当前位置：首页 > 文章列表 > 文章 > python教程 > pytorch的兰德姆布森

pytorch的兰德姆布森

来源：dev.to 2025-02-08 10:50:11 0浏览收藏

文章小白一枚，正在不断学习积累知识，现将学习到的知识记录一下，也是将我的所得分享给大家！而今天这篇文章《pytorch的兰德姆布森》带大家来了解一下##content_title##，希望对大家的知识积累有所帮助，从而弥补自己的不足，助力实战开发！

给我买咖啡☕

*备忘录：

我的帖子解释了randomrotation（）。
我的帖子解释了randomaffine（）。
我的帖子解释了牛津iiitpet（）。

> randomperspective（）可以对图像进行随机的透视转换，如下所示：

*备忘录：

初始化的第一个参数是distortion_scale（可选默认：0.5型：int或float）： *备忘录：
- 它可以进行透视转换。
- 必须为0 < = x < = 1。
- 必须为0 < = x < = 1。
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。 *在为图像进行透视转换时，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 RandomPerspective
from torchvision.transforms.functional import InterpolationMode

randompers = RandomPerspective()
randompers = RandomPerspective(distortion_scale=0.5,
                               p=0.5,
                               interpolation=InterpolationMode.BILINEAR,
                               fill=0)
randompers
# RandomPerspective(p=0.5,
#                   distortion_scale=0.5,
#                   interpolation=InterpolationMode.BILINEAR,
#                   fill=0)

randompers.distortion_scale
# 0.5

randompers.p
# 0.5

randompers.interpolation
# <InterpolationMode.BILINEAR: 'bilinear'>

randompers.fill
# 0

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

ds0p1origin_data = OxfordIIITPet( # `ds` is distortion_scale.
    root="data",
    transform=RandomPerspective(distortion_scale=0, p=1)
)

ds01p1_data = OxfordIIITPet(
    root="data",
    transform=RandomPerspective(distortion_scale=0.1, p=1)
)

ds02p1_data = OxfordIIITPet(
    root="data",
    transform=RandomPerspective(distortion_scale=0.2, p=1)
)

ds03p1_data = OxfordIIITPet(
    root="data",
    transform=RandomPerspective(distortion_scale=0.3, p=1)
)

ds04p1_data = OxfordIIITPet(
    root="data",
    transform=RandomPerspective(distortion_scale=0.4, p=1)
)

ds05p1_data = OxfordIIITPet(
    root="data",
    transform=RandomPerspective(distortion_scale=0.5, p=1)
)

ds06p1_data = OxfordIIITPet(
    root="data",
    transform=RandomPerspective(distortion_scale=0.6, p=1)
)

ds07p1_data = OxfordIIITPet(
    root="data",
    transform=RandomPerspective(distortion_scale=0.7, p=1)
)

ds08p1_data = OxfordIIITPet(
    root="data",
    transform=RandomPerspective(distortion_scale=0.8, p=1)
)

ds09p1_data = OxfordIIITPet(
    root="data",
    transform=RandomPerspective(distortion_scale=0.9, p=1)
)

ds1p1_data = OxfordIIITPet(
    root="data",
    transform=RandomPerspective(distortion_scale=1, p=1)
)

p0_data = OxfordIIITPet(
    root="data",
    transform=RandomPerspective(p=0)
)

p05_data = OxfordIIITPet(
    root="data",
    transform=RandomPerspective(p=0.5)
)

p1_data = OxfordIIITPet(
    root="data",
    transform=RandomPerspective(p=1)
)

p1fgray_data = OxfordIIITPet( # `f` is fill.
    root="data",
    transform=RandomPerspective(p=1, fill=150)
)

p1fpurple_data = OxfordIIITPet(
    root="data",
    transform=RandomPerspective(p=1, fill=[160, 32, 240])
)

