RandomAffine in PyTorch (4)

This content originally appeared on DEV Community and was authored by Super Kai (Kazuya Ito)

*Memos:

My post explains RandomAffine() about degrees, translate, fill and center argument.
My post explains RandomAffine() about scale argument.
My post explains RandomAffine() about shear argument (1).
My post explains OxfordIIITPet().

RandomAffine() can do random rotation or random affine transformation for an image as shown below:

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

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

shear0_0_0_0origin_data = OxfordIIITPet(
    root="data",
    transform=RandomAffine(degrees=[0, 0], shear=[0, 0, 0, 0])
)

shear0_0_10_10_data = OxfordIIITPet(
    root="data",
    transform=RandomAffine(degrees=[0, 0], shear=[0, 0, 10, 10])
    # transform=RandomAffine(degrees=[0, 0], shear=[0, 0, -170, -170])
)

shear0_0_20_20_data = OxfordIIITPet(
    root="data",
    transform=RandomAffine(degrees=[0, 0], shear=[0, 0, 20, 20])
    # transform=RandomAffine(degrees=[0, 0], shear=[0, 0, -160, -160])
)

shear0_0_30_30_data = OxfordIIITPet(
    root="data",
    transform=RandomAffine(degrees=[0, 0], shear=[0, 0, 30, 30])
    # transform=RandomAffine(degrees=[0, 0], shear=[0, 0, -150, -150])
)

shear0_0_40_40_data = OxfordIIITPet(
    root="data",
    transform=RandomAffine(degrees=[0, 0], shear=[0, 0, 40, 40])
    # transform=RandomAffine(degrees=[0, 0], shear=[0, 0, -140, -140])
)

shear0_0_50_50_data = OxfordIIITPet(
    root="data",
    transform=RandomAffine(degrees=[0, 0], shear=[0, 0, 50, 50])
    # transform=RandomAffine(degrees=[0, 0], shear=[0, 0, -130, -130])
)

shear0_0_60_60_data = OxfordIIITPet(
    root="data",
    transform=RandomAffine(degrees=[0, 0], shear=[0, 0, 60, 60])
    # transform=RandomAffine(degrees=[0, 0], shear=[0, 0, -120, -120])
)

shear0_0_70_70_data = OxfordIIITPet(
    root="data",
    transform=RandomAffine(degrees=[0, 0], shear=[0, 0, 70, 70])
    # transform=RandomAffine(degrees=[0, 0], shear=[0, 0, -110, -110])
)

shear0_0_80_80_data = OxfordIIITPet(
    root="data",
    transform=RandomAffine(degrees=[0, 0], shear=[0, 0, 80, 80])
    # transform=RandomAffine(degrees=[0, 0], shear=[0, 0, -100, -100])
)

shear0_0_90_90_data = OxfordIIITPet(
    root="data",
    transform=RandomAffine(degrees=[0, 0], shear=[0, 0, 90, 90])
    # transform=RandomAffine(degrees=[0, 0], shear=[0, 0, -90, -90])
)

shear0_0n10n10_data = OxfordIIITPet( # `n` is negative.
    root="data",
    transform=RandomAffine(degrees=[0, 0], shear=[0, 0, -10, -10])
    # transform=RandomAffine(degrees=[0, 0], shear=[0, 0, 170, 170])
)

shear0_0n20n20_data = OxfordIIITPet(
    root="data",
    transform=RandomAffine(degrees=[0, 0], shear=[0, 0, -20, -20])
    # transform=RandomAffine(degrees=[0, 0], shear=[0, 0, 160, 160])
)

shear0_0n30n30_data = OxfordIIITPet(
    root="data",
    transform=RandomAffine(degrees=[0, 0], shear=[0, 0, -30, -30])
    # transform=RandomAffine(degrees=[0, 0], shear=[0, 0, 150, 150])
)

shear0_0n40n40_data = OxfordIIITPet(
    root="data",
    transform=RandomAffine(degrees=[0, 0], shear=[0, 0, -40, -40])
    # transform=RandomAffine(degrees=[0, 0], shear=[0, 0, 140, 140])
)

