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

use floating-point in docs (#6659)

Browse Source 
* use `floating-point` in docs

* Get back capital letter.
This commit is contained in:
Patryk Elszkowski 2021-07-16 06:48:45 +02:00 committed by GitHub
parent 1621c66ad8
commit 39afcb2e99
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
48 changed files with 81 additions and 81 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docs/ops/activation/Clamp_1.md
View File

@ -23,14 +23,14 @@ clamp( x_{i} )=\min\big( \max\left( x_{i}, min\_value \right), max\_value \big)
* *min*
* **Description**: *min* is the lower bound of values in the output.
* **Range of values**: arbitrary floating point number
* **Range of values**: arbitrary floating-point number
* **Type**: `float`
* **Required**: *yes*
* *max*
* **Description**: *max* is the upper bound of values in the output.
* **Range of values**: arbitrary floating point number
* **Range of values**: arbitrary floating-point number
* **Type**: `float`
* **Required**: *yes*

2
docs/ops/activation/HSigmoid_5.md
View File

@ -27,7 +27,7 @@ The HSigmoid operation is introduced in the following [article](https://arxiv.or
**Types**
* *T*: any floating point type.
* *T*: any floating-point type.
**Examples**

2
docs/ops/activation/HSwish_4.md
View File

@ -27,7 +27,7 @@ The HSwish operation is introduced in the following [article](https://arxiv.org/
**Types**
* *T*: arbitrary supported floating point type.
* *T*: arbitrary supported floating-point type.
**Example**

2
docs/ops/activation/HardSigmoid_1.md
View File

@ -30,7 +30,7 @@ For each element from the input tensor calculates corresponding
**Types**
* *T*: any floating point type.
* *T*: any floating-point type.
**Examples**

2
docs/ops/activation/LogSoftmax_5.md
View File

@ -32,7 +32,7 @@ LogSoftmax(x, axis) = t - Log(ReduceSum(Exp(t), axis))
**Types**
* *T*: any floating point type.
* *T*: any floating-point type.
**Mathematical Formulation**

4
docs/ops/activation/Sigmoid_1.md
View File

@ -20,11 +20,11 @@ sigmoid( x ) = \frac{1}{1+e^{-x}}
**Inputs**:
* **1**: Input tensor *x* of any floating point type. **Required.**
* **1**: Input tensor *x* of any floating-point type. **Required.**
**Outputs**:
* **1**: Result of Sigmoid function applied to the input tensor *x*. Floating point tensor with shape and type matching the input tensor.
* **1**: Result of Sigmoid function applied to the input tensor *x*. Floating-point tensor with shape and type matching the input tensor.
**Example**

2
docs/ops/arithmetic/Acosh_3.md
View File

@ -20,7 +20,7 @@
**Types**
* *T*: any floating point type.
* *T*: any floating-point type.
*Acosh* does the following with the input tensor *a*:

2
docs/ops/arithmetic/Atanh_3.md
View File

@ -20,7 +20,7 @@
**Types**
* *T*: any floating point type.
* *T*: any floating-point type.
*Atanh* does the following with the input tensor *a*:

2
docs/ops/arithmetic/Erf_1.md
View File

@ -27,7 +27,7 @@ erf(x) = \pi^{-1} \int_{-x}^{x} e^{-t^2} dt
**Types**
* *T*: any supported floating point type.
* *T*: any supported floating-point type.
**Examples**

4
docs/ops/detection/DeformablePSROIPooling_1.md
View File

@ -66,7 +66,7 @@ This operation is compatible with [MXNet DeformablePSROIPooling](https://mxnet.a
* *trans_std*
* **Description**: *trans_std* is the value that all third input values (offests) are multiplied with to modulate the magnitude of the offsets.
* **Range of values**: floating point number
* **Range of values**: floating-point number
* **Type**: `float`
* **Default value**: 1
* **Required**: *no*
@ -93,7 +93,7 @@ Batch indices must be in the range of `[0, N_in-1]`.
**Types**:
* *T*: Any floating point type.
* *T*: Any floating-point type.
**Example**

