本文介绍了用于图像分类和语义分割的图像预处理的处理方法,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
就针对不同类型的图像相关作品(例如图像分类,语义分割)的深度学习模型的训练而言,需要执行什么样的预处理工作?
In terms of training deep learning models for different types of image-related works, such as image classification, semantic segmentation, what kind of pre-processing works need to be performed?
例如,如果我想训练网络进行语义分割,是否需要将图像值(通常表示为nd数组)缩放到[0,1]
范围,还是将其保持在[0,255]
范围?谢谢.
For instance, if I want to train a network for semantic segmentation, do I need to scale the image value (normally represented as an nd-array) to [0,1]
range, or keep it as [0,255]
range? Thanks.
推荐答案
完成的工作很少,但实际上并没有总会完成的预处理集.
There are few things that are done but really there is no set or fix set of pre-processing that is always done.
以下是一些示例:
- 减去均值图像,
- 除以方差(较不常见)
- 标准化值
- 如果要处理真实"图像(例如人的图像),请水平翻转
- 随机农作物
- 翻译
这篇关于用于图像分类和语义分割的图像预处理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!