Visible to Intel only — GUID: GUID-4CC7A3FA-50BC-42F4-B075-977B53C1DADD
Visible to Intel only — GUID: GUID-4CC7A3FA-50BC-42F4-B075-977B53C1DADD
ConvolutionBackwardData
General
ConvolutionBackwardData operation accepts , and optional dst shape as inputs, and compute the .
If auto_pad attribute is specified to one of valid, same_upper and same_lower, pads_begin and pads_end attributes will be ignored. The paddings will be calculated by following the below formula:
Let the parameters be:
Parameter |
Depth |
Height |
Width |
Comment |
---|---|---|---|---|
Paddings: Front, top, and left |
In the attributes we use pads_begin to indicate the corresponding vector of paddings |
|||
Padding: Back, bottom, and right |
In the attributes we use pads_end to indicate the corresponding vector of paddings |
|||
Stride |
In the attributes we use strides to indicate the corresponding vector of strides |
|||
Dilation |
In the attributes we use dilations to indicate the corresponding vector of dilations |
Firstly, is calculated according to and . Let be height dimension of and be height dimension of .
If auto_pad attribute is specified as valid :
If auto_pad attribute is specified as same_lower :
If auto_pad attribute is specified as same_upper :
where:
is either an attribute or an input tensor,
is an optional attribute.
Operation attributes
Attribute Name |
Description |
Value Type |
Supported Values |
Required or Optional |
---|---|---|---|---|
Controls the strides the weights tensor is moved when computing convolution. |
s64 |
A s64 list containing positive values |
Required |
|
Controls number of zeros to be add to the front/top/left of spatial dimensions, the attribute will be ignored when auto_pad attribute is specified to same_upper , same_lower or valid . |
s64 |
A s64 list containing non-negative values |
Required |
|
Controls number of zeros to be add to the back/bottom/right of spatial dimensions, the attribute will be ignored when auto_pad attribute is specified to same_upper , same_lower or valid . |
s64 |
A s64 list containing non-negative values |
Required |
|
Controls the amount of stretching the kernel before convolution ( visualization link ). |
s64 |
A s64 list containing positive values (>1 means dilated convolution) |
Required |
|
Controls how the padding is calculated. |
string |
none (default), same_upper , same_lower , valid |
Optional |
|
Adds additional amount of padding per each spatial axis in dst . |
s64 |
A s64 list containing non-negative values, all zeros by default |
Optional |
|
Controls how input channels and output channels are divided into. |
s64 |
A positive s64 value, 1 by default |
Optional |
|
Controls how to interpret the shape of src and dst . |
string |
NCX , NXC (default) |
Optional |
|
Controls how to interpret the shape of weights . |
string |
OIX , XIO (default) |
Optional |
|
Denotes the shape of the dst tensor. |
s64 |
A s64 list containing positive values |
Optional |
Execution arguments
The inputs and outputs must be provided according to below index order when constructing an operation.
Inputs
Index |
Argument Name |
Required or Optional |
---|---|---|
0 |
diff_dst |
Required |
1 |
weights |
Required |
2 |
dst_shape |
Optional |
Outputs
Index |
Argument Name |
Required or Optional |
---|---|---|
0 |
diff_src |
Required |
Supported data types
ConvolutionBackwardData operation supports the following data type combinations.
Diff_dst |
Weights |
Diff_src |
Dst_shape |
---|---|---|---|
f32 |
f32 |
f32 |
s32 |
bf16 |
bf16 |
bf16 |
s32 |
f16 |
f16 |
f16 |
s32 |