LogSoftmax¶
General¶
LogSoftmax operation applies the \(\log(softmax(src))\) function to an n-dimensional input Tensor. The formulation can be simplified as:
\[dst_i = \log\Big( \frac{exp(src_i)}{\sum_{j}^{ } exp(src_j)} \Big)\]
Operation attributes¶
Attribute Name |
Descr |
|||
|---|---|---|---|---|
Represents the axis of which the LogSoftmax is calculated. Negative value means counting dimensions from the back. |
s64 |
Arbitrary s64 value ( |
Optional |
Execution arguments¶
The inputs and outputs must be provided according to below index order when constructing an operation.
Inputs¶
Index |
Argu |
|
|---|---|---|
0 |
|
Required |
Outputs¶
Index |
Argu |
|
|---|---|---|
0 |
|
Required |
Supported data types¶
LogSoftmax operation supports the following data type combinations.
Src |
D |
|---|---|
f32 |
f32 |
bf16 |
bf16 |
f16 |
f16 |