Super Kai (Kazuya Ito)

Posted on Feb 21 • Edited on Apr 13

RandomRotation in PyTorch

#python #pytorch #randomrotation #v2

Buy Me a Coffee☕

*Memos:

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

RandomRotation() can randomly rotate an image as shown below:

*Memos:

The 1st argument for initialization is degrees(Required-Type:int, float or tuple/list(int or float)): *Memos:
- It can do rotation.
- It's the range of the degrees [min, max] so it must be min <= max.
- A tuple/list must be the 1D with 2 elements.
- A single value must be 0 <= x.
- A single value means [-degrees, +degrees].
The 2nd argument for initialization is interpolation(Optional-Default:InterpolationMode.NEAREST-Type:InterpolationMode).
The 3rd argument for initialization is expand(Optional-Default:False-Type:bool).
The 4th argument for initialization is center(Optional-Default:None-Type:tuple/list(int or float)): *Memos:
- It can change the center position of an image.
- It must be the 1D with 2 elements.
- If at least one value is x <= 0, an image isn't shown, only showing the background of the image.
The 5th argument for initialization is fill(Optional-Default:0-Type:int, float or tuple/list(int or float)): *Memos:
- It can change the background of an image. *The background can be seen when rotating an image.
- A tuple/list must be the 1D with 1 or 3 elements.
- If all values are x <= 0, it's black.
- If all values are 255 <= x, it's white.
The 1st argument is img(Required-Type:PIL Image or tensor(int)): *Memos:
- A tensor must be 3D.
- Don't use img=.
v2 is recommended to use according to V1 or V2? Which one should I use?.

from torchvision.datasets import OxfordIIITPet
from torchvision.transforms.v2 import RandomRotation
from torchvision.transforms.functional import InterpolationMode

rr = RandomRotation(degrees=90)
rr = RandomRotation(degrees=[-90, 90], 
                    interpolation=InterpolationMode.NEAREST,
                    expand=False,
                    center=None,
                    fill=0)
rr
# RandomRotation(degrees=[-90.0, 90.0],
#                interpolation=InterpolationMode.NEAREST,
#                expand=False,
#                fill=0)

rr.degrees
# [-90.0, 90.0]

rr.interpolation
# <InterpolationMode.NEAREST: 'nearest'>

rr.expand
# False

print(rr.center)
# None

rr.fill
# 0

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

d0origin_data = OxfordIIITPet( # `d` is degrees.
    root="data",
    transform=RandomRotation(degrees=0)
    # transform=RandomRotation(degrees=[0, 0])
)

d180_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=180)
    # transform=RandomRotation(degrees=[-180, 180])
    # transform=RandomRotation(degrees=[-360, 0])
    # transform=RandomRotation(degrees=[0, 360])
)

dn180_0_data = OxfordIIITPet( # `n` is negative.
    root="data",
    transform=RandomRotation(degrees=[-180, 0])
    # transform=RandomRotation(degrees=[180, 360])
)

d0_180_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[0, 180])
    # transform=RandomRotation(degrees=[-360, -180])
)

d15_15_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[15, 15])
    # transform=RandomRotation(degrees=[-345, -345])
)

d30_30_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[30, 30])
    # transform=RandomRotation(degrees=[-330, -330])
)

d45_45_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[45, 45])
    # transform=RandomRotation(degrees=[-315, -315])
)

d60_60_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[60, 60])
    # transform=RandomRotation(degrees=[-300, -300])
)

d75_75_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[75, 75])
    # transform=RandomRotation(degrees=[-285, -285])
)

d90_90_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[90, 90])
    # transform=RandomRotation(degrees=[-270, -270])
)

d105_105_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[105, 105])
    # transform=RandomRotation(degrees=[-255, -255])
)

d120_120_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[120, 120])
    # transform=RandomRotation(degrees=[-240, -240])
)

d135_135_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[135, 135])
    # transform=RandomRotation(degrees=[-225, -225])
)

d150_150_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[150, 150])
    # transform=RandomRotation(degrees=[-210, -210])
)

d165_165_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[165, 165])
    # transform=RandomRotation(degrees=[-195, -195])
)

d180_180_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[180, 180])
    # transform=RandomRotation(degrees=[-180, -180])
)

dn15n15_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[-15, -15])
    # transform=RandomRotation(degrees=[345, 345])
)

