From da7c0f1326677ec7c22b6cdbd6595e2f4a1d59a2 Mon Sep 17 00:00:00 2001 From: Yu Yang Date: Wed, 23 Nov 2016 17:41:20 +0800 Subject: [PATCH] Format sequence_nest_rnn_multi_unequalength*.conf --- ...ce_nest_rnn_multi_unequalength_inputs.conf | 106 ----------------- ...ence_nest_rnn_multi_unequalength_inputs.py | 107 ++++++++++++++++++ ...sequence_rnn_multi_unequalength_inputs.py} | 68 +++++------ .../tests/test_RecurrentGradientMachine.cpp | 19 ++-- 4 files changed, 151 insertions(+), 149 deletions(-) delete mode 100644 paddle/gserver/tests/sequence_nest_rnn_multi_unequalength_inputs.conf create mode 100644 paddle/gserver/tests/sequence_nest_rnn_multi_unequalength_inputs.py rename paddle/gserver/tests/{sequence_rnn_multi_unequalength_inputs.conf => sequence_rnn_multi_unequalength_inputs.py} (52%) diff --git a/paddle/gserver/tests/sequence_nest_rnn_multi_unequalength_inputs.conf b/paddle/gserver/tests/sequence_nest_rnn_multi_unequalength_inputs.conf deleted file mode 100644 index d0b9450f4b9..00000000000 --- a/paddle/gserver/tests/sequence_nest_rnn_multi_unequalength_inputs.conf +++ /dev/null @@ -1,106 +0,0 @@ -#edit-mode: -*- python -*- -# Copyright (c) 2016 Baidu, Inc. 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. - -from paddle.trainer_config_helpers import * - -######################## data source ################################ -define_py_data_sources2(train_list='gserver/tests/Sequence/dummy.list', - test_list=None, - module='rnn_data_provider', - obj='process_unequalength_subseq') - - -settings(batch_size=2, learning_rate=0.01) -######################## network configure ################################ -dict_dim = 10 -word_dim = 8 -hidden_dim = 8 -label_dim = 2 - -speaker1 = data_layer(name="word1", size=dict_dim) -speaker2 = data_layer(name="word2", size=dict_dim) - -emb1 = embedding_layer(input=speaker1, size=word_dim) -emb2 = embedding_layer(input=speaker2, size=word_dim) - -# This hierachical RNN is designed to be equivalent to the simple RNN in -# sequence_rnn_multi_unequalength_inputs.conf - -def outer_step(x1, x2): - outer_mem1 = memory(name = "outer_rnn_state1", size = hidden_dim) - outer_mem2 = memory(name = "outer_rnn_state2", size = hidden_dim) - def inner_step1(y): - inner_mem = memory(name = 'inner_rnn_state_' + y.name, - size = hidden_dim, - boot_layer = outer_mem1) - out = fc_layer(input = [y, inner_mem], - size = hidden_dim, - act = TanhActivation(), - bias_attr = True, - name = 'inner_rnn_state_' + y.name) - return out - - def inner_step2(y): - inner_mem = memory(name = 'inner_rnn_state_' + y.name, - size = hidden_dim, - boot_layer = outer_mem2) - out = fc_layer(input = [y, inner_mem], - size = hidden_dim, - act = TanhActivation(), - bias_attr = True, - name = 'inner_rnn_state_' + y.name) - return out - - encoder1 = recurrent_group( - step = inner_step1, - name = 'inner1', - input = x1) - - encoder2 = recurrent_group( - step = inner_step2, - name = 'inner2', - input = x2) - - sentence_last_state1 = last_seq(input = encoder1, name = 'outer_rnn_state1') - sentence_last_state2_ = last_seq(input = encoder2, name = 'outer_rnn_state2') - - encoder1_expand = expand_layer(input = sentence_last_state1, - expand_as = encoder2) - - return [encoder1_expand, encoder2] - - -encoder1_rep, encoder2_rep = recurrent_group( - name="outer", - step=outer_step, - input=[SubsequenceInput(emb1), SubsequenceInput(emb2)], - targetInlink=emb2) - -encoder1_last = last_seq(input = encoder1_rep) -encoder1_expandlast = expand_layer(input = encoder1_last, - expand_as = encoder2_rep) -context = mixed_layer(input = [identity_projection(encoder1_expandlast), - identity_projection(encoder2_rep)], - size = hidden_dim) - -rep = last_seq(input=context) -prob = fc_layer(size=label_dim, - input=rep, - act=SoftmaxActivation(), - bias_attr=True) - -outputs(classification_cost(input=prob, - label=data_layer(name="label", size=label_dim))) - diff --git a/paddle/gserver/tests/sequence_nest_rnn_multi_unequalength_inputs.py b/paddle/gserver/tests/sequence_nest_rnn_multi_unequalength_inputs.py new file mode 100644 index 00000000000..1b709a39c4b --- /dev/null +++ b/paddle/gserver/tests/sequence_nest_rnn_multi_unequalength_inputs.py @@ -0,0 +1,107 @@ +#edit-mode: -*- python -*- +# Copyright (c) 2016 Baidu, Inc. 