The values of the pixels in RGB images range from 0 to 255.
So, we need to apply Scaling to these features values for our ML algorithms to work fine on them.
After scaling, all the values will be spread in the range of 0 to 1.
Note:
min() returns the minimum value of the NumPy array upon which it is called.
max() returns the maximum value of the NumPy array upon which it is called.
Print the minimum and maximum values of the pixels in train data.
print("Original Min value: ",train_set_x_flatten.reshape(1,-1).min())
print("Original Max value: ",train_set_x_flatten.reshape(1,-1).max())
Scale the dataset values by dividing them with 255.
train_set_x = train_set_x_flatten / 255.
validation_set_x = << your code comes here >> / 255.
test_set_x = << your code comes here >> / 255.
Now, print the minimum and maximum values of the pixels in standardized train data.
print("Standardized Min value: ",train_set_x.reshape(1,-1).min())
print("Standardized Max value: ",train_set_x.reshape(1,-1).max())
Note - Having trouble with the assessment engine? Follow the steps listed here
Loading comments...