How to adjust the contrast of an image in PyTorch

In this article, we are going to see how to adjust the contrast of an image in PyTorch using Python. We can adjust the contrast of an image by using the adjust_contrast() method.

adjust_contrast() method

adjust_contrast() method accepts the PIL and tensor images as input. tensor image is a tensor with [C, H, W] shape, where C is the number of channels, and H W is the image height and width respectively. This method also accepts a batch of tensors as input with shape [B, C, H, W] where B is the number of images in the batch. and C, H, and W are the number of channels image height and width respectively. This method returns a Contrast adjusted image.  before moving further let’s see the syntax of the adjust_contrast() method.

Syntax: adjust_contrast(img, contrast_factor)

Parameters:

• img: This is our PIL or tensor image of which the contrast is to be adjusted.
• contrast_factor: This is a  non-negative float number. 0 and 1 gives solid gray original image respectively.

Returns: This method returns a Contrast adjusted image:

The below image is used for demonstration:

image is used for demonstration

Example 1:

In this example, we are adjusting the contrast of an image in PyTorch when the contrast_factor is 0.5.  

Python3

# Import the required libraries
import torch
from PIL import Image
import torchvision.transforms.functional as con

# read the input image from computer
input_img = Image.open('image.png')

# adjust the contrast of the image
input_img = con.adjust_contrast(input_img, 0.5)

# display result
input_img.show()

Output:

image is used for demonstration

Example 2:

In this example, we are adjusting the contrast of an image in PyTorch when the contrast_factor is 0.  

Python3

# Import the required libraries
import torch
from PIL import Image
import torchvision.transforms.functional as con

# read the input image from computer
input_img = Image.open('a.png')

# adjust the contrast of the image
input_img = con.adjust_contrast(input_img, 0)

# display result
input_img.show()

Output

image is used for demonstration

Example 3:

In this example, we are adjusting the contrast of an image in PyTorch when the contrast_factor is 1.

Python3

# Import the required libraries
import torch
from PIL import Image
import torchvision.transforms.functional as con

# read the input image from computer
input_img = Image.open('a.png')

# adjust the contrast of the image
input_img = con.adjust_contrast(input_img, 1)

# display result
input_img.show()

Output

image is used for demonstration