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. + +from paddle.trainer_config_helpers import * + +######################## data source ################################ +define_py_data_sources2( + train_list='gserver/tests/Sequence/dummy.list', + test_list=None, + module='rnn_data_provider', + obj='process_unequalength_subseq') + +settings(batch_size=2, learning_rate=0.01) +######################## network configure ################################ +dict_dim = 10 +word_dim = 8 +hidden_dim = 8 +label_dim = 2 + +speaker1 = data_layer(name="word1", size=dict_dim) +speaker2 = data_layer(name="word2", size=dict_dim) + +emb1 = embedding_layer(input=speaker1, size=word_dim) +emb2 = embedding_layer(input=speaker2, size=word_dim) + +# This hierachical RNN is designed to be equivalent to the simple RNN in +# sequence_rnn_multi_unequalength_inputs.conf + + +def outer_step(x1, x2): + outer_mem1 = memory(name="outer_rnn_state1", size=hidden_dim) + outer_mem2 = memory(name="outer_rnn_state2", size=hidden_dim) + + def inner_step1(y): + inner_mem = memory( + name='inner_rnn_state_' + y.name, + size=hidden_dim, + boot_layer=outer_mem1) + out = fc_layer( + input=[y, inner_mem], + size=hidden_dim, + act=TanhActivation(), + bias_attr=True, + name='inner_rnn_state_' + y.name) + return out + + def inner_step2(y): + inner_mem = memory( + name='inner_rnn_state_' + y.name, + size=hidden_dim, + boot_layer=outer_mem2) + out = fc_layer( + input=[y, inner_mem], + size=hidden_dim, + act=TanhActivation(), + bias_attr=True, + name='inner_rnn_state_' + y.name) + return out + + encoder1 = recurrent_group(step=inner_step1, name='inner1', input=x1) + + encoder2 = recurrent_group(step=inner_step2, name='inner2', input=x2) + + sentence_last_state1 = last_seq(input=encoder1, name='outer_rnn_state1') + sentence_last_state2_ = last_seq(input=encoder2, name='outer_rnn_state2') + + encoder1_expand = expand_layer( + input=sentence_last_state1, expand_as=encoder2) + + return [encoder1_expand, encoder2] + + +encoder1_rep, encoder2_rep = recurrent_group( + name="outer", + step=outer_step, + input=[SubsequenceInput(emb1), SubsequenceInput(emb2)], + targetInlink=emb2) + +encoder1_last = last_seq(input=encoder1_rep) +encoder1_expandlast = expand_layer(input=encoder1_last, expand_as=encoder2_rep) +context = mixed_layer( + input=[ + identity_projection(encoder1_expandlast), + identity_projection(encoder2_rep) + ], + size=hidden_dim) + +rep = last_seq(input=context) +prob = fc_layer( + size=label_dim, input=rep, act=SoftmaxActivation(), bias_attr=True) + +outputs( + classification_cost( + input=prob, label=data_layer( + name="label", size=label_dim))) diff --git a/paddle/gserver/tests/sequence_rnn_multi_unequalength_inputs.conf b/paddle/gserver/tests/sequence_rnn_multi_unequalength_inputs.py similarity index 52% rename from paddle/gserver/tests/sequence_rnn_multi_unequalength_inputs.conf rename to paddle/gserver/tests/sequence_rnn_multi_unequalength_inputs.py index 28b1cb98cf1..4cf7035477c 100644 --- a/paddle/gserver/tests/sequence_rnn_multi_unequalength_inputs.conf +++ b/paddle/gserver/tests/sequence_rnn_multi_unequalength_inputs.py @@ -16,11 +16,11 @@ from paddle.trainer_config_helpers import * ######################## data