EmnistIterator

EmnistIterator

EMNIST: an extension of MNIST to handwritten letters
The EMNIST Dataset

STRUCTURE AND ORGANIZATION OF THE EMNIST DATASETS.
Name	Classes	No. Training	No. Testing	Validation	Total
By_Class	62	697,932	116,323	No	814,255
By_Merge	47	697,932	116,323	No	814,255
Balanced	47	112,800	18,800	Yes	131,600
Digits	10	240,000	40,000	Yes	280,000
Letters	37	88,800	14,800	Yes	103,600
MNIST	10	60,000	10,000	Yes	70,000

Linear Supertypes

AnyRef, Any

Value Members

final def !=(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def ##(): Int

Definition Classes
AnyRef → Any
final def ==(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def asInstanceOf[T0]: T0

Definition Classes
Any
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
def hashCode(): Int

Definition Classes
AnyRef → Any
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef

def run(dataset: Set, batchSize: Int, binarize: Boolean = false, train: Boolean = true, shuffle: Boolean = true, seed: Long = 2018L): EmnistDataSetIterator

dataset

dataset type Options: EmnistDataSet.X:

COMPLETE: 62 unbalanced classes, 814,255 examples total (train + test).
MERGE:    47 unbalanced classes, 814,255 examples total. Combines lower and upper case characters (that are difficult to distinguish) into one class for each letter (instead of 2), for letters C, I, J, K, L, M, O, P, S, U, V, W, X, Y and Z
BALANCED: 47 balanced classes,   131,600 examples total.
LETTERS:  26 balanced classes,   145,600 examples total.
DIGITS:   10 balanced classes,   280,000 examples total.
MNIST:    10 balanced classes.,   70,000 examples total. Equivalent to the original MNIST dataset in MnistDataSetIterator

batchSize

batch size

binarize

whether to binarize features

train

whether to get the train (train=true) or the test (train=false) split

shuffle

whether to shuffle the dataset

seed

seed for the random generator

returns

dataset iterator

final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def toString(): String

Definition Classes
AnyRef → Any
final def wait(): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long, arg1: Int): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )

Related Doc: package vectorization

object EmnistIterator

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

final def asInstanceOf[T0]: T0

def clone(): AnyRef

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def finalize(): Unit

final def getClass(): Class[_]

def hashCode(): Int

final def isInstanceOf[T0]: Boolean

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

def run(dataset: Set, batchSize: Int, binarize: Boolean = false, train: Boolean = true, shuffle: Boolean = true, seed: Long = 2018L): EmnistDataSetIterator

final def synchronized[T0](arg0: ⇒ T0): T0

def toString(): String

final def wait(): Unit

final def wait(arg0: Long, arg1: Int): Unit

final def wait(arg0: Long): Unit

Inherited from AnyRef

Inherited from Any

Ungrouped