Skip to content

P
Paddle

PaddlePaddle / Paddle
大约 1 年 前同步成功

通知 2298
Star 20931
Fork 5422
P
Paddle
未验证 提交 51d4afaa 编写于 作者: Y Yu Yang 提交者： GitHub
浏览文件
操作

Rename program->main_program, init_program->startup_program (#5360)

上级 e745bcfc
显示空白变更内容
内联 并排
Showing with 486 addition and 418 deletion
python/paddle/v2/framework/framework.py
浏览文件 @ 51d4afaa
......@@ -550,5 +550,5 @@ class Parameter(Variable):
# program is a global instance.
g_program = Program()
g_init_program = Program()
g_main_program = Program()
g_startup_program = Program()
python/paddle/v2/framework/io.py
浏览文件 @ 51d4afaa
import os
import cPickle as pickle
from paddle.v2.framework.framework import Program, Parameter, g_program, \
from paddle.v2.framework.framework import Program, Parameter, g_main_program, \
Variable
__all__ = [
......@@ -29,13 +29,13 @@ def _clone_var_in_block_(block, var):
persistable=True)
def save_vars(executor, dirname, program=None, vars=None, predicate=None):
def save_vars(executor, dirname, main_program=None, vars=None, predicate=None):
"""
Save variables to directory by executor.
:param executor: executor that save variable
:param dirname: directory path
:param program: program. If vars is None, then filter all variables in this
:param main_program: program. If vars is None, then filter all variables in this
program which fit `predicate`. Default g_program.
:param predicate: The Predicate describes a callable that returns a variable
as a bool. If it returns true, the variables will be saved.
......@@ -44,15 +44,15 @@ def save_vars(executor, dirname, program=None, vars=None, predicate=None):
:return: None
"""
if vars is None:
if program is None:
program = g_program
if not isinstance(program, Program):
if main_program is None:
main_program = g_main_program
if not isinstance(main_program, Program):
raise TypeError("program should be as Program type or None")
save_vars(
executor,
dirname=dirname,
vars=filter(predicate, program.list_vars()))
vars=filter(predicate, main_program.list_vars()))
else:
save_program = Program()
save_block = save_program.global_block()
......@@ -66,37 +66,37 @@ def save_vars(executor, dirname, program=None, vars=None, predicate=None):
executor.run(save_program)
def save_params(executor, dirname, program=None):
def save_params(executor, dirname, main_program=None):
"""
Save all parameters to directory with executor.
"""
save_vars(
executor,
dirname=dirname,
program=program,
main_program=main_program,
vars=None,
predicate=is_parameter)
def save_persistables(executor, dirname, program=None):
def save_persistables(executor, dirname, main_program=None):
"""
Save all persistables to directory with executor.
"""
save_vars(
executor,
dirname=dirname,
program=program,
main_program=main_program,
vars=None,
predicate=is_persistable)
def load_vars(executor, dirname, program=None, vars=None, predicate=None):
def load_vars(executor, dirname, main_program=None, vars=None, predicate=None):
"""
Load variables from directory by executor.
:param executor: executor that save variable
:param dirname: directory path
:param program: program. If vars is None, then filter all variables in this
:param main_program: program. If vars is None, then filter all variables in this
program which fit `predicate`. Default g_program.
:param predicate: The Predicate describes a callable that returns a variable
as a bool. If it returns true, the variables will be loaded.
......@@ -105,15 +105,15 @@ def load_vars(executor, dirname, program=None, vars=None, predicate=None):
:return: None
"""
if vars is None:
if program is None:
program = g_program
if not isinstance(program, Program):
if main_program is None:
main_program = g_main_program
if not isinstance(main_program, Program):
raise TypeError("program's type should be Program")
load_vars(
executor,
dirname=dirname,
vars=filter(predicate, program.list_vars()))
vars=filter(predicate, main_program.list_vars()))
else:
load_prog = Program()
load_block = load_prog.global_block()
......@@ -129,27 +129,33 @@ def load_vars(executor, dirname, program=None, vars=None, predicate=None):
executor.run(load_prog)
def load_params(executor, dirname, program=None):
def load_params(executor, dirname, main_program=None):
"""
load all parameters from directory by executor.
