From 9522f9fc04df9ee2e1e3572efd9caab74b438534 Mon Sep 17 00:00:00 2001 From: Evgeny Lazarev Date: Mon, 30 Nov 2020 18:50:55 +0300 Subject: [PATCH] Removed confusing information about required/optional output of the operation. The output exists always but it may be not connected to anywhere. --- docs/ops/activation/Clamp_1.md | 2 +- docs/ops/activation/Elu_1.md | 2 +- docs/ops/activation/Exp_1.md | 2 +- docs/ops/activation/GELU_2.md | 6 +++++- docs/ops/activation/Mish_4.md | 4 ++-- docs/ops/activation/Sigmoid_1.md | 4 ++-- docs/ops/arithmetic/Sinh_1.md | 4 ++-- docs/ops/arithmetic/Tanh_1.md | 4 ++-- docs/ops/convolution/BinaryConvolution_1.md | 3 ++- docs/ops/detection/Proposal_4.md | 4 ++-- docs/ops/detection/ROIPooling_1.md | 4 ++-- docs/ops/detection/ReorgYolo_1.md | 2 +- docs/ops/shape/Squeeze_1.md | 6 +++++- docs/ops/shape/Unsqueeze_1.md | 6 +++++- docs/ops/sort/NonMaxSuppression_5.md | 2 +- docs/ops/sort/TopK_3.md | 2 +- 16 files changed, 35 insertions(+), 22 deletions(-) diff --git a/docs/ops/activation/Clamp_1.md b/docs/ops/activation/Clamp_1.md index 4a4151a4d18291..8ee374fdf25254 100644 --- a/docs/ops/activation/Clamp_1.md +++ b/docs/ops/activation/Clamp_1.md @@ -30,7 +30,7 @@ **Outputs**: -* **1**: Multidimensional output tensor with shape and type matching the input tensor. Required. +* **1**: Multidimensional output tensor with shape and type matching the input tensor. **Detailed description**: diff --git a/docs/ops/activation/Elu_1.md b/docs/ops/activation/Elu_1.md index bc69b40de18a0f..8d5d424d02312b 100644 --- a/docs/ops/activation/Elu_1.md +++ b/docs/ops/activation/Elu_1.md @@ -33,4 +33,4 @@ elu(x) = \left\{\begin{array}{ll} **Outputs**: -* **1**: Result of Elu function applied to the input tensor *x*. Floating point tensor with shape and type matching the input tensor. Required. +* **1**: Result of Elu function applied to the input tensor *x*. Floating point tensor with shape and type matching the input tensor. diff --git a/docs/ops/activation/Exp_1.md b/docs/ops/activation/Exp_1.md index c3f05c72db96f9..b5815a271603cb 100644 --- a/docs/ops/activation/Exp_1.md +++ b/docs/ops/activation/Exp_1.md @@ -14,4 +14,4 @@ **Outputs**: -* **1**: Result of Exp function applied to the input tensor *x*. Floating point tensor with shape and type matching the input tensor. Required. +* **1**: Result of Exp function applied to the input tensor *x*. Floating point tensor with shape and type matching the input tensor. diff --git a/docs/ops/activation/GELU_2.md b/docs/ops/activation/GELU_2.md index c22e72d2b99821..461defb02c9e56 100644 --- a/docs/ops/activation/GELU_2.md +++ b/docs/ops/activation/GELU_2.md @@ -28,6 +28,10 @@ Similarly, the following Gelu approximation (typical for the TensorFlow*) is rec * **1**: Multidimensional input tensor. Required. +**Outputs**: + +* **1**: Floating point tensor with shape and type matching the input tensor. + **Example** ```xml @@ -46,4 +50,4 @@ Similarly, the following Gelu approximation (typical for the TensorFlow*) is rec -``` \ No newline at end of file +``` diff --git a/docs/ops/activation/Mish_4.md b/docs/ops/activation/Mish_4.md index de8397c188825a..6163131e11073f 100644 --- a/docs/ops/activation/Mish_4.md +++ b/docs/ops/activation/Mish_4.md @@ -16,7 +16,7 @@ **Outputs**: -* **1**: Floating point tensor with shape and type matching the input tensor. Required. +* **1**: Floating point tensor with shape and type matching the input tensor. **Types** @@ -47,4 +47,4 @@ -``` \ No newline at end of file +``` diff --git