中的所有图像，因为其中一些是不相关的，我只使用了我注释的图像.

   解决方案

   一个问题可能是在配置文件中，类的数量是 37，但是对于您的数据集，您只有一个班级.尝试将配置文件中的 num_classes 更改为 1，看看会发生什么.

   Am trying tensorflow object detection on a custom dataset, for some reason my model is not learning anything here is a list of what i tried

   1. i tried training pet data set from Oxford-IIIT Pet Dataset as in here. It worked as expected

   2. Now i followed this tutorial to train my own dataset ( for testing am just using images of monkeys)

   but unfortunately my model is not learning anything

   Info : am training on google could platform as in this tutorial. My configuration pipeline config, my pbtxt.

   I created annotations using Labelimg

   EDIT

   No actual detection is seen even after 6hrs of training in google cloud platform and no increase in Precision is seen.

   EDIT 2

   link to dataset. I have not used all the images in this dataset as some of them were irrelevant, I have used only the images which i have annotated.

   解决方案

   One issue could be that in the config file, the number of classes is 37, but for your dataset you only have a single class. Try to change the num_classes in the config file to 1 and see what happens.

   这篇关于Tensorflow 对象检测未在自定义数据集上学习(猴子图像)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！