"""
load_vars(
executor, dirname=dirname, program=program, predicate=is_parameter)
executor,
dirname=dirname,
main_program=main_program,
predicate=is_parameter)
def load_persistables(executor, dirname, program=None):
def load_persistables(executor, dirname, main_program=None):
"""
load all persistables from directory by executor.
"""
load_vars(
executor, dirname=dirname, program=program, predicate=is_persistable)
executor,
dirname=dirname,
main_program=main_program,
predicate=is_persistable)
def save_inference_model(dirname,
feeded_var_names,
target_vars,
executor,
program=None):
main_program=None):
"""
Build a model especially for inference,
and save it to directory by the executor.
......@@ -158,20 +164,20 @@ def save_inference_model(dirname,
:param feeded_var_names: Names of variables that need to be feeded data during inference
:param target_vars: Variables from which we can get inference results.
:param executor: executor that save inference model
:param program: original program, which will be pruned to build the inference model.
:param main_program: original program, which will be pruned to build the inference model.
Default g_program.
:return: None
"""
if program is None:
program = g_program
if main_program is None:
main_program = g_main_program
if not isinstance(target_vars, list):
target_vars = [target_vars]
if not os.path.isdir(dirname):
os.makedirs(dirname)
pruned_program = program.prune(target_vars)
pruned_program = main_program.prune(target_vars)
fetch_var_names = [v.name for v in target_vars]
model_file_name = dirname + "/__model__"
......@@ -182,10 +188,10 @@ def save_inference_model(dirname,
"fetch_var_names": fetch_var_names
}, f, -1)
save_params(executor, dirname, program)
save_params(executor, dirname, main_program)
def load_persistables_if_exist(executor, dirname, program=None):
def load_persistables_if_exist(executor, dirname, main_program=None):
filenames = next(os.walk(dirname))[2]
filenames = set(filenames)
......@@ -198,7 +204,7 @@ def load_persistables_if_exist(executor, dirname, program=None):
load_vars(
executor,
dirname,
program=program,
main_program=main_program,
vars=None,
predicate=_is_presistable_and_exist_)
......
python/paddle/v2/framework/layer_helper.py
浏览文件 @ 51d4afaa
import copy
import itertools
from paddle.v2.framework.framework import Variable, g_program, \
g_init_program, unique_name, Program
from paddle.v2.framework.framework import Variable, g_main_program, \
g_startup_program, unique_name, Program
from paddle.v2.framework.initializer import ConstantInitializer, \
UniformInitializer
......@@ -20,23 +20,23 @@ class LayerHelper(object):
return self.kwargs['name']
@property
def program(self):
prog = self.kwargs.get('program', None)
def main_program(self):
prog = self.kwargs.get('main_program', None)
if prog is None:
return g_program
return g_main_program
else:
return prog
@property
def init_program(self):
prog = self.kwargs.get('init_program', None)
def startup_program(self):
prog = self.kwargs.get('startup_program', None)
if prog is None:
return g_init_program
return g_startup_program
else:
return prog
def append_op(self, *args, **kwargs):
return self.program.current_block().append_op(*args, **kwargs)
return self.main_program.current_block().append_op(*args, **kwargs)
def multiple_input(self, input_param_name='input'):
inputs = self.kwargs.get(input_param_name, [])
......@@ -120,27 +120,27 @@ class LayerHelper(object):
attr_copy['initializer'] = initializer
if attr_copy['name'] is None:
attr_copy['name'] = unique_name(".".join([self.name, suffix]))
self.init_program.global_block().create_parameter(
self.startup_program.global_block().create_parameter(
dtype=dtype, shape=shape, **attr_copy)
return self.program.global_block().create_parameter(
return self.main_program.global_block().create_parameter(
name=attr_copy['name'], dtype=dtype, shape=shape)
def create_tmp_variable(self, dtype):
return self.program.current_block().create_var(
return self.main_program.current_block().create_var(
name=unique_name(".".join([self.name, 'tmp'])),
dtype=dtype,
persistable=False)
def create_variable(self, *args, **kwargs):
return self.program.current_block().create_var(*args, **kwargs)
return self.main_program.current_block().create_var(*args, **kwargs)
def create_global_variable(self, persistable=False, *args, **kwargs):
return self.program.global_block().create_var(
return self.main_program.global_block().create_var(
*args, persistable=persistable, **kwargs)
def set_variable_initializer(self, var, initializer):
assert isinstance(var, Variable)
self.init_program.global_block().create_var(
self.startup_program.global_block().create_var(
name=var.name,
type=var.type,
dtype=var.data_type,
......
