From d211b51bd412a521898ba02edd1764e4fd279b0d Mon Sep 17 00:00:00 2001 From: Yancey1989 Date: Tue, 10 Oct 2017 12:26:56 +0800 Subject: [PATCH] update comment --- paddle/operators/sequence_concat_op.cc | 49 +++++++++++-------- paddle/operators/sequence_concat_op.h | 28 +++-------- .../v2/framework/tests/test_seq_concat_op.py | 40 +++++++++++---- 3 files changed, 67 insertions(+), 50 deletions(-) diff --git a/paddle/operators/sequence_concat_op.cc b/paddle/operators/sequence_concat_op.cc index d385e47b6c6..eedf5315b4d 100644 --- a/paddle/operators/sequence_concat_op.cc +++ b/paddle/operators/sequence_concat_op.cc @@ -48,11 +48,11 @@ class SequenceConcatOpMaker : public framework::OpProtoAndCheckerMaker { framework::OpAttrChecker* op_checker) : OpProtoAndCheckerMaker(proto, op_checker) { AddInput("X", - "The input Multip LoDTensors, which are variable-length " - "sequence or nested sequence.") + "(A vector of LoDTensor), the input is a vector of LoDTensor, " + "each of which is a variable-length sequence or nested sequence.") .AsDuplicable(); AddOutput("Out", - "A LoDTensor, the variable-length output of " + "(A LoDTensor), the variable-length output of " "sequence_concat Op."); AddAttr("axis", "(int, default 0)" @@ -61,27 +61,36 @@ class SequenceConcatOpMaker : public framework::OpProtoAndCheckerMaker { .SetDefault(0); AddAttr("level", "(int, default 0)" - "The level which the inputs will be joined with." - "If level is 0, the inputs will be joined with " - "nested sequences." - "If level is 1, the inputs will be joined with sequences.") + "The level at which the inputs will be joined." + "If the level is 0, the inputs will be joined at the nested " + "sequence level." + "If the level is 1, the inputs will be joined at the " + "sequence level.") .SetDefault(0); AddComment(R"DOC( The sequence_concat operator concatenates multiple LoDTensors. - It only supports sequences ( LoD Tensor with level=1) - or nested sequences (LoD tensor with level=0) as its inputs. + It only supports sequence (LoD Tensor with level number is 1) + or a nested sequence (LoD tensor with level number is 2) as its input. - Case1: - If the axis is 1, level is 1, the LoD of Inputs are the same, - LoD(x0) = {{0,2,4},{0,1,2,3,4}}; Dims(x0) = (2,3,4) - LoD(x1) = {{0,2,4},{0,1,2,3,4}}; Dims(x1) = (2,4,4) - LoD(Out) = {{0,2,4},{0,1,2,3,4}}; Dims(Out) = (2,7,4) + If the axis is other than 0(here, axis is 1 and level is 1), + each input should have the same LoD information and the LoD + information of the output keeps the same as the input. + LoD(x0) = {{0,2,4}, {0,1,2,3,4}}; Dims(x0) = (4,3,4) + LoD(x1) = {{0,2,4}, {0,1,2,3,4}}; Dims(x1) = (4,4,4) + LoD(Out) = {{0,2,4}, {0,1,2,3,4}}; Dims(Out) = (4,7,4) - Case2: - If the axis is 0, level is 1, the LoD of inputs are different, - LoD(x0) = {{0,2,4}, {0,1,2,3,4}}; Dims(x0) = (2,3,4) - LoD(x1) = {{0,3,5}, {0,1,3,4,5}}; Dims(x1) = (3,3,4) - LoD(Out) = {{0,5,9}, {0,1,2,4,5,6,7,8,9}}; Dims(Out) = (5,3,4) - - NOTE: The level of all the inputs should be the