Computes the mean of squares of errors between labels and predictions.
loss = loss = square(labels - predictions)
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} }); MeanSquaredError mse = new MeanSquaredError(tf); Operand<TFloat32> result = mse.call(labels, predictions); // produces 0.5f
Calling with sample weight:
Operand<TFloat32> sampleWeight = tf.constant(new float[] {0.7f, 0.3f}); Operand<TFloat32> result = mse.call(labels, predictions, sampleWeight); // produces 0.25f
Using SUM
reduction type:
MeanSquaredError mse = new MeanSquaredError(tf, Reduction.SUM); Operand<TFloat32> result = mse.call(labels, predictions); // produces 1.0f
Using NONE
reduction type:
MeanSquaredError mse = new MeanSquaredError(tf, Reduction.NONE); Operand<TFloat32> result = mse.call(labels, predictions); // produces [0.5f, 0.5f]
Inherited Fields
public static final Reduction | REDUCTION_DEFAULT |
Public Constructors
MeanSquaredError(Ops tf)
Creates a MeanSquaredError Loss using
getSimpleName() as the loss name and a Loss
Reduction of REDUCTION_DEFAULT |
|
MeanSquaredError(Ops tf, Reduction reduction)
Creates a MeanSquaredError Loss using
getSimpleName() as the loss name |
|
Public Methods
Inherited Methods
boolean |
equals(Object arg0)
|
final Class<?> |
getClass()
|
int |
hashCode()
|
final void |
notify()
|
final void |
notifyAll()
|
String |
toString()
|
final void |
wait(long arg0, int arg1)
|
final void |
wait(long arg0)
|
final void |
wait()
|
Public Constructors
public MeanSquaredError (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 MeanSquaredError (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 MeanSquaredError (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