python/paddle/v2/framework/layers.py
浏览文件 @ 51d4afaa
......@@ -18,8 +18,8 @@ def fc(input,
name=None,
act=None,
num_flatten_dims=1,
program=None,
init_program=None):
main_program=None,
startup_program=None):
# create helper
helper = LayerHelper('fc', **locals())
......@@ -64,8 +64,8 @@ def embedding(input,
data_type='float32',
is_sparse=False,
param_attr=None,
program=None,
init_program=None):
main_program=None,
startup_program=None):
helper = LayerHelper('embedding', **locals())
w = helper.create_parameter(
attr=helper.param_attr, shape=size, dtype=data_type)
......@@ -84,8 +84,8 @@ def data(name,
data_type='float32',
type=core.VarDesc.VarType.LOD_TENSOR,
append_batch_size=True,
program=None,
init_program=None):
main_program=None,
startup_program=None):
helper = LayerHelper('data', **locals())
shape = list(shape)
for i in xrange(len(shape)):
......@@ -178,7 +178,7 @@ _create_op_func_('sigmoid')
_create_op_func_('scale')
def cast(x, data_type, program=None):
def cast(x, data_type, main_program=None):
helper = LayerHelper('cast', **locals())
out = helper.create_tmp_variable(dtype=data_type)
helper.append_op(
......@@ -190,7 +190,7 @@ def cast(x, data_type, program=None):
return out
def concat(input, axis, program=None, init_program=None):
def concat(input, axis, main_program=None, startup_program=None):
helper = LayerHelper('concat', **locals())
out = helper.create_tmp_variable(dtype=helper.input_dtype())
helper.append_op(
......@@ -201,7 +201,7 @@ def concat(input, axis, program=None, init_program=None):
return out
def sums(input, program=None, init_program=None):
def sums(input, main_program=None, startup_program=None):
helper = LayerHelper('sum', **locals())
out = helper.create_tmp_variable(dtype=helper.input_dtype())
helper.append_op(type='sum', inputs={'X': input}, outputs={'Out': out})
......@@ -281,8 +281,8 @@ def sequence_conv(input,
padding=None,
bias_attr=None,
param_attr=None,
program=None,
init_program=None):
main_program=None,
startup_program=None):
# FIXME(dzh) : want to unify the argument of python layer
# function. So we ignore some unecessary attributes.
# such as, padding_trainable, context_start.
......@@ -321,8 +321,8 @@ def conv2d(input,
padding=None,
bias_attr=None,
param_attr=None,
program=None,
init_program=None):
main_program=None,
startup_program=None):
helper = LayerHelper('conv2d', **locals())
dtype = helper.input_dtype()
......@@ -388,8 +388,8 @@ def pool2d(input,
pool_stride=[1, 1],
pool_padding=[0, 0],
global_pooling=False,
program=None,
init_program=None):
main_program=None,
startup_program=None):
if pool_type not in ["max", "avg"]:
raise ValueError(
"Unknown pool_type: '%s'. It can only be 'max' or 'avg'.",
......@@ -428,8 +428,8 @@ def batch_norm(input,
param_attr=None,
bias_attr=None,
data_layout='NCHW',
program=None,
init_program=None):
main_program=None,
startup_program=None):
helper = LayerHelper('batch_norm', **locals())
dtype = helper.input_dtype()
......@@ -505,16 +505,16 @@ class BlockGuard(object):
keyword.