6
docs/ops/detection/DetectionOutput_1.md
View File

@ -69,14 +69,14 @@ At each feature map cell, *DetectionOutput* predicts the offsets relative to the
* *nms_threshold*
* **Description**: threshold to be used in the NMS stage
* **Range of values**: floating point values
* **Range of values**: floating-point values
* **Type**: float
* **Required**: *yes*
* *confidence_threshold*
* **Description**: only consider detections whose confidences are larger than a threshold. If not provided, consider all boxes.
* **Range of values**: floating point values
* **Range of values**: floating-point values
* **Type**: float
* **Default value**: 0
* **Required**: *no*
@ -145,7 +145,7 @@ At each feature map cell, *DetectionOutput* predicts the offsets relative to the
**Types**
* *T*: any supported floating point type.
* *T*: any supported floating-point type.
**Example**

10
docs/ops/detection/ExperimentalDetectronDetectionOutput_6.md
View File

@ -58,7 +58,7 @@ tensor elements.
* **Description**: The *score_threshold* attribute specifies a threshold to consider only detections whose score are
larger than the threshold.
* **Range of values**: non-negative floating point number
* **Range of values**: non-negative floating-point number
* **Type**: float
* **Default value**: None
* **Required**: *yes*
@ -66,7 +66,7 @@ tensor elements.
* *nms_threshold*
* **Description**: The *nms_threshold* attribute specifies a threshold to be used in the NMS stage.
* **Range of values**: non-negative floating point number
* **Range of values**: non-negative floating-point number
* **Type**: float
* **Default value**: None
* **Required**: *yes*
@ -109,7 +109,7 @@ tensor elements.
* *max_delta_log_wh*
* **Description**: The *max_delta_log_wh* attribute specifies maximal delta of logarithms for width and height.
* **Range of values**: floating point number
* **Range of values**: floating-point number
* **Type**: float
* **Default value**: None
* **Required**: *yes*
@ -117,7 +117,7 @@ tensor elements.
* *deltas_weights*
* **Description**: The *deltas_weights* attribute specifies weights for bounding boxes sizes deltas.
* **Range of values**: a list of non-negative floating point numbers
* **Range of values**: a list of non-negative floating-point numbers
* **Type**: float[]
* **Default value**: None
* **Required**: *yes*
@ -146,7 +146,7 @@ should be the same. **Required.**
**Types**
* *T*: any supported floating point type.
* *T*: any supported floating-point type.
* *T_IND*: `int64` or `int32`.

6
docs/ops/detection/ExperimentalDetectronGenerateProposalsSingleImage_6.md
View File

@ -23,7 +23,7 @@ is less than *post_nms_count* returns output tensors filled with zeroes.
* *min_size*
* **Description**: The *min_size* attribute specifies minimum box width and height.
* **Range of values**: non-negative floating point number
* **Range of values**: non-negative floating-point number
* **Type**: float
* **Default value**: None
* **Required**: *yes*
@ -31,7 +31,7 @@ is less than *post_nms_count* returns output tensors filled with zeroes.
* *nms_threshold*
* **Description**: The *nms_threshold* attribute specifies threshold to be used in the NMS stage.
* **Range of values**: non-negative floating point number
* **Range of values**: non-negative floating-point number
* **Type**: float
* **Default value**: None
* **Required**: *yes*
@ -73,7 +73,7 @@ Height and width for third and fourth inputs should be equal. **Required.**
**Types**
* *T*: any supported floating point type.
* *T*: any supported floating-point type.
**Example**

2
docs/ops/detection/ExperimentalDetectronPriorGridGenerator_6.md
View File

@ -81,7 +81,7 @@ rest output tensor elements.
**Types**
* *T*: any supported floating point type.
* *T*: any supported floating-point type.
**Example**

2
docs/ops/detection/ExperimentalDetectronROIFeatureExtractor_6.md
View File

@ -86,7 +86,7 @@ must be the same as for 1 input: `[number_of_ROIs, 4]`.
**Types**
* *T*: any supported floating point type.
* *T*: any supported floating-point type.
**Example**

2
docs/ops/detection/PSROIPooling_1.md
View File

@ -72,7 +72,7 @@ Batch indices must be in the range of `[0, N-1]`.
**Types**
* *T*: any supported floating point type.
* *T*: any supported floating-point type.
**Example**

