代码实战（小土堆）——常见的Transforms（二）

实现Resize

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

writer = SummaryWriter("logs")
img = Image.open("dataset/train/ants_image/0013035.jpg")

# Resize
print(img.size)
trans_resize = transforms.Resize((512, 512))

# PIL.img 经过resize——> PIL.img_resize
img_resize = trans_resize(img)

# 得到PIL类型的img，无法使用tensorboard显示，把img_resize变成tensor类型
trans_totensor = transforms.ToTensor()
img_resize = trans_totensor(img_resize)

writer.add_image("Resize", img_resize, 0)

writer.close()

结果 

Compose()的使用 

Compose()中的参数需要是一个列表，Python中，列表的表示形式为 [数据1， 数据2，...]，在Compose中，数据需要是 transforms类型，所以得到，Compose([transforms参数1，transforms参数2，...])。

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

writer = SummaryWriter("logs")
img = Image.open("dataset/train/ants_image/0013035.jpg")

#Compose
trans_totensor = transforms.ToTensor()
trans_resize_2 = transforms.Resize(512)

#PIL ——> PIL ——> tensor
trans_compose = transforms.Compose([trans_resize_2, trans_totensor])
img_resize_2 = trans_compose(img)
writer.add_image("Resize",img_resize_2, 1)

writer.close()

结果 

 RandomCrop()的使用 

随机裁剪

可以设置宽高：transforms.RandomCrop((400,500))

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

writer = SummaryWriter("logs")
img = Image.open("dataset/train/ants_image/0013035.jpg")

# RandomCrop
trans_random = transforms.RandomCrop(512)
trans_totensor = transforms.ToTensor()

trans_compose_2 = transforms.Compose([trans_random, trans_totensor])
for i in range(10):
    img_crop = trans_compose_2(img)
    writer.add_image("RandomCrop", img_crop, i)


writer.close()

结果