"""
def __init__(self, program):
if not isinstance(program, Program):
def __init__(self, main_program):
if not isinstance(main_program, Program):
raise TypeError("BlockGuard takes a program")
self.program = program
self.main_program = main_program
def __enter__(self):
self.program.create_block()
self.main_program.create_block()
def __exit__(self, exc_type, exc_val, exc_tb):
self.program.rollback()
self.main_program.rollback()
if exc_type is not None:
return False # re-raise exception
return True
......@@ -524,7 +524,7 @@ class StaticRNNGuard(BlockGuard):
def __init__(self, rnn):
if not isinstance(rnn, StaticRNN):
raise TypeError("StaticRNNGuard takes an StaticRNN")
super(StaticRNNGuard, self).__init__(rnn.helper.program)
super(StaticRNNGuard, self).__init__(rnn.helper.main_program)
self.rnn = rnn
def __enter__(self):
......@@ -560,8 +560,9 @@ class StaticRNN(object):
IN_RNN_BLOCK = 1
AFTER_RNN_BLOCK = 2
def __init__(self, name=None, program=None):
self.helper = LayerHelper("static_rnn", name=name, program=program)
def __init__(self, name=None, main_program=None):
self.helper = LayerHelper(
"static_rnn", name=name, main_program=main_program)
self.memories = {} # memory map, from pre_mem.name --> MemoryLink
self.inputs = [] # input variable list in current block
self.outputs = [] # output variable list in parent block
......@@ -653,7 +654,7 @@ class StaticRNN(object):
self.memories[mem.name].mem = var
def parent_block(self):
prog = self.helper.program
prog = self.helper.main_program
parent_idx = prog.current_block().parent_idx
assert parent_idx >= 0
parent_block = prog.block(parent_idx)
......@@ -670,8 +671,8 @@ class StaticRNN(object):
return self.outputs
def complete_rnn_op(self):
program = self.helper.program
rnn_block = program.current_block()
main_program = self.helper.main_program
rnn_block = main_program.current_block()
parent_block = self.parent_block()
local_inputs = set()
......@@ -737,7 +738,7 @@ class StaticRNN(object):
})
def lod_rank_table(x, level=0, program=None):
def lod_rank_table(x, level=0, main_program=None):
helper = LayerHelper("lod_rank_table", **locals())
table = helper.create_variable(
type=core.VarDesc.VarType.LOD_RANK_TABLE,
......
python/paddle/v2/framework/net_drawer.py
浏览文件 @ 51d4afaa
......@@ -80,7 +80,7 @@ def parse_graph(program, graph, var_dict, **kwargs):
graph.edge(**draw_edge(var_dict, op, e, arg))
def draw_graph(init_program, program, **kwargs):
def draw_graph(startup_program, main_program, **kwargs):
if kwargs.has_key("graph_attr"):
GRAPH_STYLE.update(kwargs[graph_attr])
if kwargs.has_key("node_attr"):
......@@ -101,8 +101,8 @@ def draw_graph(init_program, program, **kwargs):
**kwargs)
var_dict = {}
parse_graph(init_program, g, var_dict)
parse_graph(program, g, var_dict)
parse_graph(startup_program, g, var_dict)
parse_graph(main_program, g, var_dict)
if filename != None:
g.save()
......
python/paddle/v2/framework/nets.py
浏览文件 @ 51d4afaa
......@@ -10,23 +10,23 @@ def simple_img_conv_pool(input,
pool_stride,
act,
pool_type='max',
program=None,
init_program=None):
main_program=None,
startup_program=None):
conv_out = layers.conv2d(
input=input,
num_filters=num_filters,
filter_size=filter_size,
act=act,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
pool_out = layers.pool2d(
input=conv_out,
pool_size=pool_size,
pool_type=pool_type,
pool_stride=pool_stride,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
return pool_out
......@@ -40,8 +40,8 @@ def img_conv_group(input,
conv_batchnorm_drop_rate=None,
pool_stride=1,
pool_type=None,
program=None,
init_program=None):
main_program=None,
startup_program=None):
"""
Image Convolution Group, Used for vgg net.