dn30n30_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[-30, -30])
    # transform=RandomRotation(degrees=[330, 330])
)

dn45n45_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[-45, -45])
    # transform=RandomRotation(degrees=[315, 315])
)

dn60n60_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[-60, -60])
    # transform=RandomRotation(degrees=[300, 300])
)

dn75n75_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[-75, -75])
    # transform=RandomRotation(degrees=[285, 285])
)

dn90n90_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[-90, -90])
    # transform=RandomRotation(degrees=[270, 270])
)

dn105n105_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[-105, -105])
    # transform=RandomRotation(degrees=[255, 255])
)

dn120n120_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[-120, -120])
    # transform=RandomRotation(degrees=[240, 240])
)

dn135n135_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[-135, -135])
    # transform=RandomRotation(degrees=[225, 225])
)

dn150n150_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[-150, -150])
    # transform=RandomRotation(degrees=[210, 210])
)

dn165n165_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[-165, -165])
    # transform=RandomRotation(degrees=[195, 195])
)

dn180n180_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[-180, -180])
    # transform=RandomRotation(degrees=[180, 180])
)

dn90n90expand_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[-90, -90], expand=True)
)

d180_180c270_200_data = OxfordIIITPet( # `c` is center.
    root="data",
    transform=RandomRotation(degrees=[180, 180], center=[270, 200])
)

dn45n45fgray_data = OxfordIIITPet( # `f` is fill.
    root="data",
    transform=RandomRotation(degrees=[-45, -45], fill=150)
    # transform=RandomRotation(degrees=[-45, -45], fill=[150])
)

d135_135fpurple_data = OxfordIIITPet(
    root="data",
    transform=RandomRotation(degrees=[135, 135], 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=d0origin_data, main_title="d0origin_data")
show_images1(data=d180_data, main_title="d180_data")
show_images1(data=dn180_0_data, main_title="dn180_0_data")
show_images1(data=d0_180_data, main_title="d0_180_data")
print()
show_images1(data=d0origin_data, main_title="d0origin_data")
show_images1(data=d15_15_data, main_title="d15_15_data")
show_images1(data=d30_30_data, main_title="d30_30_data")
show_images1(data=d45_45_data, main_title="d45_45_data")
show_images1(data=d60_60_data, main_title="d60_60_data")
show_images1(data=d75_75_data, main_title="d75_75_data")
show_images1(data=d90_90_data, main_title="d90_90_data")
show_images1(data=d105_105_data, main_title="d105_105_data")
show_images1(data=d120_120_data, main_title="d120_120_data")
show_images1(data=d135_135_data, main_title="d135_135_data")
show_images1(data=d150_150_data, main_title="d150_150_data")
show_images1(data=d165_165_data, main_title="d165_165_data")
show_images1(data=d180_180_data, main_title="d180_180_data")
print()
show_images1(data=d0origin_data, main_title="d0origin_data")
show_images1(data=dn15n15_data, main_title="dn15n15_data")
show_images1(data=dn30n30_data, main_title="dn30n30_data")
show_images1(data=dn45n45_data, main_title="dn45n45_data")
show_images1(data=dn60n60_data, main_title="dn60n60_data")
show_images1(data=dn75n75_data, main_title="dn75n75_data")
show_images1(data=dn90n90_data, main_title="dn90n90_data")
show_images1(data=dn105n105_data, main_title="dn105n105_data")
show_images1(data=dn120n120_data, main_title="dn120n120_data")
show_images1(data=dn135n135_data, main_title="dn135n135_data")
show_images1(data=dn150n150_data, main_title="dn150n150_data")
show_images1(data=dn165n165_data, main_title="dn165n165_data")
show_images1(data=dn180n180_data, main_title="dn180n180_data")
print()
show_images1(data=dn90n90expand_data, main_title="dn90n90expand_data")
show_images1(data=d180_180c270_200_data, main_title="d180_180c270_200_data")
show_images1(data=dn45n45fgray_data, main_title="dn45n45fgray_data")
show_images1(data=d135_135fpurple_data, main_title="d135_135fpurple_data")

