You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
71 lines
2.4 KiB
71 lines
2.4 KiB
/* Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved.
|
|
|
|
Licensed under the Apache License, Version 2.0 (the "License");
|
|
you may not use this file except in compliance with the License.
|
|
You may obtain a copy of the License at
|
|
|
|
http://www.apache.org/licenses/LICENSE-2.0
|
|
|
|
Unless required by applicable law or agreed to in writing, software
|
|
distributed under the License is distributed on an "AS IS" BASIS,
|
|
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
See the License for the specific language governing permissions and
|
|
limitations under the License. */
|
|
|
|
#pragma once
|
|
#include "paddle/fluid/operators/elementwise_op_function.h"
|
|
|
|
namespace paddle {
|
|
namespace operators {
|
|
|
|
template <typename T>
|
|
struct SubFunctor {
|
|
inline HOSTDEVICE T operator()(T a, T b) const { return a - b; }
|
|
};
|
|
|
|
template <typename DeviceContext, typename T>
|
|
class ElementwiseSubKernel : public framework::OpKernel<T> {
|
|
public:
|
|
void Compute(const framework::ExecutionContext& ctx) const override {
|
|
using Tensor = framework::Tensor;
|
|
|
|
auto* x = ctx.Input<Tensor>("X");
|
|
auto* y = ctx.Input<Tensor>("Y");
|
|
auto* z = ctx.Output<Tensor>("Out");
|
|
z->mutable_data<T>(ctx.GetPlace());
|
|
int axis = ctx.Attr<int>("axis");
|
|
ElementwiseComputeEx<SubFunctor<T>, DeviceContext, T>(ctx, x, y, axis,
|
|
SubFunctor<T>(), z);
|
|
}
|
|
};
|
|
|
|
template <typename T>
|
|
struct SubGradDX {
|
|
HOSTDEVICE T operator()(T x, T y, T out, T dout) const { return dout; }
|
|
};
|
|
|
|
template <typename T>
|
|
struct SubGradDY {
|
|
HOSTDEVICE T operator()(T x, T y, T out, T dout) const { return -dout; }
|
|
};
|
|
|
|
template <typename DeviceContext, typename T>
|
|
class ElementwiseSubGradKernel : public framework::OpKernel<T> {
|
|
public:
|
|
void Compute(const framework::ExecutionContext& ctx) const override {
|
|
using Tensor = framework::Tensor;
|
|
|
|
auto* x = ctx.Input<Tensor>("X");
|
|
auto* y = ctx.Input<Tensor>("Y");
|
|
auto* out = ctx.Input<Tensor>("Out");
|
|
auto* dout = ctx.Input<Tensor>(framework::GradVarName("Out"));
|
|
auto* dx = ctx.Output<Tensor>(framework::GradVarName("X"));
|
|
auto* dy = ctx.Output<Tensor>(framework::GradVarName("Y"));
|
|
int axis = ctx.Attr<int>("axis");
|
|
ElemwiseGradCompute<DeviceContext, T, SubGradDX<T>, SubGradDY<T>>(
|
|
ctx, *x, *y, *out, *dout, axis, dx, dy, SubGradDX<T>(), SubGradDY<T>());
|
|
}
|
|
};
|
|
} // namespace operators
|
|
} // namespace paddle
|