将 PIL 图像转换为张量时，为什么像素会发生变化? [英] While converting a PIL image into a tensor why the pixels are changing?

问题描述

transform = transforms.Compose([transforms.ToPILImage(), transforms.ToTensor()])

应用转换之前

应用转换后

Q.1 为什么要改变像素值?
Q.2 如何更正?

Q.1 Why the pixel values are changed?
Q.2 How to correct this?

推荐答案

我能够通过在转换之前对输入数据进行规范化来解决这个问题.
问题是 ToPILImage() 丢弃了所有大于 1 的值，因此亮像素变暗.

I was able to solve this problem by normalizing the input data before transforming it.
The problem was that ToPILImage() was discarding all the values which were greater than 1 hence the bright pixels became dark.

这里是工作代码的链接.

这篇关于将 PIL 图像转换为张量时，为什么像素会发生变化?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！