# ↓ ↓ ↓ ↓ ↓ ↓ The code below is identical to the code above. ↓ ↓ ↓ ↓ ↓ ↓
def show_images2(data, main_title=None, d=None, ip=InterpolationMode.NEAREST,
                 e=False, c=None, f=0):
    plt.figure(figsize=[10, 5])
    plt.suptitle(t=main_title, y=0.8, fontsize=14)
    if main_title != "origin_data":
        for i, (im, _) in zip(range(1, 6), data):
            plt.subplot(1, 5, i)
            rr = RandomRotation(degrees=d, interpolation=ip,
                                expand=e, center=c, fill=f)
            plt.imshow(X=rr(im))
            plt.xticks(ticks=[])
            plt.yticks(ticks=[])
    else:
        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_images2(data=origin_data, main_title="origin_data")
print()
show_images2(data=origin_data, main_title="d0origin_data", d=0)
show_images2(data=origin_data, main_title="d180_data", d=180)
show_images2(data=origin_data, main_title="dn180_0_data", d=[-180, 0])
show_images2(data=origin_data, main_title="d0_180_data", d=[0, 180])
print()
show_images2(data=origin_data, main_title="d0origin_data", d=0)
show_images2(data=origin_data, main_title="d15_15_data", d=[15, 15])
show_images2(data=origin_data, main_title="d30_30_data", d=[30, 30])
show_images2(data=origin_data, main_title="d45_45_data", d=[45, 45])
show_images2(data=origin_data, main_title="d60_60_data", d=[60, 60])
show_images2(data=origin_data, main_title="d75_75_data", d=[75, 75])
show_images2(data=origin_data, main_title="d90_90_data", d=[90, 90])
show_images2(data=origin_data, main_title="d105_105_data", d=[105, 105])
show_images2(data=origin_data, main_title="d120_120_data", d=[120, 120])
show_images2(data=origin_data, main_title="d135_135_data", d=[135, 135])
show_images2(data=origin_data, main_title="d150_150_data", d=[150, 150])
show_images2(data=origin_data, main_title="d165_165_data", d=[165, 165])
show_images2(data=origin_data, main_title="d180_180_data", d=[180, 180])
print()
show_images2(data=origin_data, main_title="d0origin_data", d=0)
show_images2(data=origin_data, main_title="dn15n15_data", d=[-15, -15])
show_images2(data=origin_data, main_title="dn30n30_data", d=[-30, -30])
show_images2(data=origin_data, main_title="dn45n45_data", d=[-45, -45])
show_images2(data=origin_data, main_title="dn60n60_data", d=[-60, -60])
show_images2(data=origin_data, main_title="dn75n75_data", d=[-75, -75])
show_images2(data=origin_data, main_title="dn90n90_data", d=[-90, -90])
show_images2(data=origin_data, main_title="dn105n105_data", d=[-105, -105])
show_images2(data=origin_data, main_title="dn120n120_data", d=[-120, -120])
show_images2(data=origin_data, main_title="dn135n135_data", d=[-135, -135])
show_images2(data=origin_data, main_title="dn150n150_data", d=[-150, -150])
show_images2(data=origin_data, main_title="dn165n165_data", d=[-165, -165])
show_images2(data=origin_data, main_title="dn180n180_data", d=[-180, -180])
print()
show_images2(data=origin_data, main_title="dn90n90expand_data", d=[-90, -90],
             e=True)
show_images2(data=origin_data, main_title="d180_180c270_200_data",
             d=[180, 180], c=[270, 200])
show_images2(data=origin_data, main_title="dn45n45fgray_data", d=[-45, -45],
             f=150)
show_images2(data=origin_data, main_title="d135_135fpurple_data", d=[135, 135],
             f=[160, 32, 240])

Built for developers, by developers.

Whether you're building a simple prototype or a business-critical product, Heroku's fully-managed platform gives you the simplest path to delivering apps quickly — using the tools and languages you already love!

Learn More

Top comments (0)

Check out Episode 1: How a Hackathon Project Became a Web3 Startup 🚀

Ever wondered what it takes to build a web3 startup from scratch? In the Stellar Dev Diaries series, we follow the journey of a team of developers building on the Stellar Network as they go from hackathon win to getting funded and launching on mainnet.

DEV Community

RandomRotation in PyTorch

Built for developers, by developers.

Top comments (0)

Check out Episode 1: How a Hackathon Project Became a Web3 Startup 🚀

Okay