pytorch transforms使用和演示

pytorch transforms实例演示

演示下transforms的效果，供大家一个参考吧

首先准备下需要用到的图片

import matplotlib.pyplot as plt
import torchvision.transforms as tf
from PIL import Image
import PIL
import numpy as np
import torch
import imageio


def show(img, transform=None):
    if transform:
        if isinstance(transform, (tf.FiveCrop, tf.TenCrop)):
            t = transform(img)
            for i in range(len(t)):
                plt.subplot(len(t)/5, 5, 1+i)
                plt.axis('off')
                plt.imshow(t[i])
        else:
            for i in range(9):
                plt.subplot(331 + i)
                plt.axis('off')
                t= transform(img)
                plt.imshow(t)
        print(str(transform))
        print(t)
    else:
        plt.imshow(img)
        plt.axis('off')
    plt.show()

    
img = imageio.imread('http://ww1.sinaimg.cn/large/7ec23716gy1g6rx3xt8x1j203d02j3ye.jpg')
img = Image.fromarray(img)
print(img)
show(img)

<PIL.Image.Image image mode=RGB size=121x91 at 0x1F1687DD8D0>

RandomHorizontalFlip,RandomVerticalFlip - 水平翻转，垂直翻转

# multiplt img
t = tf.RandomHorizontalFlip()
show(img, t)
show(img, tf.RandomVerticalFlip())

RandomHorizontalFlip(p=0.5)
<PIL.Image.Image image mode=RGB size=121x91 at 0x1F1687DD8D0>

RandomVerticalFlip(p=0.5)
<PIL.Image.Image image mode=RGB size=121x91 at 0x1F1687DD8D0>

CenterCrop - 中心裁剪，以图片中心为起点，按像素大小进行裁剪

show(img, tf.CenterCrop(60))  # 小于图片大小则进行中心缩放
show(img, tf.CenterCrop(150))  # 大于图片大小则进行中心缩小，边缘填充0

CenterCrop(size=(60, 60))
<PIL.Image.Image image mode=RGB size=60x60 at 0x1F168D8A390>

CenterCrop(size=(150, 150))
<PIL.Image.Image image mode=RGB size=150x150 at 0x1F169F81240>

RandomCrop - 随机取不同的点作为中心进行裁剪

show(img, tf.RandomCrop(60))
show(img, tf.RandomCrop(100,padding=50, pad_if_needed=True))
show(img, tf.RandomCrop(100,padding=50, pad_if_needed=True, fill=255))

RandomCrop(size=(60, 60), padding=None)
<PIL.Image.Image image mode=RGB size=60x60 at 0x1F16A029048>

RandomCrop(size=(100, 100), padding=50)
<PIL.Image.Image image mode=RGB size=100x100 at 0x1F168B805F8>

RandomCrop(size=(100, 100), padding=50)
<PIL.Image.Image image mode=RGB size=100x100 at 0x1F168AABC50>

RandomResizedCrop - 先crop，再resize，将给定图像随机裁剪为不同的大小和宽高比，然后缩放所裁剪得到的图像为制定的大小

• size为缩放之后的大小
• scala为裁剪比例
• ratio为伸缩比例
• interpolation为resize模式

show(img, tf.RandomResizedCrop(60))
show(img, tf.RandomResizedCrop(150))
show(img, tf.RandomResizedCrop(60, scale=(0.5, 2.0)))  # 缩放比例
show(img, tf.RandomResizedCrop(60, ratio=(1/2, 2/1)))  # 拉伸比例

RandomResizedCrop(size=(60, 60), scale=(0.08, 1.0), ratio=(0.75, 1.3333), interpolation=PIL.Image.BILINEAR)
<PIL.Image.Image image mode=RGB size=60x60 at 0x1F16A189668>

RandomResizedCrop(size=(150, 150), scale=(0.08, 1.0), ratio=(0.75, 1.3333), interpolation=PIL.Image.BILINEAR)
<PIL.Image.Image image mode=RGB size=150x150 at 0x1F1689A66A0>

RandomResizedCrop(size=(60, 60), scale=(0.5, 2.0), ratio=(0.75, 1.3333), interpolation=PIL.Image.BILINEAR)
<PIL.Image.Image image mode=RGB size=60x60 at 0x1F168DAAAC8>

RandomResizedCrop(size=(60, 60), scale=(0.08, 1.0), ratio=(0.5, 2.0), interpolation=PIL.Image.BILINEAR)
<PIL.Image.Image image mode=RGB size=60x60 at 0x1F169F69BE0>

ColorJitter - hsv颜色空间 色调（H），饱和度（S），明度（V）

show(img, tf.ColorJitter(brightness=0.5))  # 亮度
show(img, tf.ColorJitter(contrast=0.5))  # 对比度
show(img, tf.ColorJitter(saturation=0.5))  # 饱和度
show(img, tf.ColorJitter(hue=0.1))  # 色调，只能是-0.5~0.5，应该指的是可以逆时针旋转180度或顺时针旋转180度

ColorJitter(brightness=[0.5, 1.5], contrast=None, saturation=None, hue=None)
<PIL.Image.Image image mode=RGB size=121x91 at 0x1F16A025D68>

ColorJitter(brightness=None, contrast=[0.5, 1.5], saturation=None, hue=None)
<PIL.Image.Image image mode=RGB size=121x91 at 0x1F168AB0D68>

ColorJitter(brightness=None, contrast=None, saturation=[0.5, 1.5], hue=None)
<PIL.Image.Image image mode=RGB size=121x91 at 0x1F168BE3EF0>

ColorJitter(brightness=None, contrast=None, saturation=None, hue=[-0.1, 0.1])
<PIL.Image.Image image mode=RGB size=121x91 at 0x1F168A45828>

FiveCrop,TenCrop - 将一张图片裁剪出5张出来

• 输入(batch_size, channel, height, width)
• 输出(batch_size, ncrops, channel, height, width)

show(img, tf.FiveCrop(60))
# show(img, tf.FiveCrop(121))

FiveCrop(size=(60, 60))
(<PIL.Image.Image image mode=RGB size=60x60 at 0x1F16A00D470>, <PIL.Image.Image image mode=RGB size=60x60 at 0x1F16A00D208>, <PIL.Image.Image image mode=RGB size=60x60 at 0x1F16A00D5C0>, <PIL.Image.Image image mode=RGB size=60x60 at 0x1F168ACD048>, <PIL.Image.Image image mode=RGB size=60x60 at 0x1F16A00DA90>)

show(img, tf.TenCrop(60))
show(img, tf.TenCrop(60, vertical_flip=True))

TenCrop(size=(60, 60), vertical_flip=False)
(<PIL.Image.Image image mode=RGB size=60x60 at 0x1F16A00D710>, <PIL.Image.Image image mode=RGB size=60x60 at 0x1F168A7FF28>, <PIL.Image.Image image mode=RGB size=60x60 at 0x1F168A524E0>, <PIL.Image.Image image mode=RGB size=60x60 at 0x1F168A52CC0>, <PIL.Image.Image image mode=RGB size=60x60 at 0x1F168A52DA0>, <PIL.Image.Image image mode=RGB size=60x60 at 0x1F168A520F0>, <PIL.Image.Image image mode=RGB size=60x60 at 0x1F168A52E10>, <PIL.Image.Image image mode=RGB size=60x60 at 0x1F168A592B0>, <PIL.Image.Image image mode=RGB size=60x60 at 0x1F168B8A7F0>, <PIL.Image.Image image mode=RGB size=60x60 at 0x1F168A59D68>)

TenCrop(size=(60, 60), vertical_flip=True)
(<PIL.Image.Image image mode=RGB size=60x60 at 0x1F168A52CC0>, <PIL.Image.Image image mode=RGB size=60x60 at 0x1F168A52DA0>, <PIL.Image.Image image mode=RGB size=60x60 at 0x1F168A520F0>, <PIL.Image.Image image mode=RGB size=60x60 at 0x1F168A52E10>, <PIL.Image.Image image mode=RGB size=60x60 at 0x1F168B8A7F0>, <PIL.Image.Image image mode=RGB size=60x60 at 0x1F168A59D68>, <PIL.Image.Image image mode=RGB size=60x60 at 0x1F162FB22B0>, <PIL.Image.Image image mode=RGB size=60x60 at 0x1F168A59668>, <PIL.Image.Image image mode=RGB size=60x60 at 0x1F168CB14E0>, <PIL.Image.Image image mode=RGB size=60x60 at 0x1F168CB1898>)

Pad - 填充值

show(img, tf.Pad(20))
show(img, tf.Pad(20,padding_mode='edge'))
show(img, tf.Pad(20,padding_mode='reflect'))

Pad(padding=20, fill=0, padding_mode=constant)
<PIL.Image.Image image mode=RGB size=161x131 at 0x1F168B0B240>

Pad(padding=20, fill=0, padding_mode=edge)
<PIL.Image.Image image mode=RGB size=161x131 at 0x1F168900D30>

