Crate caffe2op_gelu

Structs

• GeluFunctor
• GeluGradientFunctor
• GetGeluGradient

Constants

• kFastCoeff

Functions

• cost_inference_for_gelu

Type Definitions

• GeluGradientOp
• GeluOp
  | Relu takes one input data (Tensor) and | produces one output data (Tensor) where | the rectified linear function, y = xP(X | <= x) where X ~ N(0, 1), is applied to the | tensor elementwise. | | Input: X, output: Y |