a/docs/ops/activation/Sigmoid_1.md b/docs/ops/activation/Sigmoid_1.md index f14e58e53b3115..17e012061f9c70 100644 --- a/docs/ops/activation/Sigmoid_1.md +++ b/docs/ops/activation/Sigmoid_1.md @@ -24,7 +24,7 @@ **Outputs**: -* **1**: Result of Sigmoid function applied to the input tensor *x*. Floating point tensor with shape and type matching the input tensor. Required. +* **1**: Result of Sigmoid function applied to the input tensor *x*. Floating point tensor with shape and type matching the input tensor. **Example** @@ -44,4 +44,4 @@ -``` \ No newline at end of file +``` diff --git a/docs/ops/arithmetic/Sinh_1.md b/docs/ops/arithmetic/Sinh_1.md index a4a0264f31c59e..7bac2216a42af3 100644 --- a/docs/ops/arithmetic/Sinh_1.md +++ b/docs/ops/arithmetic/Sinh_1.md @@ -16,7 +16,7 @@ **Outputs** -* **1**: The result of element-wise sinh operation. A tensor of type T. +* **1**: The result of element-wise sinh operation. A tensor of type *T*. **Types** @@ -47,4 +47,4 @@ a_{i} = sinh(a_{i}) -``` \ No newline at end of file +``` diff --git a/docs/ops/arithmetic/Tanh_1.md b/docs/ops/arithmetic/Tanh_1.md index 9f6e2d8079fb2f..d50fe2fdade034 100644 --- a/docs/ops/arithmetic/Tanh_1.md +++ b/docs/ops/arithmetic/Tanh_1.md @@ -14,7 +14,7 @@ **Outputs**: -* **1**: Result of Tanh function applied to the input tensor *x*. Floating point tensor with shape and type matching the input tensor. Required. +* **1**: Result of Tanh function applied to the input tensor *x*. Floating point tensor with shape and type matching the input tensor. **Detailed description** @@ -22,4 +22,4 @@ For each element from the input tensor calculates corresponding element in the output tensor with the following formula: \f[ tanh ( x ) = \frac{2}{1+e^{-2x}} - 1 = 2sigmoid(2x) - 1 -\f] \ No newline at end of file +\f] diff --git a/docs/ops/convolution/BinaryConvolution_1.md b/docs/ops/convolution/BinaryConvolution_1.md index d6aabd0b20c11a..21d3a5b7fb5f2b 100644 --- a/docs/ops/convolution/BinaryConvolution_1.md +++ b/docs/ops/convolution/BinaryConvolution_1.md @@ -35,4 +35,5 @@ The operation has the same attributes as a regular *Convolution* layer and sever **Outputs**: -* **1**: output tensor containing float values. Required. +* **1**: output tensor containing float values. + diff --git a/docs/ops/detection/Proposal_4.md b/docs/ops/detection/Proposal_4.md index 8bf9dca4969bff..a22cd1684c64b1 100644 --- a/docs/ops/detection/Proposal_4.md +++ b/docs/ops/detection/Proposal_4.md @@ -153,7 +153,7 @@ the second optional tensor of shape `[batch_size * post_nms_topn]` with probabil * **1**: tensor of type *T* and shape `[batch_size * post_nms_topn, 5]`. -* **2**: tensor of type *T* and shape `[batch_size * post_nms_topn]` with probabilities. *Optional*. +* **2**: tensor of type *T* and shape `[batch_size * post_nms_topn]` with probabilities. **Types** @@ -191,4 +191,4 @@ the second optional tensor of shape `[batch_size * post_nms_topn]` with probabil -``` \ No newline at end of file +``` diff --git a/docs/ops/detection/ROIPooling_1.md b/docs/ops/detection/ROIPooling_1.md index 67a7f0a1e77a23..7699b133f3c128 100644 --- a/docs/ops/detection/ROIPooling_1.md +++ b/docs/ops/detection/ROIPooling_1.md @@ -63,7 +63,7 @@ Batch indices must be in the range of `[0, N-1]`. **Outputs**: -* **1**: 4D output tensor of shape `[NUM_ROIS, C, pooled_h, pooled_w]` with feature maps of type *T*. Required. +* **1**: 4D output tensor of shape `[NUM_ROIS, C, pooled_h, pooled_w]` with feature maps of type *T*. **Types** @@ -77,4 +77,4 @@ Batch indices