Skip to content

Latest commit

 

History

History
104 lines (84 loc) · 3.67 KB

ns-directml-dml_activation_softmax_operator_desc.md

File metadata and controls

104 lines (84 loc) · 3.67 KB
Raw
UID title description helpviewer_keywords old-location tech.root ms.assetid ms.date ms.keywords req.header req.include-header req.target-type req.target-min-winverclnt req.target-min-winversvr req.kmdf-ver req.umdf-ver req.ddi-compliance req.unicode-ansi req.idl req.max-support req.namespace req.assembly req.type-library req.lib req.dll req.irql targetos req.typenames req.redist ms.custom f1_keywords dev_langs topic_type api_type api_location api_name
NS:directml.DML_ACTIVATION_SOFTMAX_OPERATOR_DESC
DML_ACTIVATION_SOFTMAX_OPERATOR_DESC
Performs a softmax activation function on *InputTensor*, placing the result into the corresponding element of *OutputTensor*.
DML_ACTIVATION_SOFTMAX_OPERATOR_DESC
DML_ACTIVATION_SOFTMAX_OPERATOR_DESC structure
direct3d12.dml_activation_softmax_operator_desc
directml/DML_ACTIVATION_SOFTMAX_OPERATOR_DESC
direct3d12\dml_activation_softmax_operator_desc.htm
directml
93B799D1-E98B-42A1-87E5-F2B84721D98C
07/20/2022
DML_ACTIVATION_SOFTMAX_OPERATOR_DESC, DML_ACTIVATION_SOFTMAX_OPERATOR_DESC structure, direct3d12.dml_activation_softmax_operator_desc, directml/DML_ACTIVATION_SOFTMAX_OPERATOR_DESC
directml.h
Windows
Windows
19H1
DML_ACTIVATION_SOFTMAX_OPERATOR_DESC
directml/DML_ACTIVATION_SOFTMAX_OPERATOR_DESC
c++
APIRef
kbSyntax
HeaderDef
DirectML.h
DML_ACTIVATION_SOFTMAX_OPERATOR_DESC

-description

Performs a softmax activation function on InputTensor, placing the result into the corresponding element of OutputTensor.

For 1-D InputTensor:
// Let x[i] be the current element in the InputTensor, and j be the total number of elements in the InputTensor
f(x[i]) = exp(x[i]) / sum(exp(x[0]), ..., exp(x[j-1]))

Where exp(x) is the natural exponentiation function.

-struct-fields

-field InputTensor

Type: const DML_TENSOR_DESC*

The input tensor to read from. This tensor must have an effective rank no greater than 2. The effective rank of a tensor is the DimensionCount of the tensor, excluding leftmost dimensions of size 1. For example a tensor size of { 1, 1, BatchCount, Width } is valid, and is equivalent to a tensor of sizes { BatchCount, Width }.

-field OutputTensor

Type: const DML_TENSOR_DESC*

The output tensor to write the results to.

Availability

This operator was introduced in DML_FEATURE_LEVEL_1_0.

Tensor constraints

InputTensor and OutputTensor must have the same DataType, DimensionCount, and Sizes.

Tensor support

DML_FEATURE_LEVEL_3_0 and above

Tensor Kind Supported dimension counts Supported data types
InputTensor Input 1 to 8 FLOAT32, FLOAT16
OutputTensor Output 1 to 8 FLOAT32, FLOAT16

DML_FEATURE_LEVEL_2_0 and above

Tensor Kind Supported dimension counts Supported data types
InputTensor Input 4 to 5 FLOAT32, FLOAT16
OutputTensor Output 4 to 5 FLOAT32, FLOAT16

DML_FEATURE_LEVEL_1_0 and above

Tensor Kind Supported dimension counts Supported data types
InputTensor Input 4 FLOAT32, FLOAT16
OutputTensor Output 4 FLOAT32, FLOAT16

-see-also

DML_ACTIVATION_LOG_SOFTMAX_OPERATOR_DESC structure

DML_ARGMAX_OPERATOR_DESC structure