Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into dev_add_axis
fengjiayi
8 years ago
commit
823bdd670f
File diff suppressed because it is too large
Load Diff
@ -0,0 +1,107 @@
|
|||||||
|
/* Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserve.
|
||||||
|
|
||||||
|
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. */
|
||||||
|
|
||||||
|
#include "paddle/operators/cos_sim_op.h"
|
||||||
|
|
||||||
|
namespace paddle {
|
||||||
|
namespace operators {
|
||||||
|
|
||||||
|
using framework::Tensor;
|
||||||
|
|
||||||
|
class CosSimOp : public framework::OperatorWithKernel {
|
||||||
|
public:
|
||||||
|
using framework::OperatorWithKernel::OperatorWithKernel;
|
||||||
|
|
||||||
|
protected:
|
||||||
|
void InferShape(const framework::InferShapeContext &ctx) const override {
|
||||||
|
PADDLE_ENFORCE_NOT_NULL(ctx.InputVar("X"), "Input(X) must not be null.");
|
||||||
|
PADDLE_ENFORCE_NOT_NULL(ctx.InputVar("Y"), "Input(Y) must not be null.");
|
||||||
|
PADDLE_ENFORCE_EQ(ctx.Input<Tensor>("X")->dims(),
|
||||||
|
ctx.Input<Tensor>("Y")->dims(),
|
||||||
|
"Dimensions of Input(X) and Input(Y) must be the same.");
|
||||||
|
|
||||||
|
auto dims = ctx.Input<Tensor>("X")->dims();
|
||||||
|
ctx.Output<Tensor>("Out")->Resize({dims[0], 1});
|
||||||
|
ctx.Output<Tensor>("XNorm")->Resize({dims[0], 1});
|
||||||
|
ctx.Output<Tensor>("YNorm")->Resize({dims[0], 1});
|
||||||
|
}
|
||||||
|
};
|
||||||
|
|
||||||
|
class CosSimOpMaker : public framework::OpProtoAndCheckerMaker {
|
||||||
|
public:
|
||||||
|
CosSimOpMaker(framework::OpProto *proto, framework::OpAttrChecker *op_checker)
|
||||||
|
: OpProtoAndCheckerMaker(proto, op_checker) {
|
||||||
|
AddInput("X", "The first input of cos_sim op.");
|
||||||
|
AddInput("Y", "The second input of cos_sim op.");
|
||||||
|
AddOutput("Out", "The output of cos_sim op.");
|
||||||
|
AddOutput("XNorm", "Row norm of the first input.").AsIntermediate();
|
||||||
|
AddOutput("YNorm", "Row norm of the second input.").AsIntermediate();
|
||||||
|
|
||||||
|
AddComment(R"DOC(
|
||||||
|
Cosine Similarity Operator.
|
||||||
|
|
||||||
|
The equation is: Out = X^T * Y / (sqrt(X^T * X) * sqrt(Y^T * Y))
|
||||||
|
)DOC");
|
||||||
|
}
|
||||||
|
};
|
||||||
|
|
||||||
|
class CosSimOpGrad : public framework::OperatorWithKernel {
|
||||||
|
public:
|
||||||
|
using framework::OperatorWithKernel::OperatorWithKernel;
|
||||||
|
|
||||||
|
protected:
|
||||||
|
void InferShape(const framework::InferShapeContext &ctx) const override {