Pad(padding=20, fill=0, padding_mode=reflect)
<PIL.Image.Image image mode=RGB size=161x131 at 0x1F16A17AF60>

RandomPerspective - 透视变换

show(img, tf.RandomPerspective())

C:\ProgramData\Anaconda3\lib\site-packages\torchvision\transforms\functional.py:440: UserWarning: torch.gels is deprecated in favour of torch.lstsq and will be removed in the next release. Please use torch.lstsq instead.
  res = torch.gels(B, A)[0]


RandomPerspective(p=0.5)
<PIL.Image.Image image mode=RGB size=121x91 at 0x1F1687DD8D0>

RandomAffine - 仿射变换，有旋转，平移，缩放，剪切变换

show(img, tf.RandomAffine(50))  # 旋转角度
show(img, tf.RandomAffine(0, translate=(0.1,0.3)))  # 平移范围
show(img, tf.RandomAffine(0, scale=(0.5, 1)))  # 缩放比例
show(img, tf.RandomAffine(0, shear=50))  # 剪切变换
show(img, tf.RandomAffine(50, resample=PIL.Image.BILINEAR))  # TODO

RandomAffine(degrees=(-50, 50))
<PIL.Image.Image image mode=RGB size=121x91 at 0x1F16A0BE358>

RandomAffine(degrees=(0, 0), translate=(0.1, 0.3))
<PIL.Image.Image image mode=RGB size=121x91 at 0x1F16A1DDC50>

RandomAffine(degrees=(0, 0), scale=(0.5, 1))
<PIL.Image.Image image mode=RGB size=121x91 at 0x1F166449A90>

RandomAffine(degrees=(0, 0), shear=(-50, 50))
<PIL.Image.Image image mode=RGB size=121x91 at 0x1F16883F860>

RandomAffine(degrees=(-50, 50), resample=PIL.Image.BILINEAR)
<PIL.Image.Image image mode=RGB size=121x91 at 0x1F168A43198>

RandomGrayscale - 灰度模式

show(img, tf.RandomGrayscale(0.5))  # 使用0.5的概率进行灰度化

RandomGrayscale(p=0.5)
<PIL.Image.Image image mode=RGB size=121x91 at 0x1F1687DD8D0>

RandomErasing - 随机擦除

# Erasing还需要组合使用
t = tf.Compose([tf.ToTensor(),tf.RandomErasing(), tf.ToPILImage()])
show(img, t)

Compose(
    ToTensor()
    <torchvision.transforms.transforms.RandomErasing object at 0x000001F169F9CA20>
    ToPILImage()
)
<PIL.Image.Image image mode=RGB size=121x91 at 0x1F168A6DDA0>

lambda

def foo(x):
    r = x[0, ...] + 0.1
    print(x.shape, x.max(), x.min(), r.shape, r.max(), r.min())
    return r
t = tf.Compose([tf.ToTensor(),tf.Lambda(foo), tf.ToPILImage()])
show(img, t)

torch.Size([3, 91, 121]) tensor(0.9686) tensor(0.) torch.Size([91, 121]) tensor(1.0686) tensor(0.1275)
torch.Size([3, 91, 121]) tensor(0.9686) tensor(0.) torch.Size([91, 121]) tensor(1.0686) tensor(0.1275)
torch.Size([3, 91, 121]) tensor(0.9686) tensor(0.) torch.Size([91, 121]) tensor(1.0686) tensor(0.1275)
torch.Size([3, 91, 121]) tensor(0.9686) tensor(0.) torch.Size([91, 121]) tensor(1.0686) tensor(0.1275)
torch.Size([3, 91, 121]) tensor(0.9686) tensor(0.) torch.Size([91, 121]) tensor(1.0686) tensor(0.1275)
torch.Size([3, 91, 121]) tensor(0.9686) tensor(0.) torch.Size([91, 121]) tensor(1.0686) tensor(0.1275)
torch.Size([3, 91, 121]) tensor(0.9686) tensor(0.) torch.Size([91, 121]) tensor(1.0686) tensor(0.1275)
torch.Size([3, 91, 121]) tensor(0.9686) tensor(0.) torch.Size([91, 121]) tensor(1.0686) tensor(0.1275)
torch.Size([3, 91, 121]) tensor(0.9686) tensor(0.) torch.Size([91, 121]) tensor(1.0686) tensor(0.1275)
Compose(
    ToTensor()
    Lambda()
    ToPILImage()
)
<PIL.Image.Image image mode=L size=121x91 at 0x1F168AA24E0>