"""
......@@ -71,30 +71,30 @@ def img_conv_group(input,
filter_size=conv_filter_size[i],
padding=conv_padding[i],
act=local_conv_act,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
if conv_with_batchnorm[i]:
tmp = layers.batch_norm(
input=tmp,
act=conv_act,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
drop_rate = conv_batchnorm_drop_rate[i]
if abs(drop_rate) > 1e-5:
tmp = layers.dropout(
x=tmp,
dropout_prob=drop_rate,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
pool_out = layers.pool2d(
input=tmp,
pool_size=pool_size,
pool_type=pool_type,
pool_stride=pool_stride,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
return pool_out
......@@ -103,19 +103,19 @@ def sequence_conv_pool(input,
filter_size,
act="sigmoid",
pool_type="max",
program=None,
init_program=None):
main_program=None,
startup_program=None):
conv_out = layers.sequence_conv(
input=input,
num_filters=num_filters,
filter_size=filter_size,
act=act,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
pool_out = layers.sequence_pool(
input=conv_out,
pool_type=pool_type,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
return pool_out
python/paddle/v2/framework/optimizer.py
浏览文件 @ 51d4afaa
......@@ -132,7 +132,7 @@ class Optimizer(object):
def create_optimization_pass(self,
parameters_and_grads,
loss,
init_program=None):
startup_program=None):
"""Add optimization operators to update gradients to variables.
Args:
......@@ -144,7 +144,7 @@ class Optimizer(object):
optimization. This will include parameter update ops, global step
update ops and any other custom ops required by subclasses to manage
their internal state.
:param init_program:
:param startup_program:
"""
# This is a default implementation of create_optimization_pass that
# can be shared by most optimizers. This implementation assumes that
......@@ -156,7 +156,9 @@ class Optimizer(object):
# Create any accumulators
program = loss.block.program
self.helper = LayerHelper(
self.__class__.__name__, program=program, init_program=init_program)
self.__class__.__name__,
main_program=program,
startup_program=startup_program)
self._create_accumulators(loss.block,
[p[0] for p in parameters_and_grads])
# Create any necessary tensors
......@@ -185,7 +187,7 @@ class Optimizer(object):
def minimize(self,
loss,
init_program=None,
startup_program=None,
parameter_list=None,
no_grad_set=None):
"""Add operations to minimize `loss` by updating `parameter_list`.
......@@ -198,7 +200,7 @@ class Optimizer(object):
# Add regularization if any
params_grads = append_regularization_ops(params_grads)
optimize_ops = self.create_optimization_pass(params_grads, loss,
init_program)
startup_program)
return optimize_ops
......
python/paddle/v2/framework/tests/test_executor_and_mul.py
浏览文件 @ 51d4afaa
......@@ -2,7 +2,7 @@ import unittest
from paddle.v2.framework.layers import mul, data
import paddle.v2.framework.core as core
from paddle.v2.framework.executor import Executor
from paddle.v2.framework.framework import g_program
from paddle.v2.framework.framework import g_main_program
import numpy
......@@ -23,7 +23,7 @@ class TestExecutor(unittest.TestCase):
tensor_b = core.LoDTensor()
tensor_b.set(b_np, place)
exe = Executor(place)
outs = exe.run(g_program,
outs = exe.run(g_main_program,
feed={'a': tensor_a,
'b': tensor_b},
fetch_list=[out])
......
python/paddle/v2/framework/tests/test_fit_a_line.py
浏览文件 @ 51d4afaa
......@@ -3,40 +3,44 @@ import paddle.v2.framework.layers as layers
import paddle.v2.framework.core as core
import paddle.v2.framework.optimizer as optimizer
from paddle.v2.framework.framework import Program, g_program
from paddle.v2.framework.framework import Program, g_main_program
from paddle.v2.framework.io import save_persistables, load_persistables
from paddle.v2.framework.executor import Executor
import numpy as np
init_program = Program()
program = Program()
startup_program = Program()
main_program = Program()
x = layers.data(
name='x',
shape=[13],
data_type='float32',
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
y_predict = layers.fc(input=x,
size=1,
act=None,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
y = layers.data(
name='y',
shape=[1],
data_type='float32',
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
cost = layers.square_error_cost(
input=y_predict, label=y, program=program, init_program=init_program)
avg_cost = layers.mean(x=cost, program=program, init_program=init_program)
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)
sgd_optimizer = optimizer.SGDOptimizer(learning_rate=0.001)
opts = sgd_optimizer.minimize(avg_cost, init_program)
opts = sgd_optimizer.minimize(avg_cost, startup_program)
BATCH_SIZE = 20
......@@ -48,12 +52,12 @@ train_reader = paddle.batch(
place = core.CPUPlace()
exe = Executor(place)
exe.run(init_program, feed={}, fetch_list=[])
exe.run(startup_program, feed={}, fetch_list=[])
PASS_NUM = 100
for pass_id in range(PASS_NUM):
save_persistables(exe, "./fit_a_line.model/", program=program)
load_persistables(exe, "./fit_a_line.model/", program=program)
save_persistables(exe, "./fit_a_line.model/", main_program=main_program)
load_persistables(exe, "./fit_a_line.model/", main_program=main_program)
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")
......@@ -65,7 +69,7 @@ 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(program,
outs = exe.run(main_program,
feed={'x': tensor_x,
'y': tensor_y},
fetch_list=[avg_cost])
......
