In this step we will load the dataset, and then store it into train and test sets. The dataset consists of 4 files:
train-images-idx3-ubyte.gz
train-labels-idx1-ubyte.gz
t10k-images-idx3-ubyte.gz
t10k-labels-idx1-ubyte.gz
These files are located at the following path:
/cxldata/datasets/project/mnist/
Finally, we will store them in 4 variables:
X_train, y_train, X_test, y_test
Provide the path to the files:
filePath_train_set = '/cxldata/datasets/project/mnist/train-images-idx3-ubyte.gz'
filePath_train_label = '<< your code goes here >>/train-labels-idx1-ubyte.gz'
filePath_test_set = '<< your code goes here >>/t10k-images-idx3-ubyte.gz'
filePath_test_label = '/cxldata/datasets/project/mnist/t10k-labels-idx1-ubyte.gz'
Open the Gzip files:
with gzip.open(filePath_train_label, 'rb') as trainLbpath:
trainLabel = np.frombuffer(trainLbpath.read(), dtype=np.uint8,
offset=8)
with gzip.open(filePath_train_set, 'rb') as trainSetpath:
trainSet = np.frombuffer(trainSetpath.read(), dtype=np.uint8,
offset=16).reshape(len(trainLabel), 784)
with gzip.open(filePath_test_label, 'rb') as testLbpath:
testLabel = np.frombuffer(testLbpath.read(), dtype=np.uint8,
offset=8)
with gzip.open(filePath_test_set, 'rb') as testSetpath:
testSet = np.frombuffer(testSetpath.read(), dtype=np.uint8,
offset=16).reshape(len(testLabel), 784)
Store the data into the 4 variables:
X_train, << your code goes here >>, y_train, y_test = trainSet, testSet, trainLabel, << your code goes here >>
Note - Having trouble with the assessment engine? Follow the steps listed here
Loading comments...