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

Clarify Reshape_1 operator documentation (#3330)

Browse Source 
* Clarify Reshape_1 operator documentation

* Fix style issue

* Fix reshape documentation after review
This commit is contained in:
Bartosz Sledz authored and GitHub committed 2020-11-26 08:29:54 +03:00
1 parent 94c6aefbfe
commit 0671916cf4
1 file changed
+73 -4
Download Patch File Download Diff File Expand all files Collapse all files
docs/ops/shape/Reshape_1.md
+73 -4
View File
@@ -9,14 +9,16 @@
**Detailed description**:
*Reshape* layer takes two input tensors: the tensor to be resized and the output tensor shape. The values in the second tensor could be -1, 0 and any positive integer number. The two special values -1 and 0:
* `0` means "copy the respective dimension of the input tensor" if `special_zero` is set to `true`; otherwise it is a normal dimension and is applicable to empty tensors.
* `-1` means that this dimension is calculated to keep the overall elements count the same as in the input tensor. Not more than one `-1` can be used in a reshape operation.
* `0` means "copy the respective dimension *(left aligned)* of the input tensor" if `special_zero` is set to `true`; otherwise it is a normal dimension and is applicable to empty tensors.
* `-1` means that this dimension is calculated to keep the overall elements count the same as in the input tensor. Not more than one `-1` can be used in a reshape operation.
If `special_zero` is set to `true` index of `0` cannot be larger than the rank of the input tensor.
**Attributes**:
* *special_zero*
* **Description**: *special_zero* controls how zero values in `shape` are interpreted. If *special_zero* is `false`, then 0 is interpreted as-is which means that output shape will contain a zero dimension at the specified location. Input and output tensors are empty in this case. If *special_zero* is `true`, then all zeros in `shape` implies the copying of corresponding dimensions from `data.shape` into the output shape.
* **Description**: *special_zero* controls how zero values in `shape` are interpreted. If *special_zero* is `false`, then 0 is interpreted as-is which means that output shape will contain a zero dimension at the specified location. Input and output tensors are empty in this case. If *special_zero* is `true`, then all zeros in `shape` implies the copying of corresponding dimensions from `data.shape` into the output shape *(left aligned)*.
* **Range of values**: `false` or `true`
* **Type**: boolean
* **Default value**: None
@@ -51,7 +53,7 @@
<dim>0</dim>
</port>
<port id="1">
<dim>2</dim> <!--The tensor contains 3 elements: 0, 4 -->
<dim>2</dim> <!--The tensor contains 2 elements: 0, 4 -->
</port>
</input>
<output>
@@ -87,3 +89,70 @@
</layer>
```
```xml
<layer ... type="Reshape" ...>
<data special_zero="true"/>
<input>
<port id="0">
<dim>2</dim>
<dim>2</dim>
<dim>3</dim>
</port>
<port id="1">
<dim>4</dim> <!--The tensor contains 4 elements: 0, 0, 1, -1 -->
</port>
</input>
<output>
<port id="2">
<dim>2</dim>
<dim>2</dim>
<dim>1</dim>
<dim>3</dim>
</port>
</output>
</layer>
```
```xml
<layer ... type="Reshape" ...>
<data special_zero="true"/>
<input>
<port id="0">
<dim>3</dim>
<dim>1</dim>
<dim>1</dim>
</port>
<port id="1">
<dim>2</dim> <!--The tensor contains 2 elements: -1, 0 -->
</port>
</input>
<output>
<port id="2">
<dim>3</dim>
<dim>1</dim>
</port>
</output>
</layer>
```
```xml
<layer ... type="Reshape" ...>
<data special_zero="true"/>
<input>
<port id="0">
<dim>3</dim>
<dim>1</dim>
<dim>1</dim>
</port>
<port id="1">
<dim>2</dim> <!--The tensor contains 2 elements: 0, -1 -->
</port>
</input>
<output>
<port id="2">
<dim>3</dim>
<dim>1</dim>
</port>
</output>
</layer>
```