|
||||||
|
PADDLE_ENFORCE_NOT_NULL(ctx.InputVar("X"), "Input(X) must not be null.");
|
||||||
|
PADDLE_ENFORCE_NOT_NULL(ctx.InputVar("Y"), "Input(Y) must not be null.");
|
||||||
|
PADDLE_ENFORCE_NOT_NULL(ctx.InputVar("XNorm"),
|
||||||
|
"Input(XNorm) must not be null.");
|
||||||
|
PADDLE_ENFORCE_NOT_NULL(ctx.InputVar("YNorm"),
|
||||||
|
"Input(YNorm) must not be null.");
|
||||||
|
PADDLE_ENFORCE_NOT_NULL(ctx.InputVar(framework::GradVarName("Out")),
|
||||||
|
"Input(Out@GRAD) must not be null.");
|
||||||
|
|
||||||
|
auto x_dims = ctx.Input<Tensor>("X")->dims();
|
||||||
|
auto y_dims = ctx.Input<Tensor>("Y")->dims();
|
||||||
|
auto xnorm_dims = ctx.Input<Tensor>("XNorm")->dims();
|
||||||
|
auto ynorm_dims = ctx.Input<Tensor>("YNorm")->dims();
|
||||||
|
auto out_dims = ctx.Input<Tensor>(framework::GradVarName("Out"))->dims();
|
||||||
|
PADDLE_ENFORCE_EQ(x_dims, y_dims,
|
||||||
|
"Dimensions of Input(X) and Input(Y) must be the same.");
|
||||||
|
PADDLE_ENFORCE_EQ(xnorm_dims[0], x_dims[0],
|
||||||
|
"1st dimension of XNorm must equal that of Input(X).");
|
||||||
|
PADDLE_ENFORCE_EQ(xnorm_dims[1], 1, "2st dimension of XNorm must be one.");
|
||||||
|
PADDLE_ENFORCE_EQ(ynorm_dims[0], y_dims[0],
|
||||||
|
"1st dimension of YNorm must equal that of Input(Y).");
|
||||||
|
PADDLE_ENFORCE_EQ(ynorm_dims[1], 1, "2st dimension of YNorm must be one.");
|
||||||
|
PADDLE_ENFORCE_EQ(out_dims[0], x_dims[0],
|
||||||
|
"1st dimension of Out@GRAD must equal that of Input(X)");
|
||||||
|
PADDLE_ENFORCE_EQ(out_dims[1], 1, "1st dimension of Out@GRAD must be one.");
|
||||||
|
|
||||||
|
auto *x_grad = ctx.Output<Tensor>(framework::GradVarName("X"));
|
||||||
|
auto *y_grad = ctx.Output<Tensor>(framework::GradVarName("Y"));
|
||||||
|
if (x_grad) x_grad->Resize(x_dims);
|
||||||
|
if (y_grad) y_grad->Resize(y_dims);
|
||||||
|
}
|
||||||
|
};
|
||||||
|
|
||||||
|
} // namespace operators
|
||||||
|
} // namespace paddle
|
||||||
|
|
||||||
|
namespace ops = paddle::operators;
|
||||||
|
REGISTER_OP(cos_sim, ops::CosSimOp, ops::CosSimOpMaker, cos_sim_grad,
|
||||||
|
ops::CosSimOpGrad);
|
||||||
|
REGISTER_OP_CPU_KERNEL(cos_sim,
|
||||||
|
ops::CosSimKernel<paddle::platform::CPUPlace, float>);
|
||||||
|
REGISTER_OP_CPU_KERNEL(
|
||||||
|
cos_sim_grad, ops::CosSimGradKernel<paddle::platform::CPUPlace, float>);
|
||||||
@ -0,0 +1,107 @@
|
|||||||
|
/* Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserve.
