PyTorch图像处理器torchvision.ToTensor-归一化
文章目录
-
- 将图像转化为tensor
- 归一化 transforms.Normalize
- 公式
将图像转化为tensor
import torchvision.transforms as transforms
import numpy as np
import torch
import cv2
from matplotlib import pyplot as plt
import matplotlib.image as imgplt
img_path = "1.jpg"
# transforms.ToTensor()
transform1 = transforms.Compose([
transforms.ToTensor(), # range [0, 255] -> [0.0,1.0]
]
)
##numpy.ndarray
img = cv2.imread(img_path)# 读取图像
img1 = transform1(img) # 归一化到 [0.0,1.0]
print("img.shape = ",img.shape)
print("img1.shape = ",img1.shape)
print("img = ",img)
print("img1 = ",img1)
img.shape = (424, 640, 3)
img1.shape = torch.Size([3, 424, 640])
img = [[[249 246 231]
[248 246 228]
[247 245 227]
...
[ 17 19 20]
[ 20 19 21]
[ 32 14 21]]
[[249 246 231]
[248 246 228]
[247 245 227]
...
[ 29 30 20]
[ 29 30 20]
[ 15 24 14]]
[[248 245 230]
[248 245 230]
[248 246 228]
...
[ 80 41 26]
[ 80 41 26]
[ 45 36 16]]
...
[[169 175 216]
[174 178 219]
[167 173 210]
...
[ 14 17 22]
[ 14 17 22]
[ 15 18 23]]
[[151 157 202]
[163 167 208]
[172 174 209]
...
[ 14 17 22]
[ 13 16 21]
[ 13 16 21]]
[[168 171 215]
[173 174 212]
[179 177 207]
...
[ 13 16 21]
[ 12 15 20]
[ 11 13 21]]]
img1 = tensor([[[0.9765, 0.9725, 0.9686, ..., 0.0667, 0.0784, 0.1255],
[0.9765, 0.9725, 0.9686, ..., 0.1137, 0.1137, 0.0588],
[0.9725, 0.9725, 0.9725, ..., 0.3137, 0.3137, 0.1765],
...,
[0.6627, 0.6824, 0.6549, ..., 0.0549, 0.0549, 0.0588],
[0.5922, 0.6392, 0.6745, ..., 0.0549, 0.0510, 0.0510],
[0.6588, 0.6784, 0.7020, ..., 0.0510, 0.0471, 0.0431]],
[[0.9647, 0.9647, 0.9608, ..., 0.0745, 0.0745, 0.0549],
[0.9647, 0.9647, 0.9608, ..., 0.1176, 0.1176, 0.0941],
[0.9608, 0.9608, 0.9647, ..., 0.1608, 0.1608, 0.1412],
...,
[0.6863, 0.6980, 0.6784, ..., 0.0667, 0.0667, 0.0706],
[0.6157, 0.6549, 0.6824, ..., 0.0667, 0.0627, 0.0627],
[0.6706, 0.6824, 0.6941, ..., 0.0627, 0.0588, 0.0510]],
[[0.9059, 0.8941, 0.8902, ..., 0.0784, 0.0824, 0.0824],
[0.9059, 0.8941, 0.8902, ..., 0.0784, 0.0784, 0.0549],
[0.9020, 0.9020, 0.8941, ..., 0.1020, 0.1020, 0.0627],
...,
[0.8471, 0.8588, 0.8235, ..., 0.0863, 0.0863, 0.0902],
[0.7922, 0.8157, 0.8196, ..., 0.0863, 0.0824, 0.0824],
[0.8431, 0.8314, 0.8118, ..., 0.0824, 0.0784, 0.0824]]])
可以看到，使用transforms.ToTensor将图像转化为tensor
归一化 transforms.Normalize
transform1 = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize(mean = (0.5, 0.5, 0.5), std = (0.5, 0.5, 0.5))
]
)
将源代码修改为现在这样
img_path = "1.jpg"
# transforms.ToTensor()
transform2 = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize(mean = (0.5, 0.5, 0.5), std = (0.5, 0.5, 0.5))
]
)
##numpy.ndarray
import torchvision.transforms as transforms
import numpy as np
import torch
import cv2
from matplotlib import pyplot as plt
import matplotlib.image as imgplt
img_path = "1.jpg"
# transforms.ToTensor()
transform1 = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize(mean = (0.5, 0.5, 0.5), std = (0.5, 0.5, 0.5))
]
)
##numpy.ndarray
img = cv2.imread(img_path)# 读取图像
img1 = transform1(img) # 归一化到 [0.0,1.0]
print("img.shape = ",img.shape)
print("img1.shape = ",img1.shape)
print("img = ",img)
print("img1 = ",img1)
img.shape = (424, 640, 3)
img1.shape = torch.Size([3, 424, 640])
img = [[[249 246 231]
[248 246 228]
[247 245 227]
...