same. + If the axis is 0(here, leve is 0), the inputs are concatenated along + time steps, the LoD information of the output need to re-compute. + LoD(x0) = {{0,2,4}, {0,1,2,3,4}}; Dims(x0) = (4,3,4) + LoD(x1) = {{0,3,5}, {0,1,2,3,5}}; Dims(x1) = (5,3,4) + LoD(Out) = {{0,5,9}, {0,1,2,3,4,5,6,7,9}}; Dims(Out) = (9,3,4) + - Case3: + If the axis is 0(here, level is 1). + LoD(x0) = {{0,2,4}, {0,1,2,3,4}}; Dims(x0) = (4,3,4) + LoD(x1) = {{0,3,5}, {0,1,3,4,5}}; Dims(x1) = (5,3,4) + LoD(Out) = {{0,5,9}, {0,2,5,7,9}}; Dims(Out) = (9,3,4) + + NOTE: The levels of all the inputs should be the same. )DOC"); } }; @@ -95,7 +104,7 @@ class SequenceConcatGradOp : public framework::OperatorWithKernel { PADDLE_ENFORCE(ctx->HasInput(framework::GradVarName("Out")), "The gradient of Out should not be null."); PADDLE_ENFORCE(ctx->HasOutputs(framework::GradVarName("X")), - "The gradient of X should not be empty."); + "The gradient of X should not be null."); ctx->SetOutputsDim(framework::GradVarName("X"), ctx->GetInputsDim("X")); } }; diff --git a/paddle/operators/sequence_concat_op.h b/paddle/operators/sequence_concat_op.h index 7f9c91b3c8d..dcd98be7ee0 100644 --- a/paddle/operators/sequence_concat_op.h +++ b/paddle/operators/sequence_concat_op.h @@ -23,35 +23,22 @@ using Tensor = framework::Tensor; using LoDTensor = framework::LoDTensor; using LoD = framework::LoD; -// Concat LoD, the initialized LoD of Output is lod(x0), -// if axis is not 0, the LoD(Out) will be the same as Inputs, if axis is 0: -// Case1: -// There is one level, the Output LoD will be modified: -// LoD(x0) = {{0,2,4}} -// LoD(x1) = {{0,1,5}} -// LoD(Out) = {{0,3,9}} -// Case2: -// There is two level, and concat level is 1, -// the Output LoD will be modified as followed: -// LoD(x0) = {{0,2,4}, {0,1,2,3,4}} -// LoD(x1) = {{0,3,5}, {0,1,3,4,5}} -// LoD(Out) = {{0,5,9}, {0,1,2,4,5,6,7,8,9}} template LoD concatLoD(const std::vector ins, const size_t axis, const size_t level) { auto out_lod = ins[0]->lod(); const size_t n = ins.size(); if (axis == 0UL) { - if (level == 0) { + if (level == 0UL) { for (size_t i = 1; i < n; ++i) { for (size_t j = 0; j < ins[i]->lod()[0].size(); ++j) { out_lod[0][j] += ins[i]->lod()[0][j]; } } - } else if (level == 1) { + } else if (level == 1UL) { PADDLE_ENFORCE_EQ(ins[0]->NumLevels(), 2UL, "If the level is 1, all of the inputs " - "should be the the nested sequence."); + "should be the nested sequence."); for (size_t i = 1; i < n; ++i) { for (size_t j = 0; j < ins[i]->lod()[0].size(); ++j) { out_lod[0].push_back(ins[i]->lod()[0][j]); @@ -80,16 +67,17 @@ class SequenceConcatOpKernel : public framework::OpKernel { "The level number of all the input LoDTensors " "should be the same."); PADDLE_ENFORCE_EQ(ins[0]->dims().size(), ins[i]->dims().size(), - "The dimensions size of all the input LoDTensors " + "The dimension size of all the input LoDTensors " "should be the same."); const size_t dims_size = ins[i]->dims().size(); for (size_t j = 0; j < dims_size; ++j) { if (j == axis) continue; PADDLE_ENFORCE_EQ(ins[0]->dims()[j], ins[i]->dims()[j], - "The dimensions of all the input LoDTensors " - "except for the specify axis should be " - "matched exactly."); + "Except for the dimension of the specified " + "axis along which all the inputs are concatenated, " + "dimensions of all the other axises of the input " + "LoDTensors should be the same."); } } diff --git a/python/paddle/v2/framework/tests/test_seq_concat_op.py b/python/paddle/v2/framework/tests/test_seq_concat_op.py index 3d40d82ae7b..6309b09bc98 100644 --- a/python/paddle/v2/framework/tests/test_seq_concat_op.py +++ b/python/paddle/v2/framework/tests/test_seq_concat_op.py @@ -6,16 +6,16 @@ from op_test import OpTest class TestConcatOp(OpTest): def set_data(self): # two level, batch size is 3 - x0 = np.random.random((11, 6, 3)).astype('float32') - lod0 = [[0, 2, 5, 11], [0, 1, 2, 5, 7, 11]] - x1 = np.random.random((11, 8, 3)).astype('float32') - lod1 = [[0, 2, 5, 11], [0, 1, 2, 5, 7, 11]] + x0 = np.random.random((4, 6, 3)).astype('float32') + lod0 = [[0, 2, 4], [0, 1, 2, 3, 4]] + x1 = np.random.random((4, 8, 3)).astype('float32') + lod1 = [[0, 2, 4], [0, 1, 2, 3, 4]] axis = 1 level = 1 self.inputs = {'X': [('x0', (x0, lod0)), ('x1', (x1, lod1))]} self.attrs = {'axis': axis, 'level': level} outs = [] - for i in range(5): + for i in range(4): sub_x0 = x0[lod0[level][i]:lod0[level][i + 1], :] sub_x1 = x1[lod1[level][i]:lod1[level][i + 1], :] outs.append(np.concatenate((sub_x0, sub_x1), axis=axis)) @@ -36,16 +36,36 @@ class TestConcatOp(OpTest): class TestConcatOpDiffLod(TestConcatOp): def set_data(self): # two level, batch size is 3 - x0 = np.random.random((12, 6, 3)).astype('float32') - lod0 = [[0, 3, 9, 12], [0, 2, 3, 5, 9, 12]] - x1 = np.random.random((11, 6, 3)).astype('float32') - lod1 = [[0, 2, 5, 11], [0, 1, 2, 5, 7, 11]] + x0 = np.random.random((4, 6, 3)).astype('float32') + lod0 = [[0, 2, 4], [0, 1, 2, 3, 4]] + x1 = np.random.random((5, 6, 3)).astype('float32') + lod1 = [[0, 3, 5], [0, 1, 2, 3, 5]] axis = 0 level = 1 self.inputs = {'X': [('x0', (x0, lod0)), ('x1', (x1, lod1))]} self.attrs = {'axis': axis, 'level': level} outs = [] - for i in range(5): + for i in range(4): + sub_x0 = x0[lod0[level][i]:lod0[level][i + 1], :] + sub_x1 = x1[lod1[level][i]:lod1[level][i + 1], :] + outs.append(np.concatenate((sub_x0, sub_x1), axis=axis)) + + self.outputs = {'Out': np.concatenate(outs, axis=0)} + + +class TestConcatOpLevelZero(TestConcatOp): + def set_data(self): + # two level, batch size is 3 + x0 = np.random.random((4, 3, 4)).astype('float32') + lod0 = [[0, 2, 4], [0, 1, 2, 3, 4]] + x1 = np.random.random((5, 3, 4)).astype('float32') + lod1 = [[0, 3, 5], [0, 1, 3, 4, 5]] + axis = 0 + level = 0 + self.inputs = {'X': [('x0', (x0, lod0)), ('x1', (x1, lod1))]} + self.attrs = {'axis': axis, 'level': level} + outs = [] + for i in range(2): sub_x0 = x0[lod0[level][i]:lod0[level][i + 1], :] sub_x1 = x1[lod1[level][i]:lod1[level][i + 1], :] outs.append(np.concatenate((sub_x0, sub_x1), axis=axis)) -- GitLab