pytorch中的随机克罗普（1）-Python教程-PHP中文网

首页

后端开发

Python教程

pytorch中的随机克罗普（1）

Barbara Streisand

Jan 30, 2025 pm 12:12 PM

给我买咖啡☕

*备忘录：

我的帖子解释了牛津iiitpet（）。

Randomcrop（）可以随机裁剪图像，如下所示：

*备忘录：

- 元组/列表必须是具有1或2个元素的1D。
是[左上，右，底部]，可以从[左右，底部]或[左右右下]转换。一个元组/列表必须是1D，具有1、2或4个元素。
- 初始化的第三个参数是pad_if_needed（可选默认：false-type：bool）：
- 如果是错误的，并且大小小于原始图像或填充图像的填充图像，则出现错误。
- 如果它的真实且大小小于原始图像或填充图像的填充图像，则没有错误，则该图像被随机填充以变为尺寸。
初始化的第四个参数是填充（可选默认：0型：int，float或tuple/tuple/list（int或float））： *备忘录：
- >它可以更改图像的背景。 *当图像被正面填充时，可以看到背景。
- 元组/列表必须是具有1或3个元素的1D。
>
- 不使用img =。
建议根据V1或V2使用V2？我应该使用哪一个？

from torchvision.datasets import OxfordIIITPet
from torchvision.transforms.v2 import RandomCrop

randomcrop = RandomCrop(size=100)
randomcrop = RandomCrop(size=100,
                        padding=None,
                        pad_if_needed=False, 
                        fill=0,
                        padding_mode='constant')
randomcrop
# RandomCrop(size=(100, 100),
#            pad_if_needed=False,
#            fill=0,
#            padding_mode=constant)

randomcrop.size
# (100, 100)

print(randomcrop.padding)
# None

randomcrop.pad_if_needed
# False

randomcrop.fill
# 0

randomcrop.padding_mode
# 'constant'

origin_data = OxfordIIITPet(
    root="data",
    transform=None
)

s300_data = OxfordIIITPet( # `s` is size.
    root="data",
    transform=RandomCrop(size=300)
    # transform=RandomCrop(size=[300, 300])
)

s200_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=200)
)

s100_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=100)
)

s50_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=50)
)

s10_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=10)
)

s1_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=1)
)

s200_300_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=[200, 300])
)

s300_200_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=[300, 200])
)

s300p100_data = OxfordIIITPet( # `p` is padding.
    root="data",
    transform=RandomCrop(size=300, padding=100)
    # transform=RandomCrop(size=300, padding=[100, 100])
    # transform=RandomCrop(size=300, padding=[100, 100, 100, 100])
)

s300p200_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=300, padding=200)
)

s700_594p100origin_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=[700, 594], padding=100)
)

s300p100_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=300, padding=100)
)

s600_594p100_50origin_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=[600, 594], padding=[100, 50])
)

s300p100_50_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=300, padding=[100, 50])
)

s650_494p25_50_75_100origin_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=[650, 494], padding=[25, 50, 75, 100])
)

s300p25_50_75_100_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=300, padding=[25, 50, 75, 100])
)

s300_194pn100origin_data = OxfordIIITPet( # `n` is negative.
    root="data",
    transform=RandomCrop(size=[300, 194], padding=-100)
)

s150pn100_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=150, padding=-100)
)

s300_294pn50n100origin_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=[300, 294], padding=[-50, -100])
)

s150pn50n100_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=150, padding=[-50, -100])
)

s350_294pn25n50n75n100origin_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=[350, 294], padding=[-25, -50, -75, -100])
)

s150pn25n50n75n100_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=150, padding=[-25, -50, -75, -100])
)

s600_444p25_50origin_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=[600, 444], padding=[25, 50])
)

s200p25_50_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=200, padding=[25, 50])
)

s400_344pn25n50origin_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=[400, 344], padding=[-25, -50])
)

s200pn25n50_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=200, padding=[-25, -50])
)

s400_444p25n50origin_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=[400, 444], padding=[25, -50])
)

s200p25n50_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=200, padding=[25, -50])
)

s600_344pn25_50origin_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=[600, 344], padding=[-25, 50])
)

s200pn25_50_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=200, padding=[-25, 50])
)

s700_594p100fgrayorigin_data = OxfordIIITPet( # `f` is fill.
    root="data",
    transform=RandomCrop(size=[700, 594], padding=100, fill=150)
    # transform=RandomCrop(size=[700, 594], padding=100, fill=[150])
)

s300p100fgray_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=300, padding=100, fill=150)
)

s700_594p100fpurpleorigin_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=[700, 594], padding=100, fill=[160, 32, 240])
)

s300p100fpurple_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=300, padding=100, fill=[160, 32, 240])
)

