Keras flow

本文介绍了Keras flow_from_directory限制示例数的处理方法，对大家解决问题具有一定的参考价值，需要的朋友们下面随着小编来一起学习吧！ 问题描述

在Keras中使用flow_from_directory并将每个子目录中使用的示例数限制为一定数量N时，最简单的方法是什么?

What's the simplest way I can use flow_from_directory in Keras while limiting the number of examples used in each subdirectory by some number N?

对于上下文，我希望能够使用全部图像的一小部分进行测试，而不必为较小的数据集创建单独的顶级目录，因为我是从AWS S3存储桶中提取此数据的在训练期间.

For context, I'd like to be able to use a small subset of the total images for testing purposes without having to create a separate top level directory for the smaller dataset, since I'm pulling this data from AWS S3 buckets during training.

推荐答案

使用参数validation_split指定为float的方式创建keras.preprocessing.image.ImageDataGenerator.在这种情况下，可以在flow_from_directory中使用参数subset从每个目录中仅获取一些样本.更多信息此处.

Create keras.preprocessing.image.ImageDataGenerator with argument validation_split specified as float. In such case you can use argument subset in flow_from_directory to get only some samples from each directory. More info here.

如果要从每个文件夹中专门获取N个图像，则必须计算每个目录中有多少个文件，并相应地设置训练验证拆分.

If you want N images from each folder specifically, you would have to calculate how many files are there in each directory, and set train-validation split accordingly.