没有子文件夹的Keras图像 [英] Keras images with no subfolders

问题描述

我是深度学习的新手。我有一个问题：我正在尝试使用此数据来训练网络。一切都在一个文件夹中，标签在另一个mat文件中。

I am new to Deep Learning. I have this question: I am trying to train a network with this data. Everything is in one folder and labels are in a different mat file.

我了解我可以使用scipy.io读取数据。但是，如何将火车X放在一个文件夹中？如果我使用内置的flow_from_directory，则它不会显示图像，因为每个类都应该有自己的文件夹。

I understand that I can read the data with scipy.io. But how can I get train X in one folder? If I use the built in flow_from_directory it shows no images, because every class should have it's own folder.

如何仅使用一个文件夹创建X？现在它显示找到了0个属于0类的图像

How can I create X with only one folder? Now it shows Found 0 images belonging to 0 classes

只有一个包含图像的文件夹。所有图像都在1个文件夹中。我的意思是没有classes文件夹。使用flow_from_directory，您应该拥有类似于car / mercedes，cars / bmw，cars / audi之类的东西，但是我的数据没有子文件夹。

There is just a folder with images. All images are in 1 folder. I mean there is no classes folder. With flow_from_directory you should have something like cars/mercedes, cars/bmw, cars/audi, but my data doesn't have subfolders.

所以我的问题还有创建X数据的其他方法吗？

So my question is there any other way to create X data?

推荐答案

将类设置为无，并将所有图像放入图像文件夹的一个子文件夹中。

Set classes to None and put all images into one subfolder of your image folder.

例如：

• flow_from_directory（directory = / path / to / your / images /，class_mode = None，…）


• 将图像放入 / path / to / your / images / data

• flow_from_directory(directory = "/path/to/your/images/", class_mode="None", …)
• put your images into /path/to/your/images/data

这篇关于没有子文件夹的Keras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！