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

Revise PriorBoxClustered Spec (#6539)

Browse Source 
* Move detailed description up, add backtics to attr types

* Add backtics for range in clip attr description, remove non-existing attributes

* Adjusting the spec to review comments

* floating-point instead of floating point, remove default value for mandatory attribute
This commit is contained in:
Bartosz Lesniewski 2021-07-19 08:41:35 +02:00 committed by GitHub
parent 697c52abfe
commit 4373b0cb7d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 65 additions and 70 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

135
docs/ops/detection/PriorBoxClustered_1.md
View File

@ -6,77 +6,14 @@
**Short description**: *PriorBoxClustered* operation generates prior boxes of specified sizes normalized to the input image size.
**Attributes**
* *width (height)*
* **Description**: *width (height)* specifies desired boxes widths (heights) in pixels.
* **Range of values**: floating-point positive numbers
* **Type**: float[]
* **Default value**: 1.0
* **Required**: *no*
* *clip*
* **Description**: *clip* is a flag that denotes if each value in the output tensor should be clipped within [0,1].
* **Range of values**:
* false or 0 - clipping is not performed
* true or 1 - each value in the output tensor is within [0,1]
* **Type**: boolean
* **Default value**: true
* **Required**: *no*
* *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
* **Type**: float
* **Default value**: 0.0
* **Required**: *no*
* *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
* **Type**: float
* **Required**: *yes*
* *variance*
* **Description**: *variance* denotes a variance of adjusting bounding boxes.
* **Range of values**: floating-point positive numbers
* **Type**: float[]
* **Default value**: []
* **Required**: *no*
* *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
* **Type**: float
* **Default value**: 0
* **Required**: *no*
**Inputs**:
* **1**: `output_size` - 1D tensor with two integer elements `[height, width]`. Specifies the spatial size of generated grid with boxes. **Required.**
* **2**: `image_size` - 1D tensor with two integer elements `[image_height, image_width]` that specifies shape of the image for which boxes are generated. **Optional.**
**Outputs**:
* **1**: 2D tensor of shape `[2, 4 * height * width * priors_per_point]` with box coordinates. The `priors_per_point` is the number of boxes generated per each grid element. The number depends on layer attribute values.
**Detailed description**
*PriorBoxClustered* computes coordinates of prior boxes by following:
1. Calculates the *center_x* and *center_y* of prior box:
\f[
W \equiv Width \quad Of \quad Image
\f]
\f[
H \equiv Height \quad Of \quad Image
\f]
Let
\f[
W \equiv image\_width, \quad H \equiv image\_height.
\f]
Then calculations of *PriorBoxClustered* can be written as
\f[
center_x=(w+offset)*step
\f]
@ -89,7 +26,7 @@
\f[
h \subset \left( 0, H \right )
\f]
2. For each \f$s \subset \left( 0, W \right )\f$ calculates the prior boxes coordinates:
For each \f$s = \overline{0, W - 1}\f$ calculates the prior boxes coordinates:
\f[
xmin = \frac{center_x - \frac{width_s}{2}}{W}
\f]
@ -105,6 +42,64 @@
If *clip* is defined, the coordinates of prior boxes are recalculated with the formula:
\f$coordinate = \min(\max(coordinate,0), 1)\f$
**Attributes**
* *width (height)*
* **Description**: *width (height)* specifies desired boxes widths (heights) in pixels.
* **Range of values**: floating-point positive numbers
* **Type**: `float[]`
* **Default value**: 1.0
* **Required**: *no*
* *clip*
* **Description**: *clip* is a flag that denotes if each value in the output tensor should be clipped within `[0,1]`.
* **Range of values**:
* false or 0 - clipping is not performed
* true or 1 - each value in the output tensor is within `[0,1]`
* **Type**: `boolean`
* **Default value**: true
* **Required**: *no*
* *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
* **Type**: `float`
* **Default value**: 0.0
* **Required**: *no*
* *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
* **Type**: `float`
* **Required**: *yes*
* *variance*
* **Description**: *variance* denotes a variance of adjusting bounding boxes. The attribute could be 0, 1 or 4 elements.
* **Range of values**: floating-point positive numbers
* **Type**: `float[]`
* **Default value**: []
* **Required**: *no*
**Inputs**:
* **1**: `output_size` - 1D tensor of type *T_INT* with two elements `[height, width]`. Specifies the spatial size of generated grid with boxes. Required.
* **2**: `image_size` - 1D tensor of type *T_INT* with two elements `[image_height, image_width]` that specifies shape of the image for which boxes are generated. Optional.
**Outputs**:
* **1**: 2D tensor of shape `[2, 4 * height * width * priors_per_point]` and type *T_OUT* with box coordinates. The `priors_per_point` is the number of boxes generated per each grid element. The number depends on layer attribute values.
**Types**
* *T_INT*: any supported integer type.
* *T_OUT*: supported floating-point type.
**Example**
```xml