How to Apply FiveCrop Transformation on an Image in PyTorch?

In PyTorch, the “torchvision.transforms” module has a set of classes and functions to perform different transformations on desired images, such as cropping, resizing, rotating, and many more. It also provides a “FiveCrop()” method that is used to crop five regions from a specific image i.e., the four corners and the center. Users can pass either a single integer or two integers for height and width. This method returns five cropped images.

This article will demonstrate the method to apply FiveCrop transformation in PyTorch.

How to Apply FiveCrop Transformation on an Image in PyTorch?

To apply FiveCrop transformation on a specific image in PyTorch, look at the below-provided steps:

Step 1: Upload an Image to Google Colab

First, open Google Colab and click on the below-highlighted icons. Then, choose the specific image from the computer and upload it:

Subsequently, the image will be uploaded to Google Colab:

Here, we have uploaded the following image and we will apply FiveCrop transformation to it:

Step 2: Import Required Library

Next, import the required libraries. For instance, we have imported the following libraries:

import torch
import torchvision.transforms as transforms
from PIL import Image
import matplotlib.pyplot as plt


  • import torch” imports the PyTorch library.
  • import torchvision.transforms as transforms” imports the transforms module from torchvision that is used to preprocess image data before feeding it into a neural network.
  • from PIL import Image” opens and saves different image file formats.
  • import matplotlib.pyplot as plt” imports the “pyplot” module that is used to create visualizations and plots:

Step 3: Read the Input Image

After that, read the input image from the computer. Here, we are reading the “room.jpg” and storing it in the “input_img” variable:

input_img ='room.jpg')

Step 4: Create a Transform

Next, define a transform using the “FiveCrop()” method to crop the input image into a central crop and four corners:

transform = transforms.FiveCrop(250)

Step 5: Apply the Transform on the Image

Now, apply the above transform on the desired input image:

trans_imgs = transform(input_img )

Step 6: Display Cropped Images

Lastly, define a figure of size, row, and cols in the figure and view all the cropped images by displaying it:

fig=plt.figure(figsize=(8, 8))

row, col = 1, 5

for j in range(0, col*row):
   fig.add_subplot(row, col, j+1)


The comparison between the original image and the cropped images can be seen below:

Note: You can access our Google Colab Notebook at this link.

We have efficiently explained the method of applying FiveCrop transformation on an image in PyTorch.


To apply FiveCrop transformation on an image in PyTorch, first, upload the desired image to Google Colab. Then, import the necessary libraries and read the input image. Next, use the “FiveCrop()” method to define and apply the transform on the desired input image to crop it. Finally, display the new cropped images. This article demonstrates the method to apply FiveCrop transformation in PyTorch.

About the author

Laiba Younas

I have done bachelors in Computer Science. Being passionate about learning new technologies, I am interested in exploring different programming languages and sharing my experience with the world.