P11.常见的transforms（一）

11.1_call_使用

11.2ToTensor使用

1.代码如下：

点击查看代码

from PIL import Image
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms

img = Image.open("images/myphoto.png")
print(img)
writer = SummaryWriter("logs1")

#ToTensor
#trans_tensor是transforms.ToTensor这个类的实例化，trans_tensor是一个对象
trans_tensor = transforms.ToTensor()
img_tensor = trans_tensor(img)
writer.add_image("ToTensor",img_tensor)

writer.close()

2.运行结果如下：

点击查看代码

D:\anaconda3\envs\pytorch\python.exe D:/DeepLearning/Learn_torch/P10_UsefulTransforms.py
<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=3456x4608 at 0x15B627A9D00>

进程已结束,退出代码0

3.tensorboard打开

11.3Normalize使用(归一化）

1.计算公式

up主举例计算：

2.代码如下

点击查看代码

from PIL import Image
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms

img = Image.open("images/myphoto.png")
print(img)
writer = SummaryWriter("logs1")

#ToTensor
#trans_tensor是transforms.ToTensor这个类的实例化，trans_tensor是一个对象
trans_tensor = transforms.ToTensor()
img_tensor = trans_tensor(img)
writer.add_image("ToTensor",img_tensor)

# writer.close()
#Normalize
print(img_tensor[0][0][0])

trans_norm = transforms.Normalize([0.5,0.5,0.5],[0.5,0.5,0.5])
img_norm = trans_norm(img_tensor)
writer.add_image("ToNormalize",img_norm)

print(img_norm[0][0][0])
 writer.close()

3.归一化前后变化

4.tensorboard打开