|
||||||
|
|
||||||
|
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/framework/eigen.h"
|
||||||
|
#include "paddle/framework/op_registry.h"
|
||||||
|
|
||||||
|
namespace paddle {
|
||||||
|
namespace operators {
|
||||||
|
|
||||||
|
using Tensor = framework::Tensor;
|
||||||
|
template <typename T, int MajorType = Eigen::RowMajor,
|
||||||
|
typename IndexType = Eigen::DenseIndex>
|
||||||
|
using EigenMatrix = framework::EigenMatrix<T, MajorType, IndexType>;
|
||||||
|
template <typename T, int MajorType = Eigen::RowMajor,
|
||||||
|
typename IndexType = Eigen::DenseIndex>
|
||||||
|
using EigenVector = framework::EigenVector<T, MajorType, IndexType>;
|
||||||
|
|
||||||
|
template <typename Place, typename T>
|
||||||
|
class CosSimKernel : public framework::OpKernel {
|
||||||
|
public:
|
||||||
|
void Compute(const framework::ExecutionContext& context) const override {
|
||||||
|
auto* input_x = context.Input<Tensor>("X");
|
||||||
|
auto* input_y = context.Input<Tensor>("Y");
|
||||||
|
auto* output_z = context.Output<Tensor>("Out");
|
||||||
|
auto* output_x_norm = context.Output<Tensor>("XNorm");
|
||||||
|
auto* output_y_norm = context.Output<Tensor>("YNorm");
|
||||||
|
|
||||||
|
output_z->mutable_data<T>(context.GetPlace());
|
||||||
|
output_x_norm->mutable_data<T>(context.GetPlace());
|
||||||
|
output_y_norm->mutable_data<T>(context.GetPlace());
|
||||||
|
|
||||||
|
auto dims = input_x->dims();
|
||||||
|
int size = static_cast<int>(framework::product(dims));
|
||||||
|
auto new_dims = framework::make_ddim({dims[0], size / dims[0]});
|
||||||
|
auto x = EigenMatrix<T>::From(*input_x, new_dims);
|
||||||
|
auto y = EigenMatrix<T>::From(*input_y, new_dims);
|
||||||
|
auto z = EigenVector<T>::Flatten(*output_z);
|
||||||
|
auto x_norm = EigenVector<T>::Flatten(*output_x_norm);
|
||||||
|
auto y_norm = EigenVector<T>::Flatten(*output_y_norm);
|
||||||
|
|
||||||
|
auto place = context.GetEigenDevice<Place>();
|
||||||
|
auto xy = (x * y).sum(Eigen::array<int, 1>({{1}}));
|
||||||
|
x_norm.device(place) = x.square().sum(Eigen::array<int, 1>({{1}})).sqrt();
|
||||||
|
y_norm.device(place) = y.square().sum(Eigen::array<int, 1>({{1}})).sqrt();
|
||||||
|
z.device(place) = xy / x_norm / y_norm;
|
||||||
|
}
|
||||||
|
};
|
||||||
|
|
||||||
|
template <typename Place, typename T>
|
||||||
|
class CosSimGradKernel : public framework::OpKernel {
|
||||||
|
public:
|
||||||
|
void Compute(const framework::ExecutionContext& context) const override {
|
||||||
|
auto* input_x = context.Input<Tensor>("X");
|
||||||
|
auto* input_y = context.Input<Tensor>("Y");
|
||||||
|
auto* input_z = context.Input<Tensor>("Out");
|
||||||
|
auto* input_x_norm = context.Input<Tensor>("XNorm");
|
||||||
|
auto* input_y_norm = context.Input<Tensor>("YNorm");
|
||||||
|
auto* output_grad_x = context.Output<Tensor>(framework::GradVarName("X"));
|
||||||
|
auto* output_grad_y = context.Output<Tensor>(framework::GradVarName("Y"));
|
||||||
|
auto* input_grad_z = context.Input<Tensor>(framework::GradVarName("Out"));
|
||||||
|
|
||||||
|
auto dims = input_x->dims();
|
||||||
|
int size = static_cast<int>(framework::product(dims));
|
||||||
|
auto new_dims = framework::make_ddim({dims[0], size / dims[0]});
|
||||||
|
auto x = EigenMatrix<T>::From(*input_x, new_dims);
|
||||||
|