source ################################ -define_py_data_sources2(train_list='gserver/tests/Sequence/dummy.list', - test_list=None, - module='rnn_data_provider', - obj='process_unequalength_seq') - +define_py_data_sources2( + train_list='gserver/tests/Sequence/dummy.list', + test_list=None, + module='rnn_data_provider', + obj='process_unequalength_seq') settings(batch_size=2, learning_rate=0.01) ######################## network configure ################################ @@ -38,38 +38,40 @@ emb2 = embedding_layer(input=speaker2, size=word_dim) # This hierachical RNN is designed to be equivalent to the RNN in # sequence_nest_rnn_multi_unequalength_inputs.conf + def step(x1, x2): - def calrnn(y): - mem = memory(name = 'rnn_state_' + y.name, size = hidden_dim) - out = fc_layer(input = [y, mem], - size = hidden_dim, - act = TanhActivation(), - bias_attr = True, - name = 'rnn_state_' + y.name) - return out - - encoder1 = calrnn(x1) - encoder2 = calrnn(x2) - return [encoder1, encoder2] + def calrnn(y): + mem = memory(name='rnn_state_' + y.name, size=hidden_dim) + out = fc_layer( + input=[y, mem], + size=hidden_dim, + act=TanhActivation(), + bias_attr=True, + name='rnn_state_' + y.name) + return out + + encoder1 = calrnn(x1) + encoder2 = calrnn(x2) + return [encoder1, encoder2] + encoder1_rep, encoder2_rep = recurrent_group( - name="stepout", - step=step, - input=[emb1, emb2]) + name="stepout", step=step, input=[emb1, emb2]) -encoder1_last = last_seq(input = encoder1_rep) -encoder1_expandlast = expand_layer(input = encoder1_last, - expand_as = encoder2_rep) -context = mixed_layer(input = [identity_projection(encoder1_expandlast), - identity_projection(encoder2_rep)], - size = hidden_dim) +encoder1_last = last_seq(input=encoder1_rep) +encoder1_expandlast = expand_layer(input=encoder1_last, expand_as=encoder2_rep) +context = mixed_layer( + input=[ + identity_projection(encoder1_expandlast), + identity_projection(encoder2_rep) + ], + size=hidden_dim) rep = last_seq(input=context) -prob = fc_layer(size=label_dim, - input=rep, - act=SoftmaxActivation(), - bias_attr=True) - -outputs(classification_cost(input=prob, - label=data_layer(name="label", size=label_dim))) +prob = fc_layer( + size=label_dim, input=rep, act=SoftmaxActivation(), bias_attr=True) +outputs( + classification_cost( + input=prob, label=data_layer( + name="label", size=label_dim))) diff --git a/paddle/gserver/tests/test_RecurrentGradientMachine.cpp b/paddle/gserver/tests/test_RecurrentGradientMachine.cpp index 80d713dac03..9d86067fb5a 100644 --- a/paddle/gserver/tests/test_RecurrentGradientMachine.cpp +++ b/paddle/gserver/tests/test_RecurrentGradientMachine.cpp @@ -13,12 +13,12 @@ See the License for the specific language governing permissions and limitations under the License. */ #include -#include -#include -#include +#include #include #include -#include +#include +#include +#include P_DECLARE_int32(seed); @@ -45,10 +45,9 @@ public: auto p = const_cast(this); auto& params = p->getGradientMachine()->getParameters(); return std::accumulate( - params.begin(), - params.end(), - 0UL, - [](size_t a, const ParameterPtr& p) { return a + p->getSize(); }); + params.begin(), params.end(), 0UL, [](size_t a, const ParameterPtr& p) { + return a + p->getSize(); + }); } }; @@ -148,8 +147,8 @@ TEST(RecurrentGradientMachine, rnn_multi_input) { TEST(RecurrentGradientMachine, rnn_multi_unequalength_input) { for (bool useGpu : {false, true}) { - test("gserver/tests/sequence_rnn_multi_unequalength_inputs.conf", - "gserver/tests/sequence_nest_rnn_multi_unequalength_inputs.conf", + test("gserver/tests/sequence_rnn_multi_unequalength_inputs.py", + "gserver/tests/sequence_nest_rnn_multi_unequalength_inputs.py", 1e-6, useGpu); } -- GitLab