com.intel.analytics.bigdl.nn

ClassNLLCriterion

class ClassNLLCriterion[T] extends TensorCriterion[T]

The negative log likelihood criterion. It is useful to train a classification problem with n classes. If provided, the optional argument weights should be a 1D Tensor assigning weight to each of the classes. This is particularly useful when you have an unbalanced training set.

The input given through a forward() is expected to contain log-probabilities/probabilities of each class: input has to be a 1D Tensor of size n. Obtaining log-probabilities/probabilities in a neural network is easily achieved by adding a LogSoftMax/SoftMax layer in the last layer of your neural network. You may use CrossEntropyCriterion instead, if you prefer not to add an extra layer to your network. This criterion expects a class index (1 to the number of class) as target when calling forward(input, target) and backward(input, target).

In the log-probabilities case, The loss can be described as: loss(x, class) = -x[class] or in the case of the weights argument it is specified as follows: loss(x, class) = -weights[class] * x[class]

Due to the behaviour of the backend code, it is necessary to set sizeAverage to false when calculating losses in non-batch mode.

Note that if the target is -1, the training process will skip this sample. In other words, the forward process will return zero output and the backward process will also return zero gradInput.

By default, the losses are averaged over observations for each minibatch. However, if the field sizeAverage is set to false, the losses are instead summed for each minibatch.

In particular, when weights=None, size_average=True and logProbAsInput=False, this is same as sparse_categorical_crossentropy loss in keras.

T

numeric type

Annotations
@SerialVersionUID( 8696382776046599502L )
Linear Supertypes
TensorCriterion[T], AbstractCriterion[Tensor[T], Tensor[T], T], Serializable, Serializable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By inheritance
Inherited
  1. ClassNLLCriterion
  2. TensorCriterion
  3. AbstractCriterion
  4. Serializable
  5. Serializable
  6. AnyRef
  7. Any
  1. Hide All
  2. Show all
Learn more about member selection
Visibility
  1. Public
  2. All

Instance Constructors

  1. new ClassNLLCriterion(weights: Tensor[T] = null, sizeAverage: Boolean = true, logProbAsInput: Boolean = true)(implicit arg0: ClassTag[T], ev: TensorNumeric[T])

    weights

    weights of each element of the input

    sizeAverage

    size average of batch

    logProbAsInput

    indicating whether to accept log-probabilities or probabilities as input. True means accepting log-probabilities as input.

    ev

    numeric operator

Value Members

  1. final def !=(arg0: AnyRef): Boolean

    Definition Classes
    AnyRef
  2. final def !=(arg0: Any): Boolean

    Definition Classes
    Any
  3. final def ##(): Int

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

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

    Definition Classes
    Any
  6. final def asInstanceOf[T0]: T0

    Definition Classes
    Any
  7. def backward(input: Tensor[T], target: Tensor[T]): Tensor[T]

    Performs a back-propagation step through the criterion, with respect to the given input.

    Performs a back-propagation step through the criterion, with respect to the given input.

    input

    input data

    target

    target

    returns

    gradient corresponding to input data

    Definition Classes
    AbstractCriterion
  8. def canEqual(other: Any): Boolean

    Definition Classes
    AbstractCriterion
  9. def clone(): AnyRef

    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  10. def cloneCriterion(): AbstractCriterion[Tensor[T], Tensor[T], T]

    Deep copy this criterion

    Deep copy this criterion

    returns

    a deep copied criterion

    Definition Classes
    AbstractCriterion
  11. final def eq(arg0: AnyRef): Boolean

    Definition Classes
    AnyRef
  12. def equals(other: Any): Boolean

    Definition Classes
    AbstractCriterion → AnyRef → Any
  13. def finalize(): Unit

    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  14. def forward(input: Tensor[T], target: Tensor[T]): T

    Takes an input object, and computes the corresponding loss of the criterion, compared with target.

    Takes an input object, and computes the corresponding loss of the criterion, compared with target.

    input

    input data

    target

    target

    returns

    the loss of criterion

    Definition Classes
    AbstractCriterion
  15. final def getClass(): Class[_]

    Definition Classes
    AnyRef → Any
  16. var gradInput: Tensor[T]

    Definition Classes
    AbstractCriterion
  17. def hashCode(): Int

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

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

    Definition Classes
    AnyRef
  20. final def notify(): Unit

    Definition Classes
    AnyRef
  21. final def notifyAll(): Unit

    Definition Classes
    AnyRef
  22. var output: T

    Definition Classes
    AbstractCriterion
  23. final def synchronized[T0](arg0: ⇒ T0): T0

    Definition Classes
    AnyRef
  24. def toString(): String

    Definition Classes
    AnyRef → Any
  25. def updateGradInput(input: Tensor[T], target: Tensor[T]): Tensor[T]

    Computing the gradient of the criterion with respect to its own input.

    Computing the gradient of the criterion with respect to its own input. This is returned in gradInput. Also, the gradInput state variable is updated accordingly.

    input

    input data

    target

    target data / labels

    returns

    gradient of input

    Definition Classes
    ClassNLLCriterionAbstractCriterion
  26. def updateOutput(input: Tensor[T], target: Tensor[T]): T

    Computes the loss using input and objective function.

    Computes the loss using input and objective function. This function returns the result which is stored in the output field.

    input

    input of the criterion

    target

    target or labels

    returns

    the loss of the criterion

    Definition Classes
    ClassNLLCriterionAbstractCriterion
  27. final def wait(): Unit

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

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

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

Inherited from TensorCriterion[T]

Inherited from AbstractCriterion[Tensor[T], Tensor[T], T]

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped