From 842b485f6a15e0ddba7ff345cb17d440cc950374 Mon Sep 17 00:00:00 2001 From: guosheng Date: Wed, 13 Dec 2017 17:09:15 +0800 Subject: [PATCH] Enhance ReduceOp to support reducing over all elements --- paddle/operators/reduce_op.cc | 32 +++-- paddle/operators/reduce_op.h | 119 ++++++++++++------ .../paddle/v2/fluid/tests/test_reduce_op.py | 14 +++ 3 files changed, 113 insertions(+), 52 deletions(-) diff --git a/paddle/operators/reduce_op.cc b/paddle/operators/reduce_op.cc index b754637bf2..fedc2a5c37 100644 --- a/paddle/operators/reduce_op.cc +++ b/paddle/operators/reduce_op.cc @@ -37,18 +37,23 @@ class ReduceOp : public framework::OperatorWithKernel { PADDLE_ENFORCE_LT( dim, x_rank, "The dim should be in the range [-rank(input), rank(input))."); - bool keep_dim = ctx->Attrs().Get("keep_dim"); - auto dims_vector = vectorize(x_dims); - if (keep_dim || x_rank == 1) { - dims_vector[dim] = 1; + bool reduce_all = ctx->Attrs().Get("reduce_all"); + if (reduce_all) { + ctx->SetOutputDim("Out", {1}); } else { - dims_vector.erase(dims_vector.begin() + dim); - } - auto out_dims = framework::make_ddim(dims_vector); - ctx->SetOutputDim("Out", out_dims); - if (dim != 0) { - // Only pass LoD when not reducing on the first dim. - ctx->ShareLoD("X", /*->*/ "Out"); + bool keep_dim = ctx->Attrs().Get("keep_dim"); + auto dims_vector = vectorize(x_dims); + if (keep_dim || x_rank == 1) { + dims_vector[dim] = 1; + } else { + dims_vector.erase(dims_vector.begin() + dim); + } + auto out_dims = framework::make_ddim(dims_vector); + ctx->SetOutputDim("Out", out_dims); + if (dim != 0) { + // Only pass LoD when not reducing on the first dim. + ctx->ShareLoD("X", /*->*/ "Out"); + } } } }; @@ -95,11 +100,16 @@ class ReduceOpMaker : public framework::OpProtoAndCheckerMaker { "(bool, default false) " "If true, retain the reduced dimension with length 1.") .SetDefault(false); + AddAttr("reduce_all", + "(bool, default false) " + "If true, output a scalar reduced along all dimensions.") + .SetDefault(false); comment_ = R"DOC( {ReduceOp} Operator. This operator computes the {reduce} of input tensor along the given dimension. The result tensor has 1 fewer dimension than the input unless keep_dim is true. +If reduce_all is true, just reduce along all dimensions and output a scalar. )DOC"; AddComment(comment_); diff --git a/paddle/operators/reduce_op.h b/paddle/operators/reduce_op.h index 47ce910f28..7bd99cb1e6 100644 --- a/paddle/operators/reduce_op.h +++ b/paddle/operators/reduce_op.h @@ -26,10 +26,12 @@ using DDim = framework::DDim; template using EigenTensor = framework::EigenTensor; - template using EigenScalar = framework::EigenScalar; +template +using EigenVector = framework::EigenVector; struct SumFunctor { template @@ -95,26 +97,41 @@ template class ReduceKernel : public framework::OpKernel { public: void Compute(const framework::ExecutionContext& context) const override { - int rank = context.Input("X")->dims().size(); - switch (rank) { - case 1: - ReduceCompute<1>(context); - break; - case 2: - ReduceCompute<2>(context); - break; - case 3: - ReduceCompute<3>(context); - break; - case 4: - ReduceCompute<4>(context); - break; - case 5: - ReduceCompute<5>(context); - break; - case 6: - ReduceCompute<6>(context); - break; + bool reduce_all = context.Attr("reduce_all"); + if (reduce_all) { + // Flatten and reduce 1-D tensor + auto* input = context.Input("X"); + auto* output = context.Output("Out"); + output->mutable_data(context.GetPlace()); + auto x = EigenVector::Flatten(*input); + auto out = EigenScalar::From(*output); + auto& place = + *context.template device_context().eigen_device(); + auto reduce_dim = Eigen::array({{0}}); + Functor functor; + functor(place, x, out, reduce_dim); + } else { + int rank = context.Input("X")->dims().size(); + switch (rank) { + case 1: + ReduceCompute<1>(context); + break; + case 2: + ReduceCompute<2>(context); + break; + case 3: + ReduceCompute<3>(context); + break; + case 4: + ReduceCompute<4>(context); + break; + case 5: + ReduceCompute<5>(context); + break; + case 6: + ReduceCompute<6>(context); + break; + } } } @@ -157,26 +174,46 @@ template class ReduceGradKernel : public framework::OpKernel { public: void Compute(const framework::ExecutionContext& context) const override { - int rank = context.Input("X")->dims().size(); - switch (rank) { - case 1: - ReduceGradCompute<1>(context); - break; - case 2: - ReduceGradCompute<2>(context); - break; - case 3: - ReduceGradCompute<3>(context); - break; - case 4: - ReduceGradCompute<4>(context); - break; - case 5: - ReduceGradCompute<5>(context); - break; - case 6: - ReduceGradCompute<6>(context); - break; + bool reduce_all = context.Attr("reduce_all"); + if (reduce_all) { + auto* input0 = context.Input("X"); + auto* input1 = context.Input("Out"); + auto* input2 = context.Input(framework::GradVarName("Out")); + auto* output = context.Output(framework::GradVarName("X")); + output->mutable_data(context.GetPlace()); + auto x = EigenVector::Flatten(*input0); + auto x_reduce = EigenVector::From(*input1); + auto x_reduce_grad = EigenVector::From(*input2); + auto x_grad = EigenVector::Flatten(*output); + auto& place = + *context.template device_context().eigen_device(); + auto broadcast_dim = + Eigen::array({{static_cast(input0->numel())}}); + Functor functor; + functor(place, x, x_reduce, x_grad, x_reduce_grad, broadcast_dim, + broadcast_dim[0]); + } else { + int rank = context.Input("X")->dims().size(); + switch (rank) { + case 1: + ReduceGradCompute<1>(context); + break; + case 2: + ReduceGradCompute<2>(context); + break; + case 3: + ReduceGradCompute<3>(context); + break; + case 4: + ReduceGradCompute<4>(context); + break; + case 5: + ReduceGradCompute<5>(context); + break; + case 6: + ReduceGradCompute<6>(context); + break; + } } } diff --git a/python/paddle/v2/fluid/tests/test_reduce_op.py b/python/paddle/v2/fluid/tests/test_reduce_op.py index 70359d60cb..a021d4dd91 100644 --- a/python/paddle/v2/fluid/tests/test_reduce_op.py +++ b/python/paddle/v2/fluid/tests/test_reduce_op.py @@ -85,5 +85,19 @@ class Test1DReduce(OpTest): self.check_grad(['X'], 'Out') +class TestReduceAll(OpTest): + def setUp(self): + self.op_type = "reduce_sum" + self.inputs = {'X': np.random.random((5, 6, 2, 10)).astype("float32")} + self.attrs = {'reduce_all': True} + self.outputs = {'Out': self.inputs['X'].sum()} + + def test_check_output(self): + self.check_output() + + def test_check_grad(self): + self.check_grad(['X'], 'Out') + + if __name__ == '__main__': unittest.main() -- GitLab