Dev.to

Grayscale in PyTorch

Buy Me a Coffee☕ Memos: My post explains OxfordIIITPet(). Grayscale() can convert an image to grayscale as shown below: Memos: The 1st argument for initialization is num_output_channels(Optional-Default:1-Type:int). It must be 1 or 3. 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 Grayscale grayscale = Grayscale() grayscale = Grayscale(num_output_channels=1) grayscale # Grayscale(num_output_channels=1) grayscale.num_output_channels # 1 origin_data = OxfordIIITPet( root="data", transform=None ) noc1_data = OxfordIIITPet( root="data", transform=Grayscale(num_output_channels=1) ) noc3_data = OxfordIIITPet( root="data", transform=Grayscale(num_output_channels=3) ) 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") show_images1(data=noc1_data, main_title="noc1_data") show_images1(data=noc3_data, main_title="noc3_data") # ↓ ↓ ↓ ↓ ↓ ↓ The code below is identical to the code above. ↓ ↓ ↓ ↓ ↓ ↓ def show_images2(data, main_title=None, noc=None): plt.figure(figsize=[10, 5]) plt.suptitle(t=main_title, y=0.8, fontsize=14) if noc: for i, (im, _) in zip(range(1, 6), data): plt.subplot(1, 5, i) gs = Grayscale(num_output_channels=noc) plt.imshow(X=gs(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") show_images2(data=origin_data, main_title="noc1_data", noc=1) show_images2(data=origin_data, main_title="noc3_data", noc=3)

Feb 14, 2025 - 17:44

Buy Me a Coffee☕

*Memos:

My post explains OxfordIIITPet().

Grayscale() can convert an image to grayscale as shown below:

*Memos:

The 1st argument for initialization is num_output_channels(Optional-Default:1-Type:int). *It must be 1 or 3.
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 Grayscale

grayscale = Grayscale()
grayscale = Grayscale(num_output_channels=1)

grayscale
# Grayscale(num_output_channels=1)

grayscale.num_output_channels
# 1

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

noc1_data = OxfordIIITPet(
    root="data",
    transform=Grayscale(num_output_channels=1)
)

noc3_data = OxfordIIITPet(
    root="data",
    transform=Grayscale(num_output_channels=3)
)

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")
show_images1(data=noc1_data, main_title="noc1_data")
show_images1(data=noc3_data, main_title="noc3_data")

# ↓ ↓ ↓ ↓ ↓ ↓ The code below is identical to the code above. ↓ ↓ ↓ ↓ ↓ ↓
def show_images2(data, main_title=None, noc=None):
    plt.figure(figsize=[10, 5])
    plt.suptitle(t=main_title, y=0.8, fontsize=14)
    if noc:
        for i, (im, _) in zip(range(1, 6), data):
            plt.subplot(1, 5, i)
            gs = Grayscale(num_output_channels=noc)
            plt.imshow(X=gs(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")
show_images2(data=origin_data, main_title="noc1_data", noc=1)
show_images2(data=origin_data, main_title="noc3_data", noc=3)