Impact of Image Flattening

Flattening is a technique that is used to convert multi-dimensional arrays into a 1-D array, it is generally used in Deep Learning while feeding the 1-D array information to the classification model.

What is the need for Flattening of an Image?

Multi-Dimensional arrays take more amount of memory while 1-D arrays take less memory, which is the most important reason why we flatten the Image Array before processing/feeding the information to our model. In most cases, we will be dealing with a dataset which contains a large amount of images thus flattening helps in decreasing the memory as well as reducing the time to train the model.

Step 1: Importing the necessary libraries

Python3

import numpy as np
import pandas as pd
import cv2 as cv
from google.colab.patches import cv2_imshow
from skimage import io
from PIL import Image
import matplotlib.pylab as plt
from numpy import array
from sys import getsizeof

Step 2: Fetching a random image through web

Python3

#Fetching the url and showing the image using cv2_imshow
urls=["https://iiif.lib.ncsu.edu/iiif/0052574/full/800,/0/default.jpg"]
for url in urls:
  image = io.imread(url)
  cv2_imshow(image)
  print('\n')

Step 3: Transforming the image into a multi-dimensional array

Python3

#Getting the multi-dimensional array from the image
array1 = array(image)
#Memory occupied by the multi-dimensional array
size1 = getsizeof(array1)
print(array1)

Step 4: Now Flattening the multi-dimensional array using flatten() function

Python3

#Using Flatten function on array 1 to convert the multi-dimensional
# array to 1-D array
array2 = array1.flatten()
#Memory occupied by array 2
size2 = getsizeof(array2)
#displaying the 1-D array
print(array2)

Step5: Results of Flattening

Python3

#Print's the two different size's of the array
print(f"Size of Multidimensional Image : {size1}")
print(f"Size of Flattened Image : {size2}")
difference = size1 - size2
#Print's the difference of memory between the size of Multidimensional & 1-D array
print("Size difference in the images: ", difference)

Size of Multidimensional Image : 1324928 
Size of Flattened Image : 1324896
Size difference in the images: 32

Step 6: Full Code

Python3

#importing libraries
import numpy as np
import pandas as pd
import cv2 as cv
from google.colab.patches import cv2_imshow
from skimage import io
from PIL import Image
import matplotlib.pylab as plt
from numpy import array
from sys import getsizeof

#Fetching the url and showing the image using cv2_imshow
urls=["https://iiif.lib.ncsu.edu/iiif/0052574/full/800,/0/default.jpg"]
for url in urls:
  image = io.imread(url)
  cv2_imshow(image)
  print('\n')

#Getting the multi-dimensional array from the image
array1 = array(image)
#Memory occupied by the multi-dimensional array
size1 = getsizeof(array1)
print(array1)

#Using Flatten function on array 1 to convert the multi-dimensional
# array to 1-D array
array2 = array1.flatten()
#Memory occupied by array 2
size2 = getsizeof(array2)
#displaying the 1-D array
print(array2)

#Print's the two different size's of the array
print(f"Size of Multidimensional Image : {size1}")
print(f"Size of Flattened Image : {size2}")
difference = size1 - size2
#Print's the difference of memory between the size of Multidimensional & 1-D array
print(difference)

Conclusion:

After running the whole code we see that there is not a major difference in memory used in the multi-dimensional image array and the flattened array. Then people may ask why we are doing the flattening when the effect is negligible. In a large datasets when we are dealing with thousands of images the net amount of the memory saved due to all the images accumulates to be pretty big.