Struct rcudnn::utils::ScalParams [−][src]
pub struct ScalParams<T> where
T: Float + DataTypeInfo, {
pub a: T,
pub b: T,
}
Expand description
Provides a convenient interface for cuDNN’s scaling parameters alpha
and beta
.
Scaling parameters lend the source value with prior value in the destination tensor as follows: dstValue = alpha[0]*srcValue + beta[0]*priorDstValue. When beta[0] is zero, the output is not read and can contain any uninitialized data (including NaN). The storage data type for alpha[0], beta[0] is float for HALF and SINGLE tensors, and double for DOUBLE tensors. These parameters are passed using a host memory pointer.
For improved performance it is advised to use beta[0] = 0.0. Use a non-zero value for beta[0] only when blending with prior values stored in the output tensor is needed.
Fields
a: T
Alpha
b: T
Beta
Trait Implementations
Provides default values for ScalParams