如何使用Python对图像数据集进行过采样? [英] How to oversample image dataset using Python?

问题描述

我正在处理一个不平衡的图像数据集(不同类)的多类分类问题.我尝试了 imblearn 库，但是它不适用于图像数据集.

I am working on a multiclass classification problem with an unbalanced dataset of images(different class). I tried imblearn library, but it is not working on the image dataset.

我有一个图像数据集，它属于3类，即A，B，C.A有1000个数据，B有300个数据，C有100个数据.我想对B和C类进行过采样，以便避免数据不平衡.请让我知道如何使用python对图像数据集进行过度采样.

I have a dataset of images belonging to 3 class namely A,B,C. A has 1000 data, B has 300 and C has 100. I want to oversample class B and C, so that I can avoid data imbalance. Please let me know how to oversample the image dataset using python.

推荐答案

感谢您的澄清.通常，您不要使用Python进行过采样.而是，您对数据库进行了预处理，从而复制了简化的类.在您引用的情况下，您可以复制B类中的所有内容，并制作C类中的所有内容的5个副本.这将使您的新平衡达到1000:600:500，这可能更适合您的训练常规.现在，您可以改组2100，而不是原始的1400张图像.

Thanks for the clarification. In general, you don't oversample with Python. Rather, you pre-process your data base, duplicating the short-handed classes. In the case you cite, you might duplicate everything in class B, and make 5 copies of everything in class C. This gives you a new balance of 1000:600:500, likely more palatable to your training routines. Instead of the original 1400 images, you now shuffle 2100.

能解决您的问题吗?

这篇关于如何使用Python对图像数据集进行过采样?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！