shear0_0n50n50_data = OxfordIIITPet(
    root="data",
    transform=RandomAffine(degrees=[0, 0], shear=[0, 0, -50, -50])
    # transform=RandomAffine(degrees=[0, 0], shear=[0, 0, 130, 130])
)

shear0_0n60n60_data = OxfordIIITPet(
    root="data",
    transform=RandomAffine(degrees=[0, 0], shear=[0, 0, -60, -60])
    # transform=RandomAffine(degrees=[0, 0], shear=[0, 0, 120, 120])
)

shear0_0n70n70_data = OxfordIIITPet(
    root="data",
    transform=RandomAffine(degrees=[0, 0], shear=[0, 0, -70, -70])
    # transform=RandomAffine(degrees=[0, 0], shear=[0, 0, 110, 110])
)

shear0_0n80n80_data = OxfordIIITPet(
    root="data",
    transform=RandomAffine(degrees=[0, 0], shear=[0, 0, -80, -80])
    # transform=RandomAffine(degrees=[0, 0], shear=[0, 0, 100, 100])
)

shear0_0n90n90_data = OxfordIIITPet(
    root="data",
    transform=RandomAffine(degrees=[0, 0], shear=[0, 0, -90, -90])
    # transform=RandomAffine(degrees=[0, 0], shear=[0, 0, 90, 90])
)

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=shear0_0_0_0origin_data, 
             main_title="shear0_0_0_0origin_data")
show_images1(data=shear0_0_10_10_data, main_title="shear0_0_10_10_data")
show_images1(data=shear0_0_20_20_data, main_title="shear0_0_20_20_data")
show_images1(data=shear0_0_30_30_data, main_title="shear0_0_30_30_data")
show_images1(data=shear0_0_40_40_data, main_title="shear0_0_40_40_data")
show_images1(data=shear0_0_50_50_data, main_title="shear0_0_50_50_data")
show_images1(data=shear0_0_60_60_data, main_title="shear0_0_60_60_data")
show_images1(data=shear0_0_70_70_data, main_title="shear0_0_70_70_data")
show_images1(data=shear0_0_80_80_data, main_title="shear0_0_80_80_data")
show_images1(data=shear0_0_90_90_data, main_title="shear0_0_90_90_data")
print()
show_images1(data=shear0_0_0_0origin_data, 
             main_title="shear0_0_0_0origin_data")
show_images1(data=shear0_0n10n10_data, main_title="shear0_0n10n10_data")
show_images1(data=shear0_0n20n20_data, main_title="shear0_0n20n20_data")
show_images1(data=shear0_0n30n30_data, main_title="shear0_0n30n30_data")
show_images1(data=shear0_0n40n40_data, main_title="shear0_0n40n40_data")
show_images1(data=shear0_0n50n50_data, main_title="shear0_0n50n50_data")
show_images1(data=shear0_0n60n60_data, main_title="shear0_0n60n60_data")
show_images1(data=shear0_0n70n70_data, main_title="shear0_0n70n70_data")
show_images1(data=shear0_0n80n80_data, main_title="shear0_0n80n80_data")
show_images1(data=shear0_0n90n90_data, main_title="shear0_0n90n90_data")

# ↓ ↓ ↓ ↓ ↓ ↓ The code below is identical to the code above. ↓ ↓ ↓ ↓ ↓ ↓ 
def show_images2(data, main_title=None, d=0, t=None,
                 sc=None, sh=None, f=0, c=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)
        ra = RandomAffine(degrees=d, translate=t, scale=sc,
                          shear=sh, center=c, fill=f)
        plt.imshow(X=ra(im))
        plt.xticks(ticks=[])
        plt.yticks(ticks=[])
    plt.tight_layout()
    plt.show()