must be in the range of `[0, N-1]`. ... ... -``` \ No newline at end of file +``` diff --git a/docs/ops/detection/ReorgYolo_1.md b/docs/ops/detection/ReorgYolo_1.md index 4801e5f750fbe2..156657a98ba32f 100644 --- a/docs/ops/detection/ReorgYolo_1.md +++ b/docs/ops/detection/ReorgYolo_1.md @@ -26,7 +26,7 @@ **Outputs**: -* **1**: 4D output tensor of the same type as input tensor and shape `[N, C*stride*stride, H/stride, W/stride]`. Required. +* **1**: 4D output tensor of the same type as input tensor and shape `[N, C*stride*stride, H/stride, W/stride]`. **Example** diff --git a/docs/ops/shape/Squeeze_1.md b/docs/ops/shape/Squeeze_1.md index a17120e3137423..9dff893cd8a419 100644 --- a/docs/ops/shape/Squeeze_1.md +++ b/docs/ops/shape/Squeeze_1.md @@ -14,6 +14,10 @@ * **2**: 0D or 1D tensor of type *T_SHAPE* with dimensions indices to squeeze. Values could be negative. *Optional*. +**Outputs**: + +* **1**: Tensor with squeezed values of type *T*. + **Types** * *T*: supported type. @@ -65,4 +69,4 @@ -``` \ No newline at end of file +``` diff --git a/docs/ops/shape/Unsqueeze_1.md b/docs/ops/shape/Unsqueeze_1.md index 371882a2c92eda..7518605313116b 100644 --- a/docs/ops/shape/Unsqueeze_1.md +++ b/docs/ops/shape/Unsqueeze_1.md @@ -14,6 +14,10 @@ * **2**: OD or 1D tensor of type *T_SHAPE* with dimensions indices to be set to 1. Values could be negative. *Required*. +**Outputs**: + +* **1**: Tensor with unsqueezed values of type *T*. + **Types** * *T*: supported type. @@ -65,4 +69,4 @@ -``` \ No newline at end of file +``` diff --git a/docs/ops/sort/NonMaxSuppression_5.md b/docs/ops/sort/NonMaxSuppression_5.md index a60b0206392794..6fc70ed7424999 100644 --- a/docs/ops/sort/NonMaxSuppression_5.md +++ b/docs/ops/sort/NonMaxSuppression_5.md @@ -72,7 +72,7 @@ class must not exceed `max_output_boxes_per_class`. * **2**: `selected_scores` - tensor of type *T_THRESHOLDS* and shape `[number of selected boxes, 3]` containing information about scores for each selected box as triplets `[batch_index, class_index, box_score]`. -* **3**: `valid_outputs` - 1D tensor with 1 element of type *T_IND* representing the total number of selected boxes. Optional. +* **3**: `valid_outputs` - 1D tensor with 1 element of type *T_IND* representing the total number of selected boxes. Plugins which do not support dynamic output tensors produce `selected_indices` and `selected_scores` tensors of shape `[min(num_boxes, max_output_boxes_per_class) * num_batches * num_classes, 3]` which is an upper bound for the number of possible selected boxes. Output tensor elements following the really selected boxes are filled with value -1. diff --git a/docs/ops/sort/TopK_3.md b/docs/ops/sort/TopK_3.md index 7bf5c828cb62f8..d3a03ae2b6f58d 100644 --- a/docs/ops/sort/TopK_3.md +++ b/docs/ops/sort/TopK_3.md @@ -51,7 +51,7 @@ * **1**: Output tensor of type *T* with top *k* values from the input tensor along specified dimension *axis*. The shape of the tensor is `[input1.shape[0], ..., input1.shape[axis-1], k, input1.shape[axis+1], ...]`. -* **2**: Output tensor with top *k* indices for each slice along *axis* dimension of type *T_IND*. The shape of the tensor is the same as for the 1st output, that is `[input1.shape[0], ..., input1.shape[axis-1], k, input1.shape[axis+1], ...]` +* **2**: Output tensor with top *k* indices for each slice along *axis* dimension of type *T_IND*. The shape of the tensor is the same as for the 1st output, that is `[input1.shape[0], ..., input1.shape[axis-1], k, input1.shape[axis+1], ...]`. **Types**