【pytorch】|transforms.FiveCrop

Common image transformation
There are four categories to summarize here

tailoring （Crop）

Center cut ：transforms.CenterCrop
Random cutting ：transforms.RandomCrop
Random aspect ratio tailoring ：transforms.RandomResizedCrop
Top, bottom, left and right center cut ：transforms.FiveCrop
Cut the top, bottom, left and right center, and then flip ,transforms.TenCrop

Flip and rotate （Flip and Rotation）

According to probability p Flip horizontal ：transforms.RandomHorizontalFlip(p=0.5)
According to probability p Flip vertically ：transforms.RandomVerticalFlip(p=0.5)
Random rotation ：transforms.RandomRotation

Image transformation （resize）transforms.Resize

Standardization ：transforms.Normalize
To tensor, And normalized to [0-1]：transforms.ToTensor
fill ：transforms.Pad
Change the brightness 、 Contrast and saturation ：transforms.ColorJitter
Go to grayscale ：transforms.Grayscale
linear transformation ：transforms.LinearTransformation()
Affine transformation ：transforms.RandomAffine
According to probability p Turn to grayscale ：transforms.RandomGrayscale
Convert data to PILImage：transforms.ToPILImage
take lambda Apply as transform ：transforms.Lambda

Yes transforms operation , Make data enhancement more flexible

From a given series of transforms Choose one of them to operate ：transforms.RandomChoice(transforms),
Give me a transform Plus the probability , Operate according to probability ：transforms.RandomApply(transforms, p=0.5)
take transforms The operations in are randomly disrupted ：

import torchvision
import torchvision.transforms as transform
from PIL import Image
import matplotlib.pyplot as plt
import numpy as np
import torch
img0=Image.open('imge.png')
resize = torchvision.transforms.Resize((224,224))
img0_r=resize(img0)
img1=transform.FiveCrop((112,112))(img0_r)
axs = plt.figure().subplots(1, 6)
axs[0].imshow(img0_r);axs[0].set_title('src');axs[0].axis('off')
axs[1].imshow(img1[0]);axs[1].set_title('1');axs[1].axis('off')
axs[2].imshow(img1[1]);axs[2].set_title('2');axs[2].axis('off')
axs[3].imshow(img1[2]);axs[3].set_title('3');axs[3].axis('off')
axs[4].imshow(img1[3]);axs[4].set_title('4');axs[4].axis('off')
axs[5].imshow(img1[4]);axs[5].set_title('5');axs[5].axis('off')
plt.show()