10
docs/ops/detection/PriorBoxClustered_1.md
View File

@ -11,7 +11,7 @@
* *width (height)*
* **Description**: *width (height)* specifies desired boxes widths (heights) in pixels.
* **Range of values**: floating point positive numbers
* **Range of values**: floating-point positive numbers
* **Type**: float[]
* **Default value**: 1.0
* **Required**: *no*
@ -29,7 +29,7 @@
* *step (step_w, step_h)*
* **Description**: *step (step_w, step_h)* is a distance between box centers. For example, *step* equal 85 means that the distance between neighborhood prior boxes centers is 85. If both *step_h* and *step_w* are 0 then they are updated with value of *step*. If after that they are still 0 then they are calculated as input image width(height) divided with first input width(height).
* **Range of values**: floating point positive number
* **Range of values**: floating-point positive number
* **Type**: float
* **Default value**: 0.0
* **Required**: *no*
@ -37,14 +37,14 @@
* *offset*
* **Description**: *offset* is a shift of box respectively to top left corner. For example, *offset* equal 85 means that the shift of neighborhood prior boxes centers is 85.
* **Range of values**: floating point positive number
* **Range of values**: floating-point positive number
* **Type**: float
* **Required**: *yes*
* *variance*
* **Description**: *variance* denotes a variance of adjusting bounding boxes.
* **Range of values**: floating point positive numbers
* **Range of values**: floating-point positive numbers
* **Type**: float[]
* **Default value**: []
* **Required**: *no*
@ -52,7 +52,7 @@
* *img_h (img_w)*
* **Description**: *img_h (img_w)* specifies height (width) of input image. These attributes are taken from the second input `image_size` height(width) unless provided explicitly as the value for this attributes.
* **Range of values**: floating point positive number
* **Range of values**: floating-point positive number
* **Type**: float
* **Default value**: 0
* **Required**: *no*

10
docs/ops/detection/PriorBox_1.md
View File

@ -46,7 +46,7 @@
* *min_size (max_size)*
* **Description**: *min_size (max_size)* is the minimum (maximum) box size (in pixels).
* **Range of values**: positive floating point numbers
* **Range of values**: positive floating-point numbers
* **Type**: `float[]`
* **Default value**: []
* **Required**: *no*
@ -82,7 +82,7 @@
* *step*
* **Description**: *step* is a distance between box centers.
* **Range of values**: floating point non-negative number
* **Range of values**: floating-point non-negative number
* **Type**: `float`
* **Default value**: 0
* **Required**: *no*
@ -90,14 +90,14 @@
* *offset*
* **Description**: *offset* is a shift of box respectively to top left corner.
* **Range of values**: floating point non-negative number
* **Range of values**: floating-point non-negative number
* **Type**: `float`
* **Required**: *yes*
* *variance*
* **Description**: *variance* denotes a variance of adjusting bounding boxes. The attribute could contain 0, 1 or 4 elements.
* **Range of values**: floating point positive numbers
* **Range of values**: floating-point positive numbers
* **Type**: `float[]`
* **Default value**: []
* **Required**: *no*
@ -149,7 +149,7 @@
**Types**
* *T_INT*: any supported integer type.
* *T_OUT*: supported floating point type.
* *T_OUT*: supported floating-point type.
**Example**

2
docs/ops/detection/Proposal_1.md
View File

@ -141,7 +141,7 @@
**Types**
* *T*: floating point type.
* *T*: floating-point type.
**Example**

2
docs/ops/detection/Proposal_4.md
View File

@ -152,7 +152,7 @@ the second optional tensor of shape `[batch_size * post_nms_topn]` with probabil
**Types**
* *T*: floating point type.
* *T*: floating-point type.
**Example**

2
docs/ops/detection/ROIAlign_3.md
View File

@ -69,7 +69,7 @@ The box height and width are calculated the following way: `roi_width = max(spat
**Types**
* *T*: any supported floating point type.
* *T*: any supported floating-point type.
* *IND_T*: any supported integer type.

