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
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 anythinghere is a list of what i tried
i tried training pet data set from Oxford-IIIT Pet Dataset as in here. It worked as expected
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 platformand 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 to1
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!