pytorch transforms实例演示

程序员文章站 2022-03-17 14:15:39

...

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>

pytorch transforms实例演示

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>

pytorch transforms实例演示

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

pytorch transforms实例演示

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>

pytorch transforms实例演示

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

pytorch transforms实例演示

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>

pytorch transforms实例演示

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

pytorch transforms实例演示

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

pytorch transforms实例演示

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>

pytorch transforms实例演示

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>

pytorch transforms实例演示

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>

pytorch transforms实例演示

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>

pytorch transforms实例演示

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>

pytorch transforms实例演示

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

pytorch transforms实例演示

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

pytorch transforms实例演示

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

pytorch transforms实例演示

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>)

pytorch transforms实例演示

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>)

pytorch transforms实例演示

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>)

pytorch transforms实例演示

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>

pytorch transforms实例演示

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

pytorch transforms实例演示

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

pytorch transforms实例演示

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>

pytorch transforms实例演示

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>

pytorch transforms实例演示

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

pytorch transforms实例演示

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

pytorch transforms实例演示

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

pytorch transforms实例演示

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

pytorch transforms实例演示

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>

pytorch transforms实例演示

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>

pytorch transforms实例演示

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>

pytorch transforms实例演示

pytorch transforms实例演示

pytorch transforms实例演示

RandomHorizontalFlip,RandomVerticalFlip - 水平翻转，垂直翻转

CenterCrop - 中心裁剪，以图片中心为起点，按像素大小进行裁剪

RandomCrop - 随机取不同的点作为中心进行裁剪

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

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

FiveCrop,TenCrop - 将一张图片裁剪出5张出来

Pad - 填充值

RandomPerspective - 透视变换

RandomAffine - 仿射变换，有旋转，平移，缩放，剪切变换

RandomGrayscale - 灰度模式

RandomErasing - 随机擦除

lambda

html5 拖拽上传图片实例演示

Spring请求参数校验功能实例演示

HTML5 Canvas阴影使用方法实例演示

SQL_Server全文索引的使用实例演示

一款利用html5和css3动画排列人物头像的实例演示

List集合方法实例演示

pytorch 修改预训练model实例

Pytorch自己加载单通道图片用作数据集训练的实例

在pytorch 中计算精度、回归率、F1 score等指标的实例

html5 拖拽上传图片实例演示

pytorch transforms实例演示

pytorch transforms实例演示

RandomHorizontalFlip,RandomVerticalFlip - 水平翻转，垂直翻转

CenterCrop - 中心裁剪，以图片中心为起点，按像素大小进行裁剪

RandomCrop - 随机取不同的点作为中心进行裁剪

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

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

FiveCrop,TenCrop - 将一张图片裁剪出5张出来

Pad - 填充值

RandomPerspective - 透视变换

RandomAffine - 仿射变换，有旋转，平移，缩放，剪切变换

RandomGrayscale - 灰度模式

RandomErasing - 随机擦除

lambda

html5 拖拽上传图片实例演示

Spring请求参数校验功能实例演示

HTML5 Canvas阴影使用方法实例演示

SQL_Server全文索引的使用实例演示

一款利用html5和css3动画排列人物头像的实例演示

List集合方法实例演示

pytorch 修改预训练model实例

Pytorch自己加载单通道图片用作数据集训练的实例

在pytorch 中计算精度、回归率、F1 score等指标的实例

html5 拖拽上传图片实例演示

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