This API is used to perform the backward computation of GroupedBiasAdd. The extended API of this API is .
Formula:[object Object] (1) If
[object Object]is available:gradY has two dimensions. H indicates the size of the last dimension of gradY, and G indicates the size of the 0th dimension of groupIdxOptional, that is, groupIdxOptional has G numbers. groupIdxOptional(j) indicates the size of the jth number. After the computation, out is a 2D tensor with shape (G, H).[object Object] (2) If
[object Object]is unavailable:gradY has three dimensions. G, C, and H indicate the sizes of the 0th to 2nd dimensions of gradY, respectively. After computation, out is two-dimensional with shape (G, H).
Example:
Each operator has calls. First, [object Object] is called to obtain the workspace size required for computation and the executor that contains the operator computation process. Then, [object Object] is called to perform computation.
Parameters:
[object Object]Returns:
[object Object]: status code. For details, see .The first-phase API performs input parameter validation. The following error codes may be returned:
[object Object]
- Deterministic computing:
[object Object]defaults to a deterministic implementation.
[object Object]supports a maximum of 2048 numbers.
- If
[object Object]is available, ensure that the tensor data is sorted in ascending order and the last value is equal to the size of dimension 0 of[object Object].
- If
- If
[object Object]is available, ensure that the tensor values are not greater than the maximum INT32 value and are not negative numbers.
- If
The following example is for reference only. For details, see .