How to crop an image at center in PyTorch?

In this article, we will discuss how to crop an image at the center in PyTorch. 

CenterCrop() method

We can crop an image in PyTorch by using the CenterCrop() method. This method accepts images like PIL Image, Tensor Image, and a batch of Tensor images. The tensor image is a PyTorch tensor with [C, H, W] shape, where C represents a number of channels and  H, W represents height and width respectively. 

Syntax:  torchvision.transforms.CenterCrop(size)

Parameters:

• size: Desired crop size of the image.

Return: This method is returns the cropped image of given input size.

Image used for demonstration:

Example 1:

In this example, we are transforming the image at the center. In this, we will get a square image as output.

Python3

# import required libraries
import torch
import torchvision.transforms as transforms
from PIL import Image

# Read image
image = Image.open('a.jpg')

# create an transform for crop the image
transform = transforms.CenterCrop(200)

# use above created transform to crop
# the image
image_crop = transform(image)

# display result
image_crop.show()

Output:

Example 2:

In this example, we are transforming the image with a height of 180 and a width of 300.

Python3

# import required libraries
import torch
import torchvision.transforms as transforms
from PIL import Image

# Read image
image = Image.open('a.jpg')

# define an transform, height=180 width=300
transform = transforms.CenterCrop((180, 300))

# use above created transform to crop
# the image
image_crop = transform(image)

# display result
image_crop.show()

Output: