The first parameter is the folder that the training data is contained in

The target$\_$size variable contains the dimensions that each image in the data set will be resized to

The batch$\_$size variable represents the size of batches of data that the method will be applied to

The class$\_$mode specifies which time of classifier you're building. The two main options are binary $($for two classes$)$ or categorical $($for two or more classes$).$ There are other options which you can read about in the keras documentation if desired.

Once you run this command, you should see the following output:

Found $8000$ images belonging to $2$ classes.

Now that this is done, we can move on to preprocessing our test data.

Please print the output of training$\_$generator.flow$\_$from$\_$directory as an image here $[1$ Mark$]$

Preprocessing the Test Data

As mentioned, we will not be applying image augmentation techniques to our test data. We want the test data to remain unchanged $($which would be the case if our machine learning model was deployed in production$).$

Preprocessing our test data is comprised of two steps:

Creating a new ImageDataGenerator class that excludes the image augmentation arguments that we used on our training data

Applying the same flow$\_$from$\_$directory method to the ImageDataGenerator class that was just created

Here is the code to do this:

test$\_$generator $=$ ImageDataGenerator$($rescale $=1./255)$

test$\_$set $=$ test$\_$generator.flow$\_$from$\_$directory$(\text{'}$test$\_$data',

target$\_$size $=(64,64),$

batch$\_$size $=32,$

class$\_$mode $=$ 'binary'$)$

Once you run this command, the following output will be printed:

Found $2000$ images belonging to $2$ classes.

Please print the output of test$\_$generator.flow$\_$from$\_$directory as an image here $[1$ Mark$]$