2
docs/ops/detection/ROIPooling_1.md
View File

@ -64,7 +64,7 @@ Batch indices must be in the range of `[0, N-1]`.
**Types**
* *T*: any supported floating point type.
* *T*: any supported floating-point type.
**Example**

4
docs/ops/detection/RegionYolo_1.md
View File

@ -13,7 +13,7 @@
* *anchors*
* **Description**: *anchors* codes a flattened list of pairs `[width, height]` that codes prior box sizes. This attribute is not used in output computation, but it is required for post-processing to restore real box coordinates.
* **Range of values**: list of any length of positive floating point number
* **Range of values**: list of any length of positive floating-point number
* **Type**: `float[]`
* **Default value**: None
* **Required**: *no*
@ -83,7 +83,7 @@
`output.shape = [data.shape[0], ..., data.shape[axis-1], flat_dim, data.shape[end_axis + 1], ...]`
**Types**
* *T*: any supported floating point type.
* *T*: any supported floating-point type.
**Example**

4
docs/ops/generation/Range_4.md
View File

@ -51,7 +51,7 @@ the i-th element is calculated by the following formula:
val[i+1]=val[i]+step.
\f]
The calculations are done after casting all values to `accumulate_type(output_type)`. `accumulate_type` is a type that have better or equal accuracy for accumulation than `output_type` on current hardware, e.g. `fp64` for `fp16`. The number of elements is calculated in the floating point type according to the following formula:
The calculations are done after casting all values to `accumulate_type(output_type)`. `accumulate_type` is a type that have better or equal accuracy for accumulation than `output_type` on current hardware, e.g. `fp64` for `fp16`. The number of elements is calculated in the floating-point type according to the following formula:
\f[
max(ceil((end − start) / step), 0)
@ -103,7 +103,7 @@ This is aligned with PyTorch's operation `torch.arange`, to align with tensorflo
</layer>
```
*Example 3: floating point*
*Example 3: floating-point*
```xml
<layer ... type="Range">

2
docs/ops/image/Interpolate_1.md
View File

@ -60,7 +60,7 @@ This is a scalar that specifies padding for each spatial dimension.
**Inputs**
* **1**: `data` - Input tensor with data for interpolation. Type of elements is any supported floating point type. **Required.**
* **1**: `data` - Input tensor with data for interpolation. Type of elements is any supported floating-point type. **Required.**
* **2**: `target_spatial_shape` - 1D tensor describing output shape for spatial axes. Number of elements matches the number of indices in *axes* attribute, the order matches as well. **Required.**

6
docs/ops/image/Interpolate_4.md
View File

@ -80,8 +80,8 @@
* *cube_coeff*
* **Description**: *cube_coeff* specifies the parameter *a* for cubic interpolation (see, e.g. [article](https://ieeexplore.ieee.org/document/1163711/)). *cube_coeff* is used only when `mode == cubic`.
* **Range of values**: floating point number
* **Type**: any of supported floating point type
* **Range of values**: floating-point number
* **Type**: any of supported floating-point type
* **Default value**: `-0.75`
* **Required**: *no*
@ -102,7 +102,7 @@
**Types**
* *T*: any supported numeric type.
* *T_SIZE*: any supported integer type.
* *T_SCALES*: any supported floating point type.
* *T_SCALES*: any supported floating-point type.
* *T_AXES*: any supported integer type.

2
docs/ops/matrix/MatMul_1.md
View File

@ -67,7 +67,7 @@ Two attributes, `transpose_a` and `transpose_b` specify embedded transposition f
**Types**:
* *T*: any supported floating point or integer type.
* *T*: any supported floating-point or integer type.
**Example**

4
docs/ops/normalization/GRN_1.md
View File

@ -17,13 +17,13 @@
* *bias*
* **Description**: *bias* is added to the variance.
* **Range of values**: a non-negative floating point value
* **Range of values**: a non-negative floating-point value
* **Type**: `float`
* **Required**: *yes*
**Inputs**
* **1**: Input tensor with element of any floating point type and `2 <= rank <=4`. **Required.**
* **1**: Input tensor with element of any floating-point type and `2 <= rank <=4`. **Required.**
**Outputs**

2
docs/ops/normalization/LRN_1.md
View File

@ -68,7 +68,7 @@ output = data / (bias + (alpha / size ** len(axes)) * sqr_sum) ** beta
* **1**: Output tensor of type *T* and the same shape as the `data` input tensor.
**Types**
* *T*: any supported floating point type.
* *T*: any supported floating-point type.
* *T_IND*: any supported integer type.
**Example**

