Interpolate#
General#
Interpolate layer performs interpolation on \(\src\) tensor at spatial dimensions.
Operation attributes#
Attribute Name |
Description |
Value Type |
Supported Values |
Required or Optional |
|---|---|---|---|---|
Specifies type of interpolation. |
string |
|
Required |
|
Specifies how to transform the coordinate in the resized tensor to the coordinate in the original tensor. |
string |
|
Optional |
|
Specifies dst shape for spatial axes. |
s64 |
A s64 list containing positive values, |
Optional |
|
Specifies |
f32 |
A f32 list, |
Optional |
|
Controls how to interpret the shape of |
string |
|
Optional |
Note
Either sizes or scales should be provided. When sizes is used, scales will be ignored.
Note
The attribute coordinate_transformation_mode is the name of transformation mode in string format.
Here scale[x] is dst_shape[x]/src_shape[x] and x_resized is a coordinate in axis x,for any axis x from the src axis.
For half_pixel : the coordinate in the original tensor axis x is calculated as ((x_resized + 0.5) / scale[x]) - 0.5.
For align_corners : the coordinate in the original tensor axis x is calculated as 0 if dst_shape[x] == 1 else x_resized * (src_shape[x] - 1) / (dst_shape[x] - 1).
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 |
|
Required |
1 |
|
Optional |
Note
sizes is a 1D tensor describing output shape for spatial axes. It is a non-differentiable tensor.
Outputs#
Index |
Argument Name |
Required or Optional |
|---|---|---|
0 |
|
Required |
Note
The shape of the dst matches src shape except spatial dimensions. For spatial dimensions, they should match sizes from sizes or calculated from scales attribute.
Supported data types#
Interpolate operation supports the following data type combinations.
Src |
Dst |
Sizes |
|---|---|---|
f32 |
f32 |
s32 |
bf16 |
bf16 |
s32 |
f16 |
f16 |
s32 |