s700_594p100pmconstorigin_data = OxfordIIITPet( # `pm` is padding_mode.
    root="data",                                # `const` is constant.
    transform=RandomCrop(size=[700, 594], padding=100, padding_mode='constant')
)

s300p100pmconst_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=300, padding=100, padding_mode='constant')
)

s700_594p100pmedgeorigin_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=[700, 594], padding=100, padding_mode='edge')
)

s300p100pmedge_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=300, padding=100, padding_mode='edge')
)

s700_594p100pmrefleorigin_data = OxfordIIITPet( # `refle` is reflect.
    root="data",
    transform=RandomCrop(size=[700, 594], padding=100, padding_mode='reflect')
)

s300p100pmrefle_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=300, padding=100, padding_mode='reflect')
)

s700_594p100pmsymmeorigin_data = OxfordIIITPet( # `symme` is symmetric.
    root="data",
    transform=RandomCrop(size=[700, 594], padding=100, 
                         padding_mode='symmetric')
)

s300p100pmsymme_data = OxfordIIITPet(
    root="data",
    transform=RandomCrop(size=300, padding=100, padding_mode='symmetric')
)

import matplotlib.pyplot as plt

def show_images1(data, main_title=None):
    plt.figure(figsize=(10, 5))
    plt.suptitle(t=main_title, y=0.8, fontsize=14)
    for i in range(1, 6):
        plt.subplot(1, 5, i)
        plt.imshow(X=data[0][0])
    plt.tight_layout()
    plt.show()

plt.figure(figsize=(7, 9))
plt.title(label="s500_394origin_data", fontsize=14)
plt.imshow(X=origin_data[0][0])
show_images1(data=origin_data, main_title="s500_394origin_data")
show_images1(data=s300_data, main_title="s300_data")
show_images1(data=s200_data, main_title="s200_data")
show_images1(data=s100_data, main_title="s100_data")
show_images1(data=s50_data, main_title="s50_data")
show_images1(data=s10_data, main_title="s10_data")
show_images1(data=s1_data, main_title="s1_data")
show_images1(data=s200_300_data, main_title="s200_300_data")
show_images1(data=s300_200_data, main_title="s300_200_data")
print()
show_images1(data=s700_594p100origin_data,
             main_title="s700_594p100origin_data")
show_images1(data=s300p100_data, main_title="s300p100_data")
print()
show_images1(data=s600_594p100_50origin_data,
             main_title="s600_594p100_50origin_data")
show_images1(data=s300p100_50_data, main_title="s300p100_50_data")
print()
show_images1(data=s650_494p25_50_75_100origin_data,
             main_title="s650_494p25_50_75_100origin_data")
show_images1(data=s300p25_50_75_100_data, 
             main_title="s300p25_50_75_100_data")
print()
show_images1(data=s300_194pn100origin_data,
             main_title="s300_194pn100origin_data")
show_images1(data=s150pn100_data, 
             main_title="s150pn100_data")
print()
show_images1(data=s300_294pn50n100origin_data,
             main_title="s300_294pn50n100origin_data")
show_images1(data=s150pn50n100_data, 
             main_title="s150pn50n100_data")
print()
show_images1(data=s350_294pn25n50n75n100origin_data,
             main_title="s350_294pn25n50n75n100origin_data")
show_images1(data=s150pn25n50n75n100_data, 
             main_title="s150pn25n50n75n100_data")
print()
show_images1(data=s600_444p25_50origin_data,
             main_title="s600_444p25_50origin_data")
show_images1(data=s200p25_50_data, 
             main_title="s200p25_50_data")
print()
show_images1(data=s400_344pn25n50origin_data,
             main_title="s400_344pn25n50origin_data")
show_images1(data=s200pn25n50_data, 
             main_title="s200pn25n50_data")
print()
show_images1(data=s400_444p25n50origin_data,
             main_title="s400_444p25n50origin_data")
show_images1(data=s200p25n50_data, 
             main_title="s200p25n50_data")
print()
show_images1(data=s600_344pn25_50origin_data,
             main_title="s600_344pn25_50origin_data")
show_images1(data=s200pn25_50_data, 
             main_title="s200pn25_50_data")
print()
show_images1(data=s700_594p100fgrayorigin_data,
             main_title="s700_594p100fgrayorigin_data")
show_images1(data=s300p100fgray_data, main_title="s300p100fgray_data")
print()
show_images1(data=s700_594p100fpurpleorigin_data,
             main_title="s700_594p100fpurpleorigin_data")
show_images1(data=s300p100fpurple_data, main_title="s300p100fpurple_data")
print()
show_images1(data=s700_594p100pmconstorigin_data,
             main_title="s700_594p100pmconstorigin_data")
show_images1(data=s300p100pmconst_data, main_title="s300p100pmconst_data")
print()
show_images1(data=s700_594p100pmedgeorigin_data,
             main_title="s700_594p100pmedgeorigin_data")
show_images1(data=s300p100pmedge_data, main_title="s300p100pmedge_data")
print()
show_images1(data=s700_594p100pmrefleorigin_data,
             main_title="s700_594p100pmrefleorigin_data")
show_images1(data=s300p100pmrefle_data, main_title="s300p100pmrefle_data")
print()
show_images1(data=s700_594p100pmsymmeorigin_data,
             main_title="s700_594p100pmsymmeorigin_data")
show_images1(data=s300p100pmsymme_data, main_title="s300p100pmsymme_data")

