Though the dataset is already split for you between a training set and a test set, it can be useful to split the training set further to have a validation set. We shall do that here.
Let's split the full training set into a validation set and a (smaller) training set. We will also scale the pixel intensities down to the 0-1 range and convert them to floats, by dividing by 255.
Slice the first 5000 samples from the X_train_full and divide the values by 255. to scale the image pixel values to be in the range 0-1. Store these first 5000 scaled samples in X_valid.
X_valid = << your code comes here >>[:5000] / 255.
Store the first 5000 values from y_train_full to form the y_valid.
y_valid = << your code comes here >>[:5000]
Similarly, slice the remaining samples from 5000 of the X_train_full and divide the values by 255. to scale the image pixel values to be in the range 0-1. Store these scaled samples in X_train.
X_train = << your code comes here >>[5000:] / 255.
Store the remaining samples from 5000 of the y_train_full to form the y_train.
y_train = << your code comes here >>[5000:]
Let us print the shapes of the train data, validation data and test data.
print("Train data shape:",X_train.shape)
print("Validation data shape:",<< your code comes here >>)
print("Test data shape:",<< your code comes here >>)
Thus, the train set contains 55000 images, the validation set contains 5,000 images, and the test set contains 10,000 images.
Scale the values of the X_test.
X_test = X_test / 255.
Note - Having trouble with the assessment engine? Follow the steps listed here
Loading comments...