auto y = EigenMatrix<T>::From(*input_y, new_dims);
|
||||||
|
auto z = EigenMatrix<T>::From(*input_z);
|
||||||
|
auto x_norm = EigenMatrix<T>::From(*input_x_norm);
|
||||||
|
auto y_norm = EigenMatrix<T>::From(*input_y_norm);
|
||||||
|
auto dz = EigenMatrix<T>::From(*input_grad_z);
|
||||||
|
|
||||||
|
Eigen::DSizes<int, 2> bcast(1, new_dims[1]);
|
||||||
|
auto z_bcast = z.broadcast(bcast);
|
||||||
|
auto dz_bcast = dz.broadcast(bcast);
|
||||||
|
auto place = context.GetEigenDevice<Place>();
|
||||||
|
auto x_snorm_bcast = x_norm.square().eval().broadcast(bcast);
|
||||||
|
auto y_snorm_bcast = y_norm.square().eval().broadcast(bcast);
|
||||||
|
auto norm_prod_bcast = (x_norm * y_norm).eval().broadcast(bcast);
|
||||||
|
if (output_grad_x) {
|
||||||
|
output_grad_x->mutable_data<T>(context.GetPlace());
|
||||||
|
auto dx = EigenMatrix<T>::From(*output_grad_x, new_dims);
|
||||||
|
dx.device(place) =
|
||||||
|
dz_bcast * (y / norm_prod_bcast - z_bcast * x / x_snorm_bcast);
|
||||||
|
}
|
||||||
|
if (output_grad_y) {
|
||||||
|
output_grad_y->mutable_data<T>(context.GetPlace());
|
||||||
|
auto dy = EigenMatrix<T>::From(*output_grad_y, new_dims);
|
||||||
|
dy.device(place) =
|
||||||
|
dz_bcast * (x / norm_prod_bcast - z_bcast * y / y_snorm_bcast);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
};
|
||||||
|
|
||||||
|
} // namespace operators
|
||||||
|
} // namespace paddle
|
||||||
@ -0,0 +1,54 @@
|
|||||||
|
/* Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserve.
|
||||||
|
|
||||||
|
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. */
|
||||||
|
|
||||||
|
#include "paddle/operators/net_op.h"
|
||||||
|
#include "paddle/operators/scale_op.h"
|
||||||
|
|
||||||
|
namespace paddle {
|
||||||
|
namespace operators {
|
||||||
|
|
||||||
|
// identity is a alias of scale op. This is also a example for creating a alias
|
||||||
|
// operator.
|
||||||
|
template <typename AttrType>
|
||||||
|
class IdentityOpMaker : public framework::OpProtoAndCheckerMaker {
|
||||||
|
public:
|
||||||
|
IdentityOpMaker(framework::OpProto *proto,
|
||||||
|
framework::OpAttrChecker *op_checker)
|
||||||
|
: OpProtoAndCheckerMaker(proto, op_checker) {
|
||||||
|
AddInput("X", "input tensor of identity op");
|
||||||
|
AddOutput("Out", "output tensor of identity op");
|
||||||
|
AddComment("identity operator. Just a alias of scale op which scale = 1.0");
|
||||||
|
}
|
||||||
|
};
|
||||||
|
|
||||||
|
template <typename AttrType>
|
||||||
|
class IdentityOp : public NetOp {
|
||||||
|
public:
|
||||||
|
IdentityOp(const std::string &type, const framework::VariableNameMap &inputs,
|
||||||
|
const framework::VariableNameMap &outputs,
|
||||||
|
const framework::AttributeMap &attrs)
|
||||||
|
: NetOp(type, inputs, outputs, attrs) {
|
||||||
|
AppendOp(framework::OpRegistry::CreateOp(
|
||||||
|
"scale", {{"X", {Input("X")}}}, {{"Out", {Output("Out")}}},
|
||||||
|
{{"scale", static_cast<AttrType>(1)}}));
|
||||||
|
}
|
||||||
|
};
|
||||||
|
|
||||||
|
} // namespace operators
|
||||||
|
} // namespace paddle
|
||||||
|
|
||||||
|
namespace ops = paddle::operators;
|
||||||
|
|
||||||
|
REGISTER_OP_WITHOUT_GRADIENT(identity, ops::IdentityOp<float>,
|
||||||
|
ops::IdentityOpMaker<float>);
|
||||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in new issue