# ↓ ↓ ↓ ↓ ↓ ↓ The code below is identical to the code above. ↓ ↓ ↓ ↓ ↓ ↓
def show_images2(data, main_title=None, s=None, p=None,
                 pin=False, f=0, pm='constant'):
    plt.figure(figsize=(10, 5))
    plt.suptitle(t=main_title, y=0.8, fontsize=14)
    temp_s = s
    im = data[0][0]
    for i in range(1, 6):
        plt.subplot(1, 5, i)
        if not temp_s:
            s = [im.size[1], im.size[0]]
        rc = RandomCrop(size=s, padding=p, # Here
                        pad_if_needed=pin, fill=f, padding_mode=pm)
        plt.imshow(X=rc(im)) # Here
    plt.tight_layout()
    plt.show()

plt.figure(figsize=(7, 9))
plt.title(label="s500_394origin_data", fontsize=14)
plt.imshow(X=origin_data[0][0])
show_images2(data=origin_data, main_title="s500_394origin_data")
show_images2(data=origin_data, main_title="s300_data", s=300)
show_images2(data=origin_data, main_title="s200_data", s=200)
show_images2(data=origin_data, main_title="s100_data", s=100)
show_images2(data=origin_data, main_title="s50_data", s=50)
show_images2(data=origin_data, main_title="s10_data", s=10)
show_images2(data=origin_data, main_title="s1_data", s=1)
show_images2(data=origin_data, main_title="s200_300_data", s=[200, 300])
show_images2(data=origin_data, main_title="s300_200_data", s=[300, 200])
print()
show_images2(data=origin_data, main_title="s700_594p100origin_data",
             s=[700, 594], p=100)
show_images2(data=origin_data, main_title="s300p100_data", s=300, p=100)
print()
show_images2(data=origin_data, main_title="s600_594p100_50origin_data",
             s=[600, 594], p=[100, 50])
show_images2(data=origin_data, main_title="s300p100_50_data", s=300,
             p=[100, 50])
print()
show_images2(data=origin_data, main_title="s650_494p25_50_75_100origin_data",
             s=[650, 494], p=[25, 50, 75, 100])
show_images2(data=origin_data, main_title="s300p25_50_75_100_data", s=300, 
             p=[25, 50, 75, 100])
print()
show_images2(data=origin_data, main_title="s300_194pn100origin_data",
             s=[300, 194], p=-100)
show_images2(data=origin_data, main_title="s150pn100_data", s=150, p=-100)
print()
show_images2(data=origin_data, main_title="s300_294pn50n100origin_data",
             s=[300, 294], p=[-50, -100])
show_images2(data=origin_data, main_title="s150pn50n100_data", s=150,
             p=[-50, -100])
print()
show_images2(data=origin_data, main_title="s350_294pn25n50n75n100origin_data",
             s=[350, 294], p=[-25, -50, -75, -100])
show_images2(data=origin_data, main_title="s150pn25n50n75n100_data", s=150,
             p=[-25, -50, -75, -100])
print()
show_images2(data=origin_data, main_title="s600_444p25_50origin_data",
             s=[600, 444], p=[25, 50])
show_images2(data=origin_data, main_title="s200p25_50_data", s=200,
             p=[25, 50])
print()
show_images2(data=origin_data, main_title="s400_344pn25n50origin_data",
             s=[400, 344], p=[-25, -50])
show_images2(data=origin_data, main_title="s200pn25n50_data", s=200,
             p=[-25, -50])
print()
show_images2(data=origin_data, main_title="s400_444p25n50origin_data",
             s=[400, 444], p=[25, -50])
show_images2(data=origin_data, main_title="s200p25n50_data", s=200,
             p=[25, -50])
print()
show_images2(data=origin_data, main_title="s600_344pn25_50origin_data",
             s=[600, 344], p=[-25, 50])
show_images2(data=origin_data, main_title="s200pn25_50_data", s=200,
             p=[-25, 50])
print()
show_images2(data=origin_data, main_title="s700_594p100fgrayorigin_data", 
             s=[700, 594], p=100, f=150)
show_images2(data=origin_data, main_title="s300p100fgray_data", s=300,
             p=100, f=150)
print()
show_images2(data=origin_data, main_title="s700_594p100fpurpleorigin_data",
             s=[700, 594], p=100, f=[160, 32, 240])
show_images2(data=origin_data, main_title="s300p100fpurple_data", s=300,
             p=100, f=[160, 32, 240])
print()
show_images2(data=origin_data, main_title="s700_594p100pmconstorigin_data",
             s=[700, 594], p=100, pm='constant')
show_images2(data=origin_data, main_title="s300p100pmconst_data", s=300, 
             p=100, pm='constant')
print()
show_images2(data=origin_data, main_title="s700_594p100pmedgeorigin_data",
             s=[700, 594], p=100, pm='edge')
show_images2(data=origin_data, main_title="s300p100pmedge_data", s=300, 
             p=100, pm='edge')
print()
show_images2(data=origin_data, main_title="s700_594p100pmrefleorigin_data",
             s=[700, 594], p=100, pm='reflect')
show_images2(data=origin_data, main_title="s300p100pmrefle_data", s=300, 
             p=100, pm='reflect')
print()
show_images2(data=origin_data, main_title="s700_594p100pmsymmeorigin_data",
             s=[700, 594], p=100, pm='symmetric')
show_images2(data=origin_data, main_title="s300p100pmsymme_data", s=300, 
             p=100, pm='symmetric')

