int8_softmax_op.cc

#include "caffe2/operators/quantized/int8_softmax_op.h"

namespace caffe2 {

REGISTER_CPU_OPERATOR(Int8Softmax, int8::Int8SoftmaxOp);

OPERATOR_SCHEMA(Int8Softmax)
    .NumInputs(1)
    .NumOutputs(1)
    .Arg("Y_scale", "Output tensor quantization scale")
    .Arg("Y_zero_point", "Output tensor quantization offset")
    .IdenticalTypeAndShape()
    .SetDoc(R"DOC(
The operator computes the softmax normalized values for each layer in the batch
 of the given input. The input is a 2-D tensor (Tensor<float>) of size
(batch_size x input_feature_dimensions). The output tensor has the same shape
and contains the softmax normalized values of the corresponding input.

X does not need to explicitly be a 2D vector; rather, it will be
coerced into one. For an arbitrary n-dimensional tensor
X \in [a_0, a_1, ..., a_{k-1}, a_k, ..., a_{n-1}] and k is
the axis provided, then X will be coerced into a 2-dimensional tensor with
dimensions [a_0 * ... * a_{k-1}, a_k * ... * a_{n-1}]. For the default
case where axis=1, this means the X tensor will be coerced into a 2D tensor
of dimensions [a_0, a_1 * ... * a_{n-1}], where a_0 is often the batch size.
In this situation, we must have a_0 = N and a_1 * ... * a_{n-1} = D.
Each of these dimensions must be matched correctly, or else the operator
will throw errors.
)DOC")
    .Arg(
        "axis",
        "(int) default to 1; describes the axis of the inputs when coerced "
        "to 2D; defaults to one because the 0th axis most likely describes "
        "the batch_size")
    .Input(
        0,
        "input",
        "The input tensor that's coerced into a 2D matrix of size (NxD) "
        "as described above.")
    .Output(
        0,
        "output",
        "The softmax normalized output values with the same "
        "shape as input tensor.");

} // namespace caffe2