From 3157ce6123534896e51dfd600cb5f0fe03eb20fe Mon Sep 17 00:00:00 2001 From: Helin Wang Date: Mon, 13 Nov 2017 16:40:43 -0800 Subject: [PATCH] Simpily demo, add paddle.default_main_program() and paddle.default_startup_program - Removed all main_program and startup_program in the demo. - Using paddle.default_main_program() hides the implementation detail (e.g., using g_main_program) from the user, we can change the implementation in the future much easier. --- python/paddle/v2/__init__.py | 2 + python/paddle/v2/fluid/framework.py | 8 +- .../v2/fluid/tests/book/test_fit_a_line.py | 34 ++--- .../book/test_image_classification_train.py | 113 +++++---------- .../tests/book/test_recognize_digits_conv.py | 42 ++---- .../tests/book/test_recognize_digits_mlp.py | 38 ++--- .../tests/book/test_recommender_system.py | 137 +++++------------- .../book/test_understand_sentiment_conv.py | 7 +- .../test_understand_sentiment_dynamic_lstm.py | 7 +- .../book/test_understand_sentiment_lstm.py | 7 +- .../v2/fluid/tests/book/test_word2vec.py | 101 +++++-------- 11 files changed, 155 insertions(+), 341 deletions(-) diff --git a/python/paddle/v2/__init__.py b/python/paddle/v2/__init__.py index 1c8d8f4b2f6..3d705138434 100644 --- a/python/paddle/v2/__init__.py +++ b/python/paddle/v2/__init__.py @@ -37,6 +37,8 @@ import model import paddle.trainer.config_parser as cp __all__ = [ + 'default_startup_program', + 'default_main_program', 'optimizer', 'layer', 'activation', diff --git a/python/paddle/v2/fluid/framework.py b/python/paddle/v2/fluid/framework.py index e2587b4f745..f20567243ae 100644 --- a/python/paddle/v2/fluid/framework.py +++ b/python/paddle/v2/fluid/framework.py @@ -4,7 +4,7 @@ import collections import numpy as np import copy -__all__ = ['Block', 'Variable', 'Program', 'Operator'] +__all__ = ['Block', 'Variable', 'Program', 'Operator', 'default_startup_program', 'default_main_program'] def unique_name(prefix): @@ -562,3 +562,9 @@ class Parameter(Variable): # program is a global instance. g_main_program = Program() g_startup_program = Program() + +def default_startup_program(): + return g_startup_program + +def default_main_program(): + return g_main_program diff --git a/python/paddle/v2/fluid/tests/book/test_fit_a_line.py b/python/paddle/v2/fluid/tests/book/test_fit_a_line.py index 5ef963bffa4..ee677a2c567 100644 --- a/python/paddle/v2/fluid/tests/book/test_fit_a_line.py +++ b/python/paddle/v2/fluid/tests/book/test_fit_a_line.py @@ -2,45 +2,33 @@ import paddle.v2 as paddle import paddle.v2.fluid.layers as layers import paddle.v2.fluid.core as core import paddle.v2.fluid.optimizer as optimizer - -from paddle.v2.fluid.framework import Program +import paddle.v2.fluid.framework as framework from paddle.v2.fluid.io import save_persistables, load_persistables from paddle.v2.fluid.executor import Executor import numpy as np -startup_program = Program() -main_program = Program() x = layers.data( name='x', shape=[13], - data_type='float32', - main_program=main_program, - startup_program=startup_program) + data_type='float32') y_predict = layers.fc(input=x, size=1, - act=None, - main_program=main_program, - startup_program=startup_program) + act=None) y = layers.data( name='y', shape=[1], - data_type='float32', - main_program=main_program, - startup_program=startup_program) + data_type='float32') cost = layers.square_error_cost( input=y_predict, - label=y, - main_program=main_program, - startup_program=startup_program) -avg_cost = layers.mean( - x=cost, main_program=main_program, startup_program=startup_program) + label=y) +avg_cost = layers.mean(x=cost) sgd_optimizer = optimizer.SGDOptimizer(learning_rate=0.001) -opts = sgd_optimizer.minimize(avg_cost, startup_program) +opts = sgd_optimizer.minimize(avg_cost) BATCH_SIZE = 20 @@ -52,12 +40,12 @@ train_reader = paddle.batch( place = core.CPUPlace() exe = Executor(place) -exe.run(startup_program, feed={}, fetch_list=[]) +exe.run(framework.default_startup_program()) PASS_NUM = 100 for pass_id in range(PASS_NUM): - save_persistables(exe, "./fit_a_line.model/", main_program=main_program) - load_persistables(exe, "./fit_a_line.model/", main_program=main_program) + save_persistables(exe, "./fit_a_line.model/") + load_persistables(exe, "./fit_a_line.model/") for data in train_reader(): x_data = np.array(map(lambda x: x[0], data)).astype("float32") y_data = np.array(map(lambda x: x[1], data)).astype("float32") @@ -69,7 +57,7 @@ for pass_id in range(PASS_NUM): tensor_y = core.LoDTensor() tensor_y.set(y_data, place) # print tensor_y.get_dims() - outs = exe.run(main_program, + outs = exe.run(framework.default_main_program(), feed={'x': tensor_x, 'y': tensor_y}, fetch_list=[avg_cost]) diff --git a/python/paddle/v2/fluid/tests/book/test_image_classification_train.py b/python/paddle/v2/fluid/tests/book/test_image_classification_train.py index e253b8d27fd..f4be835b3ad 100644 --- a/python/paddle/v2/fluid/tests/book/test_image_classification_train.py +++ b/python/paddle/v2/fluid/tests/book/test_image_classification_train.py @@ -5,19 +5,17 @@ import paddle.v2.fluid.layers as layers import paddle.v2.fluid.nets as nets import paddle.v2.fluid.optimizer as optimizer from paddle.v2.fluid.executor import Executor -from paddle.v2.fluid.framework import g_startup_program, g_main_program +import paddle.v2.fluid.framework as framework from paddle.v2.fluid.initializer import XavierInitializer -def resnet_cifar10(input, depth=32, main_program=None, startup_program=None): +def resnet_cifar10(input, depth=32): def conv_bn_layer(input, ch_out, filter_size, stride, padding, - act='relu', - main_program=None, - startup_program=None): + act='relu'): tmp = layers.conv2d( input=input, filter_size=filter_size, @@ -25,14 +23,10 @@ def resnet_cifar10(input, depth=32, main_program=None, startup_program=None): stride=stride, padding=padding, act=None, - bias_attr=False, - main_program=main_program, - startup_program=startup_program) + bias_attr=False) return layers.batch_norm( input=tmp, - act=act, - main_program=main_program, - startup_program=startup_program) + act=act) def shortcut(input, ch_in, ch_out, stride, program, init_program): if ch_in != ch_out: @@ -44,40 +38,30 @@ def resnet_cifar10(input, depth=32, main_program=None, startup_program=None): def basicblock(input, ch_in, ch_out, - stride, - main_program=main_program, - startup_program=startup_program): + stride): tmp = conv_bn_layer( input, ch_out, 3, stride, - 1, - main_program=main_program, - startup_program=startup_program) + 1) tmp = conv_bn_layer( tmp, ch_out, 3, 1, 1, - act=None, - main_program=main_program, - startup_program=startup_program) - short = shortcut(input, ch_in, ch_out, stride, main_program, - startup_program) + act=None) + short = shortcut(input, ch_in, ch_out, stride) return layers.elementwise_add( x=tmp, y=short, - act='relu', - main_program=main_program, - startup_program=startup_program) + act='relu') - def layer_warp(block_func, input, ch_in, ch_out, count, stride, program, - startup_program): - tmp = block_func(input, ch_in, ch_out, stride, program, startup_program) + def layer_warp(block_func, input, ch_in, ch_out, count, stride): + tmp = block_func(input, ch_in, ch_out, stride) for i in range(1, count): - tmp = block_func(tmp, ch_out, ch_out, 1, program, startup_program) + tmp = block_func(tmp, ch_out, ch_out, 1) return tmp assert (depth - 2) % 6 == 0 @@ -87,53 +71,41 @@ def resnet_cifar10(input, depth=32, main_program=None, startup_program=None): ch_out=16, filter_size=3, stride=1, - padding=1, - main_program=main_program, - startup_program=startup_program) + padding=1) res1 = layer_warp( basicblock, conv1, 16, 16, n, - 1, - main_program=main_program, - startup_program=startup_program) + 1) res2 = layer_warp( basicblock, res1, 16, 32, n, - 2, - main_program=main_program, - startup_program=startup_program) + 2) res3 = layer_warp( basicblock, res2, 32, 64, n, - 2, - main_program=main_program, - startup_program=startup_program) + 