2
docs/ops/normalization/MVN_1.md
View File

@ -48,7 +48,7 @@ o_{i}=\frac{o_{i}}{\sum \sqrt {o_{k}^2}+\epsilon}
**Inputs**
* **1**: 4D or 5D input tensor of any floating point type. **Required.**
* **1**: 4D or 5D input tensor of any floating-point type. **Required.**
**Outputs**

2
docs/ops/normalization/MVN_6.md
View File

@ -63,7 +63,7 @@ o_{i}=\frac{o_{i}}{\sqrt {\sum {o_{k}^2}}+\epsilon}
**Types**
* *T*: any floating point type.
* *T*: any floating-point type.
* *T_IND*: `int64` or `int32`.

2
docs/ops/pooling/MaxPool_1.md
View File

@ -70,7 +70,7 @@
**Types**
* *T*: floating point or integer type.
* *T*: floating-point or integer type.
**Mathematical Formulation**
Output shape calculation based on `auto_pad` and `rounding_type`:

4
docs/ops/sequence/CTCGreedyDecoderSeqLen_6.md
View File

@ -19,7 +19,7 @@ Decoding is done in two steps:
Sequences in the batch can have different length. The lengths of sequences are coded in the second input integer tensor `sequence_length`.
The main difference between [CTCGreedyDecoder](CTCGreedyDecoder_1.md) and CTCGreedyDecoderSeqLen is in the second input. CTCGreedyDecoder uses 2D input floating point tensor with sequence masks for each sequence in the batch while CTCGreedyDecoderSeqLen uses 1D integer tensor with sequence lengths.
The main difference between [CTCGreedyDecoder](CTCGreedyDecoder_1.md) and CTCGreedyDecoderSeqLen is in the second input. CTCGreedyDecoder uses 2D input floating-point tensor with sequence masks for each sequence in the batch while CTCGreedyDecoderSeqLen uses 1D integer tensor with sequence lengths.
**Attributes**
@ -63,7 +63,7 @@ The main difference between [CTCGreedyDecoder](CTCGreedyDecoder_1.md) and CTCGre
**Types**
* *T_F*: any supported floating point type.
* *T_F*: any supported floating-point type.
* *T_I*: `int32` or `int64`.

2
docs/ops/sequence/CTCGreedyDecoder_1.md
View File

@ -37,7 +37,7 @@ Sequences in the batch can have different length. The lengths of sequences are c
* **1**: Output tensor of type *T_F* and shape `[N, T, 1, 1]` which is filled with integer elements containing final sequence class indices. A final sequence can be shorter that the size `T` of the tensor, all elements that do not code sequence classes are filled with `-1`.
**Types**
* *T_F*: any supported floating point type.
* *T_F*: any supported floating-point type.
**Example**

2
docs/ops/sequence/CTCLoss_4.md
View File

@ -96,7 +96,7 @@ Having log-probabilities for aligned paths, log of summed up probabilities for t
**Types**
* *T_F*: any supported floating point type.
* *T_F*: any supported floating-point type.
* *T1*, *T2*: `int32` or `int64`.

2
docs/ops/sequence/GRUCell_3.md
View File

@ -65,7 +65,7 @@
**Types**
* *T*: any supported floating point type.
* *T*: any supported floating-point type.
**Example**
```xml

2
docs/ops/sequence/GRUSequence_5.md
View File

@ -81,7 +81,7 @@ A single cell in the sequence is implemented in the same way as in <a href="#GRU
**Types**
* *T1*: any supported floating point type.
* *T1*: any supported floating-point type.
* *T2*: any supported integer type.
**Example**

2
docs/ops/sequence/LSTMCell_1.md
View File

@ -79,7 +79,7 @@ tanh - (e^{2x} - 1)/(e^{2x} + 1)
**Types**
* *T*: any supported floating point type.
* *T*: any supported floating-point type.
**Example**
```xml

2
docs/ops/sequence/LSTMSequence_1.md
View File

@ -77,7 +77,7 @@ A single cell in the sequence is implemented in the same way as in <a href="#LST
**Types**
* *T1*: any supported floating point type.
* *T1*: any supported floating-point type.
* *T2*: any supported integer type.
**Example**

