RandomHorizontalFlip in PyTorch

#python #pytorch #randomhorizontalflip #v2

Buy Me a Coffee☕

*Memos:

My post explains RandomVerticalFlip().
My post explains OxfordIIITPet().

RandomHorizontalFlip() can flip an image randomly and horizontally as shown below:

*Memos:

The 1st argument for initialization is p(Optional-Default:0.5-Type:int or float): *Memos:
- It's the probability of whether an image is flipped or not.
- It must be 0 <= x <= 1.
The 1st argument is img(Required-Type:PIL Image or tensor(int)): *Memos:
- A tensor must be 2D or 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 RandomHorizontalFlip

rhf = RandomHorizontalFlip()
rhf = RandomHorizontalFlip(p=0.5)

rhf
# RandomHorizontalFlip(p=0.5)

rhf.p
# 0.5

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

noargs_data = OxfordIIITPet( # `noargs` is no arguments.
    root="data",
    transform=RandomHorizontalFlip()
    # transform=RandomHorizontalFlip(p=0)
)

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

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

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

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=noargs_data, main_title="noargs_data")
show_images1(data=noargs_data, main_title="noargs_data")
show_images1(data=noargs_data, main_title="noargs_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")

# ↓ ↓ ↓ ↓ ↓ ↓ The code below is identical to the code above. ↓ ↓ ↓ ↓ ↓ ↓
def show_images2(data, main_title=None, prob=0.5):
    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)
            rhf = RandomHorizontalFlip(p=prob)
            plt.imshow(X=rhf(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="noargs_data")
show_images2(data=origin_data, main_title="noargs_data")
show_images2(data=origin_data, main_title="noargs_data")
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)