Batch Processing

Layer Input

The forward loss softmax cross-entropy layer accepts the input described below. Pass the Input ID as a parameter to the methods that provide input for your algorithm. For more details, see Algorithms.

Input ID

Input

data

Pointer to the tensor X of size n1 x n2 x ... x nk x ... x np that stores the input data for the forward loss softmax cross-entropy layer. This input can be an object of any class derived from Tensor.

groundTruth

Pointer to the tensor of size n1 x n2 x ... x 1 x ... x np that stores the ground truth data for the forward loss softmax cross-entropy layer. This input can be an object of any class derived from Tensor.

Layer Parameters

For common parameters of neural network layers, see Common Parameters.

In addition to the common parameters, the forward loss softmax cross-entropy layer has the following parameters:

Parameter

Default Value

Description

algorithmFPType

float

The floating-point type that the algorithm uses for intermediate computations. Can be float or double.

method

defaultDense

Performance-oriented computation method, the only method supported by the layer.

accuracyThresold

0.0001

The value needed to avoid degenerate cases in computing the logarithm.

dimension

1

The dimension index to calculate softmax cross-entropy.

Layer Output

The forward loss softmax cross-entropy layer calculates the result described below. Pass the Result ID as a parameter to the methods that access the results of your algorithm. For more details, see Algorithms.

Result ID

Result

value

Pointer to tensor Y of size 1 that stores the result of the forward loss softmax cross-entropy layer. This input can be an object of any class derived from Tensor.

resultForBackward

Collection of data needed for the backward loss softmax cross-entropy layer. The collection may contain objects of any class derived from Tensor.

Element ID

Element

auxProbabilities

Pointer to tensor S of size n1 x n2 x ... x nk x ... x np that stores probabilities for the forward loss softmax cross-entropy layer. This input can be an object of any class derived from Tensor.

auxGroundTruth

Pointer to tensor T of size n1 x n2 x ... x 1 x ... x np that stores the ground truth data for the forward loss softmax cross-entropy layer. This input can be an object of any class derived from Tensor.

For more complete information about compiler optimizations, see our Optimization Notice.
Select sticky button color: 
Orange (only for download buttons)