[ 17 19 20]
[ 20 19 21]
[ 32 14 21]]
[[249 246 231]
[248 246 228]
[247 245 227]
...
[ 29 30 20]
[ 29 30 20]
[ 15 24 14]]
[[248 245 230]
[248 245 230]
[248 246 228]
...
[ 80 41 26]
[ 80 41 26]
[ 45 36 16]]
...
[[169 175 216]
[174 178 219]
[167 173 210]
...
[ 14 17 22]
[ 14 17 22]
[ 15 18 23]]
[[151 157 202]
[163 167 208]
[172 174 209]
...
[ 14 17 22]
[ 13 16 21]
[ 13 16 21]]
[[168 171 215]
[173 174 212]
[179 177 207]
...
[ 13 16 21]
[ 12 15 20]
[ 11 13 21]]]
img1 = tensor([[[ 0.9529, 0.9451, 0.9373, ..., -0.8667, -0.8431, -0.7490],
[ 0.9529, 0.9451, 0.9373, ..., -0.7725, -0.7725, -0.8824],
[ 0.9451, 0.9451, 0.9451, ..., -0.3725, -0.3725, -0.6471],
...,
[ 0.3255, 0.3647, 0.3098, ..., -0.8902, -0.8902, -0.8824],
[ 0.1843, 0.2784, 0.3490, ..., -0.8902, -0.8980, -0.8980],
[ 0.3176, 0.3569, 0.4039, ..., -0.8980, -0.9059, -0.9137]],
[[ 0.9294, 0.9294, 0.9216, ..., -0.8510, -0.8510, -0.8902],
[ 0.9294, 0.9294, 0.9216, ..., -0.7647, -0.7647, -0.8118],
[ 0.9216, 0.9216, 0.9294, ..., -0.6784, -0.6784, -0.7176],
...,
[ 0.3725, 0.3961, 0.3569, ..., -0.8667, -0.8667, -0.8588],
[ 0.2314, 0.3098, 0.3647, ..., -0.8667, -0.8745, -0.8745],
[ 0.3412, 0.3647, 0.3882, ..., -0.8745, -0.8824, -0.8980]],
[[ 0.8118, 0.7882, 0.7804, ..., -0.8431, -0.8353, -0.8353],
[ 0.8118, 0.7882, 0.7804, ..., -0.8431, -0.8431, -0.8902],
[ 0.8039, 0.8039, 0.7882, ..., -0.7961, -0.7961, -0.8745],
...,
[ 0.6941, 0.7176, 0.6471, ..., -0.8275, -0.8275, -0.8196],
[ 0.5843, 0.6314, 0.6392, ..., -0.8275, -0.8353, -0.8353],
[ 0.6863, 0.6627, 0.6235, ..., -0.8353, -0.8431, -0.8353]]])
可以看到，最后的数组，值的范围变成了[-1,1]
公式
transforms.Normalize使用如下公式进行归一化：
channel=（channel-mean）/std
也就是说 ( (0,1) - 0.5 ) / 0.5 = (-1,1)