Record Class MNIST
java.lang.Object
java.lang.Record
smile.datasets.MNIST
- Record Components:
data- data frame.formula- modeling formula.
MNIST dataset. This is a large dataset of handwritten digits normalized to
fit into a 28x28 pixel bounding box and anti-aliased, which introduced
grayscale levels. The MNIST dataset contains 60,000 training images and
10,000 testing images.
-
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptiondata()Returns the value of thedatarecord component.final booleanIndicates whether some other object is "equal to" this one.formula()Returns the value of theformularecord component.final inthashCode()Returns a hash code value for this object.final StringtoString()Returns a string representation of this record class.double[][]x()Returns the sample features.int[]y()Returns the class labels.
-
Constructor Details
-
MNIST
-
MNIST
Constructor.- Parameters:
dataFilePath- the path to data file.labelFilePath- the path to label file.- Throws:
IOException- when fails to read the file.
-
MNIST
-
-
Method Details
-
x
public double[][] x()Returns the sample features.- Returns:
- the sample features.
-
y
public int[] y()Returns the class labels.- Returns:
- the class labels.
-
toString
-
hashCode
-
equals
Indicates whether some other object is "equal to" this one. The objects are equal if the other object is of the same class and if all the record components are equal. All components in this record class are compared withObjects::equals(Object,Object). -
data
-
formula
-