* Doc Migration from Gitlab (#1289) * doc migration * fix * Update FakeQuantize_1.md * Update performance_benchmarks.md * Updates graphs for FPGA * Update performance_benchmarks.md * Change DL Workbench structure (#1) * Changed DL Workbench structure * Fixed tags * fixes * Update ie_docs.xml * Update performance_benchmarks_faq.md * Fixes in DL Workbench layout * Fixes for CVS-31290 * [DL Workbench] Minor correction * Fix for CVS-30955 * Added nGraph deprecation notice as requested by Zoe * fix broken links in api doxy layouts * CVS-31131 fixes * Additional fixes * Fixed POT TOC * Update PAC_Configure.md PAC DCP 1.2.1 install guide. * Update inference_engine_intro.md * fix broken link * Update opset.md * fix * added opset4 to layout * added new opsets to layout, set labels for them * Update VisionAcceleratorFPGA_Configure.md Updated from 2020.3 to 2020.4 Co-authored-by: domi2000 <domi2000@users.noreply.github.com>
2.9 KiB
ScatterElementsUpdate
Versioned name: ScatterElementsUpdate-3
Category: Data movement operations
Short description: Creates a copy of the first input tensor with updated elements specified with second and third input tensors.
Detailed description: For each entry in updates, the target index in data is obtained by combining the corresponding entry in
indices with the index of the entry itself: the index-value for dimension equal to axis is obtained from the value of the corresponding entry in
indices and the index-value for dimension not equal to axis is obtained from the index of the entry itself.
For instance, in a 3D tensor case, the update corresponding to the [i][j][k] entry is performed as below:
output[indices[i][j][k]][j][k] = updates[i][j][k] if axis = 0,
output[i][indices[i][j][k]][k] = updates[i][j][k] if axis = 1,
output[i][j][indices[i][j][k]] = updates[i][j][k] if axis = 2
update tensor dimensions are less or equal to the corresponding data tensor dimensions.
Attributes: ScatterElementsUpdate does not have attributes.
Inputs:
-
1:
datatensor of arbitrary rankrand of type T. Required. -
2:
indicestensor with indices of type T_IND. The rank of the tensor is equal to the rank ofdatatensor. All index values are expected to be within bounds[0, s - 1]along axis of sizes. If multiple indices point to the same output location then the order of updating the values is undefined. If an index points to non-existing output tensor element or is negative then exception is raised. Required. -
3:
updatestensor of shape equal to the shape ofindicestensor and of type T. Required. -
4:
axistensor with scalar or 1D tensor with one element of type T_AXIS specifying axis for scatter. The value can be in range[-r, r - 1]whereris the rank ofdata. Required.
Outputs:
- 1: tensor with shape equal to
datatensor of the type T.
Types
-
T: any numeric type.
-
T_IND: any integer numeric type.
-
T_AXIS: any integer numeric type.
Example
<layer ... type="ScatterElementsUpdate">
<input>
<port id="0">
<dim>1000</dim>
<dim>256</dim>
<dim>7</dim>
<dim>7</dim>
</port>
<port id="1">
<dim>125</dim>
<dim>20</dim>
<dim>7</dim>
<dim>6</dim>
</port>
<port id="2">
<dim>125</dim>
<dim>20</dim>
<dim>7</dim>
<dim>6</dim>
</port>
<port id="3"> <!-- value [0] -->
<dim>1</dim>
</port>
</input>
<output>
<port id="4" precision="FP32">
<dim>1000</dim>
<dim>256</dim>
<dim>7</dim>
<dim>7</dim>
</port>
</output>
</layer>