2) pool = layers.pool2d( input=res3, pool_size=8, pool_type='avg', - pool_stride=1, - main_program=main_program, - startup_program=startup_program) + pool_stride=1) return pool -def vgg16_bn_drop(input, main_program=None, startup_program=None): +def vgg16_bn_drop(input): def conv_block(input, num_filter, groups, - dropouts, - main_program=None, - startup_program=None): + dropouts): return nets.img_conv_group( input=input, pool_size=2, @@ -143,51 +115,34 @@ def vgg16_bn_drop(input, main_program=None, startup_program=None): conv_act='relu', conv_with_batchnorm=True, conv_batchnorm_drop_rate=dropouts, - pool_type='max', - main_program=main_program, - startup_program=startup_program) + pool_type='max') - conv1 = conv_block(input, 64, 2, [0.3, 0], main_program, startup_program) - conv2 = conv_block(conv1, 128, 2, [0.4, 0], main_program, startup_program) - conv3 = conv_block(conv2, 256, 3, [0.4, 0.4, 0], main_program, - startup_program) - conv4 = conv_block(conv3, 512, 3, [0.4, 0.4, 0], main_program, - startup_program) - conv5 = conv_block(conv4, 512, 3, [0.4, 0.4, 0], main_program, - startup_program) + conv1 = conv_block(input, 64, 2, [0.3, 0]) + conv2 = conv_block(conv1, 128, 2, [0.4, 0]) + conv3 = conv_block(conv2, 256, 3, [0.4, 0.4, 0]) + conv4 = conv_block(conv3, 512, 3, [0.4, 0.4, 0]) + conv5 = conv_block(conv4, 512, 3, [0.4, 0.4, 0]) drop = layers.dropout( x=conv5, - dropout_prob=0.5, - main_program=main_program, - startup_program=startup_program) + dropout_prob=0.5) fc1 = layers.fc(input=drop, size=512, act=None, - param_attr={"initializer": XavierInitializer()}, - main_program=main_program, - startup_program=startup_program) + param_attr={"initializer": XavierInitializer()}) reshape1 = layers.reshape( x=fc1, - shape=list(fc1.shape + (1, 1)), - main_program=main_program, - startup_program=startup_program) + shape=list(fc1.shape + (1, 1))) bn = layers.batch_norm( input=reshape1, - act='relu', - main_program=main_program, - startup_program=startup_program) + act='relu') drop2 = layers.dropout( x=bn, - dropout_prob=0.5, - main_program=main_program, - startup_program=startup_program) + dropout_prob=0.5) fc2 = layers.fc(input=drop2, size=512, act=None, - param_attr={"initializer": XavierInitializer()}, - main_program=main_program, - startup_program=startup_program) + param_attr={"initializer": XavierInitializer()}) return fc2 @@ -225,7 +180,7 @@ train_reader = paddle.batch( place = core.CPUPlace() exe = Executor(place) -exe.run(g_startup_program, feed={}, fetch_list=[]) +exe.run(framework.default_startup_program()) for pass_id in range(PASS_NUM): batch_id = 0 @@ -243,7 +198,7 @@ for pass_id in range(PASS_NUM): tensor_img.set(img_data, place) tensor_y.set(y_data, place) - outs = exe.run(g_main_program, + outs = exe.run(framework.default_main_program(), feed={"pixel": tensor_img, "label": tensor_y}, fetch_list=[avg_cost, accuracy]) diff --git a/python/paddle/v2/fluid/tests/book/test_recognize_digits_conv.py b/python/paddle/v2/fluid/tests/book/test_recognize_digits_conv.py index 2b723125412..42128f1b7ce 100644 --- a/python/paddle/v2/fluid/tests/book/test_recognize_digits_conv.py +++ b/python/paddle/v2/fluid/tests/book/test_recognize_digits_conv.py @@ -3,67 +3,49 @@ import paddle.v2.fluid.layers as layers import paddle.v2.fluid.nets as nets import paddle.v2.fluid.core as core import paddle.v2.fluid.optimizer as optimizer - -from paddle.v2.fluid.framework import Program +import paddle.v2.fluid.framework as framework from paddle.v2.fluid.executor import Executor import numpy as np -startup_program = Program() -main_program = Program() - images = layers.data( name='pixel', shape=[1, 28, 28], - data_type='float32', - main_program=main_program, - startup_program=startup_program) + data_type='float32') label = layers.data( name='label', shape=[1], - data_type='int64', - main_program=main_program, - startup_program=startup_program) + data_type='int64') conv_pool_1 = nets.simple_img_conv_pool( input=images, filter_size=5, num_filters=20, pool_size=2, pool_stride=2, - act="relu", - main_program=main_program, - startup_program=startup_program) + act="relu") conv_pool_2 = nets.simple_img_conv_pool( input=conv_pool_1, filter_size=5, num_filters=50, pool_size=2, pool_stride=2, - act="relu", - main_program=main_program, - startup_program=startup_program) + act="relu") predict = layers.fc(input=conv_pool_2, size=10, - act="softmax", - main_program=main_program, - startup_program=startup_program) + act="softmax") cost = layers.cross_entropy( input=predict, - label=label, - main_program=main_program, - startup_program=startup_program) -avg_cost = layers.mean(x=cost, main_program=main_program) + label=label) +avg_cost = layers.mean(x=cost) accuracy = layers.accuracy( input=predict, - label=label, - main_program=main_program, - startup_program=startup_program) + label=label) # optimizer = optimizer.MomentumOptimizer(learning_rate=0.1 / 128.0, # momentum=0.9) optimizer = optimizer.AdamOptimizer(learning_rate=0.01, beta1=0.9, beta2=0.999) -opts = optimizer.minimize(avg_cost, startup_program) +opts = optimizer.minimize(avg_cost) BATCH_SIZE = 50 PASS_NUM = 3 @@ -75,7 +57,7 @@ train_reader = paddle.batch( place = core.CPUPlace() exe = Executor(place) -exe.run(startup_program, feed={}, fetch_list=[]) +exe.run(framework.default_startup_program()) for pass_id in range(PASS_NUM): count = 0 @@ -90,7 +72,7 @@ for pass_id in range(PASS_NUM): tensor_img.set(img_data, place) tensor_y.set(y_data, place) - outs = exe.run(main_program, + outs = exe.run(framework.default_main_program(), feed={"pixel": tensor_img, "label": tensor_y}, fetch_list=[avg_cost, accuracy]) diff --git a/python/paddle/v2/fluid/tests/book/test_recognize_digits_mlp.py b/python/paddle/v2/fluid/tests/book/test_recognize_digits_mlp.py index 2e1a9f236b6..b0164e3e365 100644 --- a/python/paddle/v2/fluid/tests/book/test_recognize_digits_mlp.py +++ b/python/paddle/v2/fluid/tests/book/test_recognize_digits_mlp.py @@ -2,8 +2,7 @@ import paddle.v2 as paddle import paddle.v2.fluid.layers as layers import paddle.v2.fluid.core as core import paddle.v2.fluid.optimizer as optimizer - -from paddle.v2.fluid.framework import Program +import paddle.v2.fluid.framework as framework from paddle.v2.fluid.executor import Executor from paddle.v2.fluid.regularizer import L2DecayRegularizer from paddle.v2.fluid.initializer import UniformInitializer @@ -11,14 +10,10 @@ from paddle.v2.fluid.initializer import UniformInitializer import numpy as np BATCH_SIZE = 128 -startup_program = Program() -main_program = Program() image = layers.data( name='x', shape=[784], - data_type='float32', - main_program=main_program, - startup_program=startup_program) + data_type='float32') param_attr = { 'name': None, @@ -30,45 +25,30 @@ param_attr = { hidden1 = layers.fc(input=image, size=128, act='relu', - main_program=main_program, - startup_program=startup_program, param_attr=param_attr) hidden2 = layers.fc(input=hidden1, size=64, act='relu', - main_program=main_program, - startup_program=startup_program, param_attr=param_attr) predict = layers.fc(input=hidden2, size=10, act='softmax', - main_program=main_program, - startup_program=startup_program, param_attr=param_attr) label = layers.data( name='y', shape=[1], - data_type='int64', - main_program=main_program, - startup_program=startup_program) + data_type='int64') -cost = layers.cross_entropy( - input=predict, - label=label, - main_program=main_program, - startup_program=startup_program) -avg_cost = layers.mean( - x=cost, main_program=main_program, startup_program=startup_program) +cost = layers.cross_entropy(input=predict, label=label) +avg_cost = layers.mean(x=cost) accuracy = layers.accuracy( input=predict, - label=label, - main_program=main_program, - startup_program=startup_program) + label=label) optimizer = optimizer.MomentumOptimizer(learning_rate=0.001, momentum=0.9) -opts = optimizer.minimize(avg_cost, startup_program) +opts = optimizer.minimize(avg_cost) train_reader = paddle.batch( paddle.reader.shuffle( @@ -78,7 +58,7 @@ train_reader = paddle.batch( place = core.CPUPlace() exe = Executor(place) -exe.run(startup_program, feed={}, fetch_list=[]) +exe.run(framework.default_startup_program()) PASS_NUM = 100 for pass_id in range(PASS_NUM): @@ -93,7 +73,7 @@ for pass_id in range(PASS_NUM): tensor_y = core.LoDTensor() tensor_y.set(y_data, place) - outs = exe.run(main_program, + outs = exe.run(framework.default_main_program(), feed={'x': tensor_x, 'y': tensor_y}, fetch_list=[avg_cost, accuracy]) diff --git a/python/paddle/v2/fluid/tests/book/test_recommender_system.py b/python/paddle/v2/fluid/tests/book/test_recommender_system.py index 4708dfe3e92..eefcb55bebf 100644 --- a/python/paddle/v2/fluid/tests/book/test_recommender_system.py +++ b/python/paddle/v2/fluid/tests/book/test_recommender_system.py @@ -3,16 +3,13 @@ import paddle.v2.fluid.layers as layers import paddle.v2.fluid.nets as nets import paddle.v2.fluid.core as core import paddle.v2.fluid.optimizer as optimizer - -from paddle.v2.fluid.framework import Program +import paddle.v2.fluid.framework as framework from paddle.v2.fluid.executor import Executor import numpy as np -startup_program = Program() -main_program = Program() -is_sparse = True -use_gpu = False +IS_SPARSE = True +USE_GPU = False BATCH_SIZE = 256 @@ -25,99 +22,71 @@ def get_usr_combined_features(): uid = layers.data( name='user_id', shape=[1], - data_type='int64', - main_program=main_program, - startup_program=startup_program) + data_type='int64') usr_emb = layers.embedding( input=uid, data_type='float32', size=[USR_DICT_SIZE, 32], param_attr={'name': 'user_table'}, - is_sparse=is_sparse, - main_program=main_program, - startup_program=startup_program) + is_sparse=IS_SPARSE) usr_fc = layers.fc(input=usr_emb, - size=32, - main_program=main_program, - startup_program=startup_program) + size=32) USR_GENDER_DICT_SIZE = 2 usr_gender_id = layers.data( name='gender_id', shape=[1], - data_type='int64', - main_program=main_program, - startup_program=startup_program) + data_type='int64') usr_gender_emb = layers.embedding( input=usr_gender_id, size=[USR_GENDER_DICT_SIZE, 16], param_attr={'name': 'gender_table'}, - is_sparse=is_sparse, - main_program=main_program, - startup_program=startup_program) + is_sparse=IS_SPARSE) usr_gender_fc = layers.fc(input=usr_gender_emb, - size=16, - main_program=main_program, - startup_program=startup_program) + size=16) USR_AGE_DICT_SIZE = len(paddle.dataset.movielens.age_table) usr_age_id = layers.data( name='age_id', shape=[1], - data_type="int64", - main_program=main_program, - startup_program=startup_program) + data_type="int64") usr_age_emb = layers.embedding( input=usr_age_id, size=[USR_AGE_DICT_SIZE, 16], - is_sparse=is_sparse, - param_attr={'name': 'age_table'}, - main_program=main_program, - startup_program=startup_program) + is_sparse=IS_SPARSE, + param_attr={'name': 'age_table'}) usr_age_fc = layers.fc(input=usr_age_emb, - size=16, - main_program=main_program, - startup_program=startup_program) + size=16) USR_JOB_DICT_SIZE = paddle.dataset.movielens.max_job_id() + 1 usr_job_id = layers.data( name='job_id', shape=[1], - data_type="int64", - main_program=main_program, - startup_program=startup_program) + data_type="int64") usr_job_emb = layers.embedding( input=usr_job_id, size=[USR_JOB_DICT_SIZE, 16], param_attr={'name': 'job_table'}, - is_sparse=is_sparse, - main_program=main_program, - startup_program=startup_program) + is_sparse=IS_SPARSE) usr_job_fc = layers.fc(input=usr_job_emb, - size=16, - main_program=main_program, - startup_program=startup_program) + size=16) concat_embed = layers.concat( input=[usr_fc, usr_gender_fc, usr_age_fc, usr_job_fc], - axis=1, - main_program=main_program, - startup_program=startup_program) + axis=1) usr_combined_features = layers.fc(input=concat_embed, size=200, - act="tanh", - main_program=main_program, - startup_program=startup_program) + act="tanh") return