show_images2(data=origin_data, main_title="origin_data")
print()
show_images2(data=origin_data, main_title="shear0_0_0_0origin_data",
             d=[0, 0], sh=[0, 0, 0, 0])
show_images2(data=origin_data, main_title="shear0_0_10_10_data",
             d=[0, 0], sh=[0, 0, 10, 10])
show_images2(data=origin_data, main_title="shear0_0_20_20_data",
             d=[0, 0], sh=[0, 0, 20, 20])
show_images2(data=origin_data, main_title="shear0_0_30_30_data",
             d=[0, 0], sh=[0, 0, 30, 30])
show_images2(data=origin_data, main_title="shear0_0_40_40_data",
             d=[0, 0], sh=[0, 0, 40, 40])
show_images2(data=origin_data, main_title="shear0_0_50_50_data",
             d=[0, 0], sh=[0, 0, 50, 50])
show_images2(data=origin_data, main_title="shear0_0_60_60_data",
             d=[0, 0], sh=[0, 0, 60, 60])
show_images2(data=origin_data, main_title="shear0_0_70_70_data",
             d=[0, 0], sh=[0, 0, 70, 70])
show_images2(data=origin_data, main_title="shear0_0_80_80_data",
             d=[0, 0], sh=[0, 0, 80, 80])
show_images2(data=origin_data, main_title="shear0_0_90_90_data",
             d=[0, 0], sh=[0, 0, 90, 90])
print()
show_images2(data=origin_data, main_title="shear0_0_0_0origin_data",
             d=[0, 0], sh=[0, 0, 0, 0])
show_images2(data=origin_data, main_title="shear0_0n10n10_data",
             d=[0, 0], sh=[0, 0, -10, -10])
show_images2(data=origin_data, main_title="shear0_0n20n20_data",
             d=[0, 0], sh=[0, 0, -20, -20])
show_images2(data=origin_data, main_title="shear0_0n30n30_data",
             d=[0, 0], sh=[0, 0, -30, -30])
show_images2(data=origin_data, main_title="shear0_0n40n40_data",
             d=[0, 0], sh=[0, 0, -40, -40])
show_images2(data=origin_data, main_title="shear0_0n50n50_data",
             d=[0, 0], sh=[0, 0, -50, -50])
show_images2(data=origin_data, main_title="shear0_0n60n60_data",
             d=[0, 0], sh=[0, 0, -60, -60])
show_images2(data=origin_data, main_title="shear0_0n70n70_data",
             d=[0, 0], sh=[0, 0, -70, -70])
show_images2(data=origin_data, main_title="shear0_0n80n80_data",
             d=[0, 0], sh=[0, 0, -80, -80])
show_images2(data=origin_data, main_title="shear0_0n90n90_data",
             d=[0, 0], sh=[0, 0, -90, -90])

This content originally appeared on DEV Community and was authored by Super Kai (Kazuya Ito)

Print Share Comment Cite Upload Translate Updates

APA

Super Kai (Kazuya Ito) | Sciencx (2025-02-22T00:35:25+00:00) RandomAffine in PyTorch (4). Retrieved from https://www.scien.cx/2025/02/22/randomaffine-in-pytorch-4/

MLA

" » RandomAffine in PyTorch (4)." Super Kai (Kazuya Ito) | Sciencx - Saturday February 22, 2025, https://www.scien.cx/2025/02/22/randomaffine-in-pytorch-4/

HARVARD

Super Kai (Kazuya Ito) | Sciencx Saturday February 22, 2025 » RandomAffine in PyTorch (4)., viewed ,<https://www.scien.cx/2025/02/22/randomaffine-in-pytorch-4/>

VANCOUVER

Super Kai (Kazuya Ito) | Sciencx - » RandomAffine in PyTorch (4). [Internet]. [Accessed ]. Available from: https://www.scien.cx/2025/02/22/randomaffine-in-pytorch-4/

CHICAGO

" » RandomAffine in PyTorch (4)." Super Kai (Kazuya Ito) | Sciencx - Accessed . https://www.scien.cx/2025/02/22/randomaffine-in-pytorch-4/

IEEE

" » RandomAffine in PyTorch (4)." Super Kai (Kazuya Ito) | Sciencx [Online]. Available: https://www.scien.cx/2025/02/22/randomaffine-in-pytorch-4/. [Accessed: ]

rf:citation

» RandomAffine in PyTorch (4) | Super Kai (Kazuya Ito) | Sciencx | https://www.scien.cx/2025/02/22/randomaffine-in-pytorch-4/ |

Please log in to upload a file.

There are no updates yet.
Click the Upload button above to add an update.

You must be logged in to translate posts. Please log in or register.

Related Posts