Specify LogSoftmax-5 operation (#2382)

* Specify LogSoftmax operation

* Fix feedback
This commit is contained in:
Maxim Vafin 2020-10-08 20:04:38 +03:00 committed by GitHub
parent 3cbf92e778
commit 694d1dcd25
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 64 additions and 0 deletions

View File

@ -174,6 +174,7 @@
<tab type="user" title="LogicalNot-1" url="@ref openvino_docs_ops_logical_LogicalNot_1"/>
<tab type="user" title="LogicalOr-1" url="@ref openvino_docs_ops_logical_LogicalOr_1"/>
<tab type="user" title="LogicalXor-1" url="@ref openvino_docs_ops_logical_LogicalXor_1"/>
<tab type="user" title="LogSoftmax-5" url="@ref openvino_docs_ops_activation_LogSoftmax_5"/>
<tab type="user" title="MVN-1" url="@ref openvino_docs_ops_normalization_MVN_1"/>
<tab type="user" title="MatMul-1" url="@ref openvino_docs_ops_matrix_MatMul_1"/>
<tab type="user" title="MaxPool-1" url="@ref openvino_docs_ops_pooling_MaxPool_1"/>

View File

@ -0,0 +1,62 @@
## LogSoftMax <a name="LogSoftmax"></a> {#openvino_docs_ops_activation_LogSoftmax_5}
**Versioned name**: *LogSoftmax-5*
**Category**: *Activation*
**Short description**: LogSoftmax computes the natural logarithm of softmax values for the given input.
**Note**: This is recommended to not compute LogSoftmax directly as Log(Softmax(x, axis)), more numeric stable is to compute LogSoftmax as:
\f[
t = (x - ReduceMax(x, axis)) \\
LogSoftmax(x, axis) = t - Log(ReduceSum(Exp(t), axis))
\f]
**Attributes**
* *axis*
* **Description**: *axis* represents the axis of which the *LogSoftmax* is calculated. Negative value means counting dimensions from the back.
* **Range of values**: any integer value
* **Type**: int
* **Default value**: 1
* **Required**: *no*
**Inputs**:
* **1**: Input tensor *x* of type T with enough number of dimension to be compatible with *axis* attribute. Required.
**Outputs**:
* **1**: The resulting tensor of the same shape and of type T.
**Types**
* *T*: any floating point type.
**Mathematical Formulation**
\f[
y_{c} = ln\left(\frac{e^{Z_{c}}}{\sum_{d=1}^{C}e^{Z_{d}}}\right)
\f]
where \f$C\f$ is a size of tensor along *axis* dimension.
**Example**
```xml
<layer ... type="LogSoftmax" ... >
<data axis="1" />
<input>
<port id="0">
<dim>256</dim>
<dim>56</dim>
</port>
</input>
<output>
<port id="3">
<dim>256</dim>
<dim>56</dim>
</port>
</output>
</layer>
```

View File

@ -75,6 +75,7 @@ declared in `namespace opset5`.
* [LogicalNot](logical/LogicalNot_1.md)
* [LogicalOr](logical/LogicalOr_1.md)
* [LogicalXor](logical/LogicalXor_1.md)
* [LogSoftmax](activation/LogSoftmax_5.md)
* [LRN](normalization/LRN_1.md)
* [LSTMCell](sequence/LSTMCell_1.md)
* [LSTMSequence](sequence/LSTMSequence_1.md)