Computes the mean squared logarithmic errors between labels and predictions.
loss = square(log(labels + 1.) - log(predictions + 1.))
Standalone usage:
Operand<TFloat32> labels = tf.constant(new float[][] { {0.f, 1.f}, {0.f, 0.f} }); Operand<TFloat32> predictions = tf.constant(new float[][] { {1.f, 1.f}, {1.f, 0.f} }); MeanSquaredLogarithmicError msle = new MeanSquaredLogarithmicError(tf); Operand<TFloat32> result = msle.call(labels, predictions); // produces 0.240f
Calling with sample weight:
Operand<TFloat32> sampleWeight = tf.constant(new float[] {0.7f, 0.3f}); Operand<TFloat32> result = msle.call(labels, predictions, sampleWeight); // produces 0.120f
Using SUM
reduction type:
MeanSquaredLogarithmicError msle = new MeanSquaredLogarithmicError(tf, Reduction.SUM); Operand<TFloat32> result = msle.call(labels, predictions); // produces 0.480f
Using NONE
reduction type:
MeanSquaredLogarithmicError msle = new MeanSquaredLogarithmicError(tf, Reduction.NONE); Operand<TFloat32> result = msle.call(labels, predictions); // produces [0.240f, 0.240f]
Inherited Fields
Public Constructors
MeanSquaredLogarithmicError(Ops tf)
Creates a MeanSquaredError Loss using
getSimpleName() as the loss name and a Loss
Reduction of REDUCTION_DEFAULT |
|
MeanSquaredLogarithmicError(Ops tf, Reduction reduction)
Creates a MeanSquaredError Loss using
getSimpleName() as the loss name |
|
Public Methods
<T extends TNumber> Operand<T> |
Inherited Methods
Public Constructors
public MeanSquaredLogarithmicError (Ops tf)
Creates a MeanSquaredError Loss using getSimpleName()
as the loss name and a Loss
Reduction of REDUCTION_DEFAULT
Parameters
tf | the TensorFlow Ops |
---|
public MeanSquaredLogarithmicError (Ops tf, Reduction reduction)
Creates a MeanSquaredError Loss using getSimpleName()
as the loss name
Parameters
tf | the TensorFlow Ops |
---|---|
reduction | Type of Reduction to apply to the loss. |
public MeanSquaredLogarithmicError (Ops tf, String name, Reduction reduction)
Creates a MeanSquaredError
Parameters
tf | the TensorFlow Ops |
---|---|
name | the name of the loss |
reduction | Type of Reduction to apply to the loss. |
Public Methods
public Operand<T> call (Operand<? extends TNumber> labels, Operand<T> predictions, Operand<T> sampleWeights)
Generates an Operand that calculates the loss.
Parameters
labels | the truth values or labels |
---|---|
predictions | the predictions |
sampleWeights | Optional sampleWeights acts as a coefficient for the loss. If a scalar is provided, then the loss is simply scaled by the given value. If SampleWeights is a tensor of size [batch_size], then the total loss for each sample of the batch is rescaled by the corresponding element in the SampleWeights vector. If the shape of SampleWeights is [batch_size, d0, .. dN-1] (or can be broadcast to this shape), then each loss element of predictions is scaled by the corresponding value of SampleWeights. (Note on dN-1: all loss functions reduce by 1 dimension, usually axis=-1.) |
Returns
- the loss