Public Constructors
Public Methods
static <T extends TNumber, U extends TNumber> Operand |
sparseSoftmaxCrossEntropyWithLogits(Scope scope, Operand<T> labels, Operand<U> logits)
Computes sparse softmax cross entropy between
logits and labels . |
Inherited Methods
Public Constructors
public SparseSoftmaxCrossEntropyWithLogits ()
Public Methods
public static Operand sparseSoftmaxCrossEntropyWithLogits (Scope scope, Operand<T> labels, Operand<U> logits)
Computes sparse softmax cross entropy between logits
and labels
.
Measures the probability error in discrete classification tasks in which the classes are mutually exclusive (each entry is in exactly one class). For example, each CIFAR-10 image is labeled with one and only one label: an image can be a dog or a truck, but not both.
NOTE:
For this operation, the probability of a given label is considered exclusive. That is, soft
classes are not allowed, and the labels
vector must provide a single specific
index for the true class for each row of logits
(each minibatch entry). For soft
softmax classification with a probability distribution for each entry, ERROR(/org.tensorflow.op.NnOps#softmaxCrossEntropyWithLogits)
.
WARNING:
This op expects unscaled logits, since it performs a softmax
on logits
internally for efficiency. Do not call this op with the output of softmax
,
as it will produce incorrect results.
A common use case is to have logits of shape [batchSize, numClasses]
and have
labels of shape [batchSize]
, but higher dimensions are supported, in which case
the dim
-th dimension is assumed to be of size numClasses
.
logits
must have the TFloat16
, TFloat32
, or TFloat64
, and labels
must have the dtype of TInt32
or TInt64
.
Parameters
scope | current scope |
---|---|
labels | Tensor of shape [d_0, d_1, ..., d_{r-1}] (where r
is rank of labels and result) and the dataType is TInt32
or TInt64 . Each entry in labels must be an index in [0,
numClasses) . Other values will raise an exception when this op is run on CPU, and
return NaN for corresponding loss and gradient rows on GPU. |
logits | Per-label activations (typically a linear output) of shape [d_0, d_1, ...,
d_{r-1}, numClasses] and dataType of TFloat16 , TFloat32 ,
or TFloat64 . These activation energies are interpreted as unnormalized log
probabilities. |
Returns
- A
Tensor
of the same shape aslabels
and of the same type aslogits
with the softmax cross entropy loss.
Throws
IllegalArgumentException | If logits are scalars (need to have rank >= 1) or if the rank of the labels is not equal to the rank of the logits minus one. |
---|