IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

math formula fix (#3512)

Browse Source 
Co-authored-by: Nikolay Tyukaev <ntyukaev_lo@jenkins.inn.intel.com>
This commit is contained in:
Nikolay Tyukaev 2020-12-09 17:03:46 +03:00 committed by GitHub
parent 4a6e153d5a
commit 17df09967d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 15 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
docs/MO_DG/prepare_model/convert_model/Legacy_IR_Layers_Catalog_Spec.md
View File

@ -1582,9 +1582,9 @@ OI, which means that Input changes the fastest, then Output.
**Mathematical Formulation** **Mathematical Formulation**
\f[ \f[
output[:, ... ,:, i, ... , j,:, ... ,:] = input2[:, ... ,:, input1[i, ... ,j],:, ... ,:] output[:, ... ,:, i, ... , j,:, ... ,:] = input2[:, ... ,:, input1[i, ... ,j],:, ... ,:]
\f] \f]
**Inputs** **Inputs**
@ -5086,7 +5086,9 @@ t \in \left ( 0, \quad tiles \right )
Output tensor is populated by values computes in the following way: Output tensor is populated by values computes in the following way:
output[i1, ..., i(axis-1), j, i(axis+1) ..., iN] = top_k(input[i1, ...., i(axis-1), :, i(axis+1), ..., iN]), k, sort, mode) \f[
output[i1, ..., i(axis-1), j, i(axis+1) ..., iN] = top_k(input[i1, ...., i(axis-1), :, i(axis+1), ..., iN]), k, sort, mode)
\f]
So for each slice `input[i1, ...., i(axis-1), :, i(axis+1), ..., iN]` which represents 1D array, top_k value is computed individually. Sorting and minimum/maximum are controlled by `sort` and `mode` attributes. So for each slice `input[i1, ...., i(axis-1), :, i(axis+1), ..., iN]` which represents 1D array, top_k value is computed individually. Sorting and minimum/maximum are controlled by `sort` and `mode` attributes.

6
docs/ops/activation/Mish_4.md
View File

@ -26,9 +26,9 @@
For each element from the input tensor calculates corresponding For each element from the input tensor calculates corresponding
element in the output tensor with the following formula: element in the output tensor with the following formula:
\f[ \f[
Mish(x) = x*tanh(ln(1.0+e^{x})) Mish(x) = x*tanh(ln(1.0+e^{x}))
\f] \f]
**Examples** **Examples**

6
docs/ops/activation/Sigmoid_1.md
View File

@ -14,9 +14,9 @@
For each element from the input tensor calculates corresponding For each element from the input tensor calculates corresponding
element in the output tensor with the following formula: element in the output tensor with the following formula:
\f[ \f[
sigmoid( x ) = \frac{1}{1+e^{-x}} sigmoid( x ) = \frac{1}{1+e^{-x}}
\f] \f]
**Inputs**: **Inputs**:

6
docs/ops/activation/Swish_4.md
View File

@ -9,9 +9,9 @@
**Detailed description**: For each element from the input tensor calculates corresponding **Detailed description**: For each element from the input tensor calculates corresponding
element in the output tensor with the following formula: element in the output tensor with the following formula:
\f[ \f[
Swish(x) = x / (1.0 + e^{-(beta * x)}) Swish(x) = x / (1.0 + e^{-(beta * x)})
\f] \f]
The Swish operation is introduced in the [article](https://arxiv.org/pdf/1710.05941.pdf). The Swish operation is introduced in the [article](https://arxiv.org/pdf/1710.05941.pdf).