Image description

以上是pytorch中的随机克罗普（1）的详细内容。更多信息请关注PHP中文网其他相关文章！

声明

本文内容由网友自发贡献，版权归原作者所有，本站不承担相应法律责任。如您发现有涉嫌抄袭侵权的内容，请联系admin@php.cn

您如何切成python列表？May 02, 2025 am 12:14 AM

SlicingaPythonlistisdoneusingthesyntaxlist[start:stop:step].Here'showitworks:1)Startistheindexofthefirstelementtoinclude.2)Stopistheindexofthefirstelementtoexclude.3)Stepistheincrementbetweenelements.It'susefulforextractingportionsoflistsandcanuseneg

在Numpy阵列上可以执行哪些常见操作？May 02, 2025 am 12:09 AM

numpyallowsforvariousoperationsonArrays：1）basicarithmeticlikeaddition，减法，乘法和division; 2）evationAperationssuchasmatrixmultiplication; 3）element-wiseOperations wiseOperationswithOutexpliitloops; 4）

Python的数据分析中如何使用阵列？May 02, 2025 am 12:09 AM

Arresinpython，尤其是Throughnumpyandpandas，weessentialFordataAnalysis，offeringSpeedAndeffied.1）NumpyArseNable efflaysenable efficefliceHandlingAtaSetSetSetSetSetSetSetSetSetSetSetsetSetSetSetSetsopplexoperationslikemovingaverages.2）

列表的内存足迹与python数组的内存足迹相比如何？May 02, 2025 am 12:08 AM

列表sandnumpyArraysInpyThonHavedIfferentMemoryfootprints：listSaremoreFlexibleButlessMemory-效率，而alenumpyArraySareSareOptimizedFornumericalData.1）listsStorReereReereReereReereFerenceStoObjects，withoverHeadeBheadaroundAroundaroundaround64bytaround64bitson64-bitsysysysyssyssyssyssyssyssysssys2）

部署可执行的Python脚本时，如何处理特定环境的配置？May 02, 2025 am 12:07 AM

toensurepythonscriptsbehavecorrectlyacrycrossdevelvermations，登台和生产，USETHESTERTATE：1）Environment varriablesforsimplesettings，2）configurationFilesForefilesForcomPlexSetups，3）dynamiCofforAdaptapity.eachmethodofferSuniquebeneiquebeneiquebeneniqueBenefitsaniqueBenefitsandrefitsandRequiresandRequireSandRequireSca

您如何切成python阵列？May 01, 2025 am 12:18 AM

Python列表切片的基本语法是list[start:stop:step]。1.start是包含的第一个元素索引，2.stop是排除的第一个元素索引，3.step决定元素之间的步长。切片不仅用于提取数据，还可以修改和反转列表。

在什么情况下，列表的表现比数组表现更好？May 01, 2025 am 12:06 AM

ListSoutPerformarRaysin：1）DynamicsizicsizingandFrequentInsertions/删除，2）储存的二聚体和3）MemoryFeliceFiceForceforseforsparsedata，butmayhaveslightperformancecostsinclentoperations。

如何将Python数组转换为Python列表？May 01, 2025 am 12:05 AM

toConvertapythonarraytoalist，usEthelist（）constructororageneratorexpression.1）intimpthearraymoduleandcreateanArray.2）USELIST（ARR）或[XFORXINARR] to ConconverTittoalist，请考虑performorefformanceandmemoryfformanceandmemoryfformienceforlargedAtasetset。

See all articles