usr_combined_features @@ -129,83 +98,61 @@ def get_mov_combined_features(): mov_id = layers.data( name='movie_id', shape=[1], - data_type='int64', - main_program=main_program, - startup_program=startup_program) + data_type='int64') mov_emb = layers.embedding( input=mov_id, data_type='float32', size=[MOV_DICT_SIZE, 32], param_attr={'name': 'movie_table'}, - is_sparse=is_sparse, - main_program=main_program, - startup_program=startup_program) + is_sparse=IS_SPARSE) mov_fc = layers.fc(input=mov_emb, - size=32, - main_program=main_program, - startup_program=startup_program) + size=32) CATEGORY_DICT_SIZE = len(paddle.dataset.movielens.movie_categories()) category_id = layers.data( name='category_id', shape=[1], - data_type='int64', - main_program=main_program, - startup_program=startup_program) + data_type='int64') mov_categories_emb = layers.embedding( input=category_id, size=[CATEGORY_DICT_SIZE, 32], - is_sparse=is_sparse, - main_program=main_program, - startup_program=startup_program) + is_sparse=IS_SPARSE) mov_categories_hidden = layers.sequence_pool( input=mov_categories_emb, - pool_type="sum", - main_program=main_program, - startup_program=startup_program) + pool_type="sum") MOV_TITLE_DICT_SIZE = len(paddle.dataset.movielens.get_movie_title_dict()) mov_title_id = layers.data( name='movie_title', shape=[1], - data_type='int64', - main_program=main_program, - startup_program=startup_program) + data_type='int64') mov_title_emb = layers.embedding( input=mov_title_id, size=[MOV_TITLE_DICT_SIZE, 32], - is_sparse=is_sparse, - main_program=main_program, - startup_program=startup_program) + is_sparse=IS_SPARSE) mov_title_conv = nets.sequence_conv_pool( input=mov_title_emb, num_filters=32, filter_size=3, act="tanh", - pool_type="sum", - main_program=main_program, - startup_program=startup_program) + pool_type="sum") concat_embed = layers.concat( input=[mov_fc, mov_categories_hidden, mov_title_conv], - axis=1, - main_program=main_program, - startup_program=startup_program) + axis=1) # FIXME(dzh) : need tanh operator mov_combined_features = layers.fc(input=concat_embed, size=200, - act="tanh", - main_program=main_program, - startup_program=startup_program) + act="tanh") return mov_combined_features @@ -217,27 +164,18 @@ def model(): # need cos sim inference = layers.cos_sim( X=usr_combined_features, - Y=mov_combined_features, - main_program=main_program, - startup_program=startup_program) + Y=mov_combined_features) label = layers.data( name='score', shape=[1], - data_type='float32', - main_program=main_program, - startup_program=startup_program) + data_type='float32') square_cost = layers.square_error_cost( input=inference, - label=label, - main_program=main_program, - startup_program=startup_program) + label=label) - avg_cost = layers.mean( - x=square_cost, - main_program=main_program, - startup_program=startup_program) + avg_cost = layers.mean(x=square_cost) return avg_cost @@ -245,16 +183,15 @@ def model(): def main(): cost = model() sgd_optimizer = optimizer.SGDOptimizer(learning_rate=0.2) - opts = sgd_optimizer.minimize(cost, startup_program=startup_program) - block = main_program.block(0) + opts = sgd_optimizer.minimize(cost) - if use_gpu: + if USE_GPU: place = core.GPUPlace(0) else: place = core.CPUPlace() exe = Executor(place) - exe.run(startup_program, feed={}, fetch_list=[]) + exe.run(framework.default_startup_program()) train_reader = paddle.batch( paddle.reader.shuffle( @@ -303,7 +240,7 @@ def main(): PASS_NUM = 100 for pass_id in range(PASS_NUM): for data in train_reader(): - outs = exe.run(main_program, + outs = exe.run(framework.default_main_program(), feed=func_feed(feeding, data), fetch_list=[cost]) out = np.array(outs[0]) diff --git a/python/paddle/v2/fluid/tests/book/test_understand_sentiment_conv.py b/python/paddle/v2/fluid/tests/book/test_understand_sentiment_conv.py index dc4b63da9b3..91fc79a9870 100644 --- a/python/paddle/v2/fluid/tests/book/test_understand_sentiment_conv.py +++ b/python/paddle/v2/fluid/tests/book/test_understand_sentiment_conv.py @@ -3,8 +3,7 @@ import paddle.v2.fluid.layers as layers import paddle.v2.fluid.nets as nets import paddle.v2.fluid.core as core import paddle.v2.fluid.optimizer as optimizer - -from paddle.v2.fluid.framework import Program, g_main_program, g_startup_program +import paddle.v2.fluid.framework as framework from paddle.v2.fluid.executor import Executor import numpy as np @@ -70,7 +69,7 @@ def main(): place = core.CPUPlace() exe = Executor(place) - exe.run(g_startup_program) + exe.run(framework.default_startup_program()) for pass_id in xrange(PASS_NUM): for data in train_data(): @@ -82,7 +81,7 @@ def main(): tensor_label = core.LoDTensor() tensor_label.set(label, place) - outs = exe.run(g_main_program, + outs = exe.run(framework.default_main_program(), feed={"words": tensor_words, "label": tensor_label}, fetch_list=[cost, acc]) diff --git a/python/paddle/v2/fluid/tests/book/test_understand_sentiment_dynamic_lstm.py b/python/paddle/v2/fluid/tests/book/test_understand_sentiment_dynamic_lstm.py index 6d507f4c8e3..8c3d4488354 100644 --- a/python/paddle/v2/fluid/tests/book/test_understand_sentiment_dynamic_lstm.py +++ b/python/paddle/v2/fluid/tests/book/test_understand_sentiment_dynamic_lstm.py @@ -3,8 +3,7 @@ import paddle.v2.fluid.layers as layers import paddle.v2.fluid.nets as nets import paddle.v2.fluid.core as core import paddle.v2.fluid.optimizer as optimizer - -from paddle.v2.fluid.framework import Program, g_main_program, g_startup_program +import paddle.v2.fluid.framework as framework from paddle.v2.fluid.executor import Executor import numpy as np @@ -81,7 +80,7 @@ def main(): place = core.CPUPlace() exe = Executor(place) - exe.run(g_startup_program) + exe.run(framework.default_startup_program()) for pass_id in xrange(PASS_NUM): for data in train_data(): @@ -93,7 +92,7 @@ def main(): tensor_label = core.LoDTensor() tensor_label.set(label, place) - outs = exe.run(g_main_program, + outs = exe.run(framework.default_main_program(), feed={"words": tensor_words, "label": tensor_label}, fetch_list=[cost, acc]) diff --git a/python/paddle/v2/fluid/tests/book/test_understand_sentiment_lstm.py b/python/paddle/v2/fluid/tests/book/test_understand_sentiment_lstm.py index 848dcce974a..a7d791c1f38 100644 --- a/python/paddle/v2/fluid/tests/book/test_understand_sentiment_lstm.py +++ b/python/paddle/v2/fluid/tests/book/test_understand_sentiment_lstm.py @@ -2,8 +2,7 @@ import paddle.v2 as paddle import paddle.v2.fluid.layers as layers import paddle.v2.fluid.core as core import paddle.v2.fluid.optimizer as optimizer - -from paddle.v2.fluid.framework import g_main_program, g_startup_program +import paddle.v2.fluid.framework as framework from paddle.v2.fluid.executor import Executor import numpy as np @@ -88,10 +87,10 @@ def main(): place = core.CPUPlace() tensor_words, tensor_label = prepare_feed_data(data, place) exe = Executor(place) - exe.run(g_startup_program) + exe.run(framework.default_startup_program()) while True: - outs = exe.run(g_main_program, + outs = exe.run(framework.default_main_program(), feed={"words": tensor_words, "label": tensor_label}, fetch_list=[cost, acc]) diff --git a/python/paddle/v2/fluid/tests/book/test_word2vec.py b/python/paddle/v2/fluid/tests/book/test_word2vec.py index 054dbd5a3d0..9dcb6f2fea0 100644 --- a/python/paddle/v2/fluid/tests/book/test_word2vec.py +++ b/python/paddle/v2/fluid/tests/book/test_word2vec.py @@ -2,20 +2,17 @@ import paddle.v2 as paddle import paddle.v2.fluid.layers as layers import paddle.v2.fluid.core as core import paddle.v2.fluid.optimizer as optimizer - -from paddle.v2.fluid.framework import Program +import paddle.v2.fluid.framework as framework from paddle.v2.fluid.executor import Executor import numpy as np -startup_program = Program() -main_program = Program() - -embed_size = 32 -hidden_size = 256 +PASS_NUM = 100 +EMBED_SIZE = 32 +HIDDEN_SIZE = 256 N = 5 -batch_size = 32 -is_sparse = True +BATCH_SIZE = 32 +IS_SPARSE = True word_dict = paddle.dataset.imikolov.build_dict() dict_size = len(word_dict) @@ -23,97 +20,67 @@ dict_size = len(word_dict) first_word = layers.data( name='firstw', shape=[1], - data_type='int64', - main_program=main_program, - startup_program=startup_program) + data_type='int64') second_word = layers.data( name='secondw', shape=[1], - data_type='int64', - main_program=main_program, - startup_program=startup_program) + data_type='int64') third_word = layers.data( name='thirdw', shape=[1], - data_type='int64', - main_program=main_program, - startup_program=startup_program) + data_type='int64') forth_word = layers.data( name='forthw', shape=[1], - data_type='int64', - main_program=main_program, - startup_program=startup_program) + data_type='int64') next_word = layers.data( name='nextw', shape=[1], - data_type='int64', - main_program=main_program, - startup_program=startup_program) + data_type='int64') embed_first = layers.embedding( input=first_word, - size=[dict_size, embed_size], + size=[dict_size, EMBED_SIZE], data_type='float32', - is_sparse=is_sparse, - param_attr={'name': 'shared_w'}, - main_program=main_program, - startup_program=startup_program) + is_sparse=IS_SPARSE, + param_attr={'name': 'shared_w'}) embed_second = layers.embedding( input=second_word, - size=[dict_size, embed_size], + size=[dict_size, EMBED_SIZE], data_type='float32', - is_sparse=is_sparse, - param_attr={'name': 'shared_w'}, - main_program=main_program, - startup_program=startup_program) - + is_sparse=IS_SPARSE, + param_attr={'name': 'shared_w'}) embed_third = layers.embedding( input=third_word, - size=[dict_size, embed_size], + size=[dict_size, EMBED_SIZE], data_type='float32', - is_sparse=is_sparse, - param_attr={'name': 'shared_w'}, - main_program=main_program, - startup_program=startup_program) + is_sparse=IS_SPARSE, + param_attr={'name': 'shared_w'}) embed_forth = layers.embedding( input=forth_word, - size=[dict_size, embed_size], + size=[dict_size, EMBED_SIZE], data_type='float32', - is_sparse=is_sparse, - param_attr={'name': 'shared_w'}, - main_program=main_program, - startup_program=startup_program) + is_sparse=IS_SPARSE, + param_attr={'name': 'shared_w'}) concat_embed = layers.concat( input=[embed_first, embed_second, embed_third, embed_forth], - axis=1, - main_program=main_program, - startup_program=startup_program) - + axis=1) hidden1 = layers.fc(input=concat_embed, - size=hidden_size, - act='sigmoid', - main_program=main_program, - startup_program=startup_program) + size=HIDDEN_SIZE, + act='sigmoid') predict_word = layers.fc(input=hidden1, size=dict_size, - act='softmax', - main_program=main_program, - startup_program=startup_program) + act='softmax') cost = layers.cross_entropy( input=predict_word, - label=next_word, - main_program=main_program, - startup_program=startup_program) -avg_cost = layers.mean( - x=cost, main_program=main_program, startup_program=startup_program) - + label=next_word) +avg_cost = layers.mean(x=cost) sgd_optimizer = optimizer.SGDOptimizer(learning_rate=0.001) -opts = sgd_optimizer.minimize(avg_cost, startup_program) +opts = sgd_optimizer.minimize(avg_cost) train_reader = paddle.batch( - paddle.dataset.imikolov.train(word_dict, N), batch_size) + paddle.dataset.imikolov.train(word_dict, N), BATCH_SIZE) place = core.CPUPlace() exe = Executor(place) @@ -122,8 +89,8 @@ exe = Executor(place) # below exit line. exit(0) -exe.run(startup_program, feed={}, fetch_list=[]) -PASS_NUM = 100 +exe.run(framework.default_startup_program()) + for pass_id in range(PASS_NUM): for data in train_reader(): input_data = [[data_idx[idx] for data_idx in data] for idx in xrange(5)] @@ -150,7 +117,7 @@ for pass_id in range(PASS_NUM): next_tensor = core.LoDTensor() next_tensor.set(next_data, place) - outs = exe.run(main_program, + outs = exe.run(framework.default_main_program(), feed={ 'firstw': first_tensor, 'secondw': second_tensor, -- GitLab