From dd0db2def075557e52b55b64c523366ad9ec2bae Mon Sep 17 00:00:00 2001 From: Nikolay Tyukaev Date: Tue, 8 Dec 2020 15:17:17 +0300 Subject: [PATCH] math formula fix --- .../convert_model/Legacy_IR_Layers_Catalog_Spec.md | 10 ++++++---- docs/ops/activation/Mish_4.md | 6 +++--- docs/ops/activation/Sigmoid_1.md | 7 ++++--- docs/ops/activation/Swish_4.md | 6 +++--- 4 files changed, 16 insertions(+), 13 deletions(-) diff --git a/docs/MO_DG/prepare_model/convert_model/Legacy_IR_Layers_Catalog_Spec.md b/docs/MO_DG/prepare_model/convert_model/Legacy_IR_Layers_Catalog_Spec.md index 569e52381501bc..dd06a2bbd6c4f9 100644 --- a/docs/MO_DG/prepare_model/convert_model/Legacy_IR_Layers_Catalog_Spec.md +++ b/docs/MO_DG/prepare_model/convert_model/Legacy_IR_Layers_Catalog_Spec.md @@ -1582,9 +1582,9 @@ OI, which means that Input changes the fastest, then Output. **Mathematical Formulation** - \f[ - output[:, ... ,:, i, ... , j,:, ... ,:] = input2[:, ... ,:, input1[i, ... ,j],:, ... ,:] - \f] +\f[ + output[:, ... ,:, i, ... , j,:, ... ,:] = input2[:, ... ,:, input1[i, ... ,j],:, ... ,:] +\f] **Inputs** @@ -5086,7 +5086,9 @@ t \in \left ( 0, \quad tiles \right ) 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. diff --git a/docs/ops/activation/Mish_4.md b/docs/ops/activation/Mish_4.md index de8397c188825a..aefc3d2f2f05d5 100644 --- a/docs/ops/activation/Mish_4.md +++ b/docs/ops/activation/Mish_4.md @@ -26,9 +26,9 @@ For each element from the input tensor calculates corresponding element in the output tensor with the following formula: - \f[ - Mish(x) = x*tanh(ln(1.0+e^{x})) - \f] +\f[ +Mish(x) = x*tanh(ln(1.0+e^{x})) +\f] **Examples** diff --git a/docs/ops/activation/Sigmoid_1.md b/docs/ops/activation/Sigmoid_1.md index f4a70faaff0705..828a56f5313c49 100644 --- a/docs/ops/activation/Sigmoid_1.md +++ b/docs/ops/activation/Sigmoid_1.md @@ -20,6 +20,7 @@ For each element from the input tensor calculates corresponding element in the output tensor with the following formula: - \f[ - sigmoid( x ) = \frac{1}{1+e^{-x}} - \f] \ No newline at end of file + +\f[ +sigmoid( x ) = \frac{1}{1+e^{-x}} +\f] \ No newline at end of file diff --git a/docs/ops/activation/Swish_4.md b/docs/ops/activation/Swish_4.md index e8a51c9dc048db..78bcb3866e7b91 100644 --- a/docs/ops/activation/Swish_4.md +++ b/docs/ops/activation/Swish_4.md @@ -9,9 +9,9 @@ **Detailed description**: For each element from the input tensor calculates corresponding element in the output tensor with the following formula: - \f[ - Swish(x) = x / (1.0 + e^{-(beta * x)}) - \f] +\f[ +Swish(x) = x / (1.0 + e^{-(beta * x)}) +\f] The Swish operation is introduced in the [article](https://arxiv.org/pdf/1710.05941.pdf).