Dev.to

Compose in PyTorch

Buy Me a Coffee☕ Memos: My post explains RandomInvert(). My post explains CenterCrop(). My post explains Pad(). My post explains OxfordIIITPet(). Compose() can apply one or more transformations to an image as shown below: Memos: The 1st argument for initialization is transforms(Required-Type:tuple/list of transformations): Memos: The transformations are applied from the 1st index in order. It must be at least one transformation. There is the 1st argument(Required-Type:PIL Image or tensor(int)). A tensor must be 3D. 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 Compose from torchvision.transforms.v2 import RandomInvert from torchvision.transforms.v2 import RandomVerticalFlip from torchvision.transforms.v2 import CenterCrop from torchvision.transforms.v2 import Pad c = Compose(transforms=[RandomInvert(p=1), RandomVerticalFlip(p=1), CenterCrop(size=200), Pad(padding=20)]) c # Compose(RandomInvert(p=1) # RandomVerticalFlip(p=1) # CenterCrop(size=(200, 200)) # Pad(padding=20, fill=0, padding_mode=constant)) c.transforms # [RandomInvert(p=1), # RandomVerticalFlip(p=1), # CenterCrop(size=(200, 200)), # Pad(padding=20, fill=0, padding_mode=constant)] origin_data = OxfordIIITPet( root="data", transform=None ) # `ri` is RandomInvert() and `rv` is RandomVerticalFlip(). # `cc` is CenterCrop() and `pad` is Pad(). ri_rv_cc_pad_data = OxfordIIITPet( root="data", transform=Compose(transforms=[RandomInvert(p=1), RandomVerticalFlip(p=1), CenterCrop(size=200), Pad(padding=20)]) ) ri_rv_pad_cc_data = OxfordIIITPet( root="data", transform=Compose(transforms=[RandomInvert(p=1), RandomVerticalFlip(p=1), Pad(padding=20), CenterCrop(size=200)]) ) 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=ri_rv_cc_pad_data, main_title="ri_rv_cc_pad_data") show_images1(data=ri_rv_pad_cc_data, main_title="ri_rv_pad_cc_data") # ↓ ↓ ↓ ↓ ↓ ↓ The code below is identical to the code above. ↓ ↓ ↓ ↓ ↓ ↓ def show_images2(data, main_title=None, t=None): 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) c = Compose(transforms=t) plt.imshow(X=c(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="ri_rv_cc_pad_data", t=[RandomInvert(p=1), RandomVerticalFlip(p=1), CenterCrop(size=200), Pad(padding=20)]) show_images2(data=origin_data, main_title="ri_rv_pad_cc_data", t=[RandomInvert(p=1), RandomVerticalFlip(p=1), Pad(padding=20), CenterCrop(size=200)])

Apr 17, 2025 - 03:16

Buy Me a Coffee☕

*Memos:

My post explains RandomInvert().
My post explains CenterCrop().
My post explains Pad().
My post explains OxfordIIITPet().

Compose() can apply one or more transformations to an image as shown below:

*Memos:

The 1st argument for initialization is transforms(Required-Type:tuple/list of transformations): *Memos:
- The transformations are applied from the 1st index in order.
- It must be at least one transformation.
There is the 1st argument(Required-Type:PIL Image or tensor(int)). *A tensor must be 3D.
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 Compose
from torchvision.transforms.v2 import RandomInvert
from torchvision.transforms.v2 import RandomVerticalFlip
from torchvision.transforms.v2 import CenterCrop 
from torchvision.transforms.v2 import Pad

c = Compose(transforms=[RandomInvert(p=1), RandomVerticalFlip(p=1), 
                        CenterCrop(size=200), Pad(padding=20)])
c
# Compose(RandomInvert(p=1)
#         RandomVerticalFlip(p=1)
#         CenterCrop(size=(200, 200))
#         Pad(padding=20, fill=0, padding_mode=constant))

c.transforms
# [RandomInvert(p=1),
#  RandomVerticalFlip(p=1),
#  CenterCrop(size=(200, 200)),
#  Pad(padding=20, fill=0, padding_mode=constant)]

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

# `ri` is RandomInvert() and `rv` is RandomVerticalFlip().
# `cc` is CenterCrop() and `pad` is Pad().
ri_rv_cc_pad_data = OxfordIIITPet(
    root="data",
    transform=Compose(transforms=[RandomInvert(p=1),
                                  RandomVerticalFlip(p=1),
                                  CenterCrop(size=200), 
                                  Pad(padding=20)])
)

ri_rv_pad_cc_data = OxfordIIITPet(
    root="data",
    transform=Compose(transforms=[RandomInvert(p=1),
                                  RandomVerticalFlip(p=1),
                                  Pad(padding=20),
                                  CenterCrop(size=200)])
)

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=ri_rv_cc_pad_data, main_title="ri_rv_cc_pad_data")
show_images1(data=ri_rv_pad_cc_data, main_title="ri_rv_pad_cc_data")

# ↓ ↓ ↓ ↓ ↓ ↓ The code below is identical to the code above. ↓ ↓ ↓ ↓ ↓ ↓
def show_images2(data, main_title=None, t=None):
    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)
            c = Compose(transforms=t)
            plt.imshow(X=c(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="ri_rv_cc_pad_data",
             t=[RandomInvert(p=1), RandomVerticalFlip(p=1),
                CenterCrop(size=200), Pad(padding=20)])
show_images2(data=origin_data, main_title="ri_rv_pad_cc_data",
             t=[RandomInvert(p=1), RandomVerticalFlip(p=1),
                Pad(padding=20), CenterCrop(size=200)])