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, (im, _) in zip(range(1, 6), data):
        plt.subplot(1, 5, i)
        plt.imshow(X=im)
        plt.xticks(ticks=[])
        plt.yticks(ticks=[])
    plt.tight_layout()
    plt.show()

show_images1(data=origin_data, main_title="origin_data")
print()
show_images1(data=ds0p1origin_data, main_title="ds0p1origin_data")
show_images1(data=ds01p1_data, main_title="ds01p1_data")
show_images1(data=ds02p1_data, main_title="ds02p1_data")
show_images1(data=ds03p1_data, main_title="ds03p1_data")
show_images1(data=ds04p1_data, main_title="ds04p1_data")
show_images1(data=ds05p1_data, main_title="ds05p1_data")
show_images1(data=ds06p1_data, main_title="ds06p1_data")
show_images1(data=ds07p1_data, main_title="ds07p1_data")
show_images1(data=ds08p1_data, main_title="ds08p1_data")
show_images1(data=ds09p1_data, main_title="ds09p1_data")
show_images1(data=ds1p1_data, main_title="ds1p1_data")
print()
show_images1(data=p0_data, main_title="p0_data")
show_images1(data=p0_data, main_title="p0_data")
show_images1(data=p0_data, main_title="p0_data")
print()
show_images1(data=p05_data, main_title="p05_data")
show_images1(data=p05_data, main_title="p05_data")
show_images1(data=p05_data, main_title="p05_data")
print()
show_images1(data=p1_data, main_title="p1_data")
show_images1(data=p1_data, main_title="p1_data")
show_images1(data=p1_data, main_title="p1_data")
print()
show_images1(data=p1fgray_data, main_title="p1fgray_data")
show_images1(data=p1fpurple_data, main_title="p1fpurple_data")

# ↓ ↓ ↓ ↓ ↓ ↓ The code below is identical to the code above. ↓ ↓ ↓ ↓ ↓ ↓
def show_images2(data, main_title=None, ds=0.5, prob=0.5,
                 ip=InterpolationMode.BILINEAR, f=0):
    plt.figure(figsize=[10, 5])
    plt.suptitle(t=main_title, y=0.8, fontsize=14)
    for i, (im, _) in zip(range(1, 6), data):
        plt.subplot(1, 5, i)
        rp = RandomPerspective(distortion_scale=ds, p=prob, # Here
                               interpolation=ip, fill=f)
        plt.imshow(X=rp(im)) # Here
        plt.xticks(ticks=[])
        plt.yticks(ticks=[])
    plt.tight_layout()
    plt.show()

show_images2(data=origin_data, main_title="origin_data", ds=0)
print()
show_images2(data=origin_data, main_title="ds0p1origin_data", ds=0,
             prob=1)
show_images2(data=origin_data, main_title="ds01p1_data", ds=0.1, prob=1)
show_images2(data=origin_data, main_title="ds02p1_data", ds=0.2, prob=1)
show_images2(data=origin_data, main_title="ds03p1_data", ds=0.3, prob=1)
show_images2(data=origin_data, main_title="ds04p1_data", ds=0.4, prob=1)
show_images2(data=origin_data, main_title="ds05p1_data", ds=0.5, prob=1)
show_images2(data=origin_data, main_title="ds06p1_data", ds=0.6, prob=1)
show_images2(data=origin_data, main_title="ds07p1_data", ds=0.7, prob=1)
show_images2(data=origin_data, main_title="ds08p1_data", ds=0.8, prob=1)
show_images2(data=origin_data, main_title="ds09p1_data", ds=0.9, prob=1)
show_images2(data=origin_data, main_title="ds1p1_data", ds=1, prob=1)
print()
show_images2(data=origin_data, main_title="p0_data", prob=0)
show_images2(data=origin_data, main_title="p0_data", prob=0)
show_images2(data=origin_data, main_title="p0_data", prob=0)
print()
show_images2(data=origin_data, main_title="p05_data", prob=0.5)
show_images2(data=origin_data, main_title="p05_data", prob=0.5)
show_images2(data=origin_data, main_title="p05_data", prob=0.5)
print()
show_images2(data=origin_data, main_title="p1_data", prob=1)
show_images2(data=origin_data, main_title="p1_data", prob=1)
show_images2(data=origin_data, main_title="p1_data", prob=1)
print()
show_images2(data=origin_data, main_title="p1fgray_data", prob=1, f=150)
show_images2(data=origin_data, main_title="p1fpurple_data", prob=1,
             f=[160, 32, 240])

image description