2
docs/ops/sequence/RNNCell_3.md
View File

@ -57,7 +57,7 @@
**Types**
* *T*: any supported floating point type.
* *T*: any supported floating-point type.
**Example**
```xml

2
docs/ops/sequence/RNNSequence_5.md
View File

@ -73,7 +73,7 @@ A single cell in the sequence is implemented in the same way as in <a href="#RNN
**Types**
* *T1*: any supported floating point type.
* *T1*: any supported floating-point type.
* *T2*: any supported integer type.
**Example**

2
docs/ops/sort/ExperimentalDetectronTopKROIs_6.md
View File

@ -35,7 +35,7 @@ output tensor elements.
**Types**
* *T*: any supported floating point type.
* *T*: any supported floating-point type.
**Example**

4
docs/ops/sort/MatrixNMS_8.md
View File

@ -136,11 +136,11 @@ When there is no box selected, `selected_num` is filled with `0`. `selected_outp
**Types**
* *T*: floating point type.
* *T*: floating-point type.
* *T_MAX_BOXES*: integer type.
* *T_THRESHOLDS*: floating point type.
* *T_THRESHOLDS*: floating-point type.
* *T_IND*: `int64` or `int32`.

4
docs/ops/sort/MulticlassNMS_8.md
View File

@ -129,11 +129,11 @@ When there is no box selected, `selected_num` is filled with `0`. `selected_outp
**Types**
* *T*: floating point type.
* *T*: floating-point type.
* *T_MAX_BOXES*: integer type.
* *T_THRESHOLDS*: floating point type.
* *T_THRESHOLDS*: floating-point type.
* *T_IND*: `int64` or `int32`.

8
docs/ops/sort/NonMaxSuppression_1.md
View File

@ -41,15 +41,15 @@ class must not exceed `max_output_boxes_per_class`.
**Inputs**:
* **1**: `boxes` - floating point tensor of shape `[num_batches, num_boxes, 4]` with box coordinates. **Required.**
* **1**: `boxes` - floating-point tensor of shape `[num_batches, num_boxes, 4]` with box coordinates. **Required.**
* **2**: `scores` - floating point tensor of shape `[num_batches, num_classes, num_boxes]` with box scores. **Required.**
* **2**: `scores` - floating-point tensor of shape `[num_batches, num_classes, num_boxes]` with box scores. **Required.**
* **3**: `max_output_boxes_per_class` - integer scalar tensor specifying maximum number of boxes to be selected per class. Optional with default value 0 meaning select no boxes.
* **4**: `iou_threshold` - floating point scalar tensor specifying intersection over union threshold. Optional with default value 0 meaning keep all boxes.
* **4**: `iou_threshold` - floating-point scalar tensor specifying intersection over union threshold. Optional with default value 0 meaning keep all boxes.
* **5**: `score_threshold` - floating point scalar tensor specifying minimum score to consider box for the processing. Optional with default value 0.
* **5**: `score_threshold` - floating-point scalar tensor specifying minimum score to consider box for the processing. Optional with default value 0.
**Outputs**:

4
docs/ops/sort/NonMaxSuppression_3.md
View File

@ -66,11 +66,11 @@ The output tensor is filled with -1s for output tensor elements if the total num
**Types**
* *T*: floating point type.
* *T*: floating-point type.
* *T_MAX_BOXES*: integer type.
* *T_THRESHOLDS*: floating point type.
* *T_THRESHOLDS*: floating-point type.
* *T_IND*: `int64` or `int32`.

4
docs/ops/sort/NonMaxSuppression_4.md
View File

@ -66,11 +66,11 @@ The output tensor is filled with -1s for output tensor elements if the total num
**Types**
* *T*: floating point type.
* *T*: floating-point type.
* *T_MAX_BOXES*: integer type.
* *T_THRESHOLDS*: floating point type.
* *T_THRESHOLDS*: floating-point type.
* *T_IND*: `int64` or `int32`.

4
docs/ops/sort/NonMaxSuppression_5.md
View File

@ -78,11 +78,11 @@ Plugins which do not support dynamic output tensors produce `selected_indices` a
**Types**
* *T*: floating point type.
* *T*: floating-point type.
* *T_MAX_BOXES*: integer type.
* *T_THRESHOLDS*: floating point type.
* *T_THRESHOLDS*: floating-point type.
* *T_IND*: `int64` or `int32`.