python/paddle/v2/framework/tests/test_image_classification_layer.py
浏览文件 @ 51d4afaa
......@@ -9,8 +9,8 @@ def conv_block(input,
num_filter,
groups,
dropouts,
program=None,
init_program=None):
main_program=None,
startup_program=None):
return nets.img_conv_group(
input=input,
pool_size=2,
......@@ -21,77 +21,81 @@ def conv_block(input,
conv_with_batchnorm=True,
conv_batchnorm_drop_rate=dropouts,
pool_type='max',
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
class TestLayer(unittest.TestCase):
def test_batch_norm_layer(self):
program = Program()
init_program = Program()
main_program = Program()
startup_program = Program()
images = layers.data(
name='pixel',
shape=[3, 48, 48],
data_type='float32',
program=program)
main_program=main_program)
layers.batch_norm(
input=images, program=program, init_program=init_program)
input=images,
main_program=main_program,
startup_program=startup_program)
# print str(program)
# print str(main_program)
def test_dropout_layer(self):
program = Program()
init_program = Program()
main_program = Program()
startup_program = Program()
images = layers.data(
name='pixel',
shape=[3, 48, 48],
data_type='float32',
program=program)
main_program=main_program)
layers.dropout(
x=images,
dropout_prob=0.5,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
# print str(program)
# print str(main_program)
def test_img_conv_group(self):
program = Program()
init_program = Program()
main_program = Program()
startup_program = Program()
images = layers.data(
name='pixel',
shape=[3, 48, 48],
data_type='float32',
program=program,
init_program=init_program)
conv1 = conv_block(images, 64, 2, [0.3, 0], program, init_program)
conv2 = conv_block(conv1, 256, 3, [0.4, 0.4, 0], program, init_program)
main_program=main_program,
startup_program=startup_program)
conv1 = conv_block(images, 64, 2, [0.3, 0], main_program,
startup_program)
conv2 = conv_block(conv1, 256, 3, [0.4, 0.4, 0], main_program,
startup_program)
# print str(program)
# print str(main_program)
def test_elementwise_add_with_act(self):
program = Program()
init_program = Program()
main_program = Program()
startup_program = Program()
image1 = layers.data(
name='pixel1',
shape=[3, 48, 48],
data_type='float32',
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
image2 = layers.data(
name='pixel2',
shape=[3, 48, 48],
data_type='float32',
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
out = layers.elementwise_add(
x=image1,
y=image2,
act='relu',
program=program,
init_program=init_program)
# print(program)
main_program=main_program,
startup_program=startup_program)
# print(main_program)
if __name__ == '__main__':
......
python/paddle/v2/framework/tests/test_image_classification_train.py
浏览文件 @ 51d4afaa
......@@ -5,19 +5,19 @@ import paddle.v2.framework.layers as layers
import paddle.v2.framework.nets as nets
import paddle.v2.framework.optimizer as optimizer
from paddle.v2.framework.executor import Executor
from paddle.v2.framework.framework import g_init_program, g_program
from paddle.v2.framework.framework import g_startup_program, g_main_program
from paddle.v2.framework.initializer import XavierInitializer
def resnet_cifar10(input, depth=32, program=None, init_program=None):
def resnet_cifar10(input, depth=32, main_program=None, startup_program=None):
def conv_bn_layer(input,
ch_out,
filter_size,
stride,
padding,
act='relu',
program=None,
init_program=None):
main_program=None,
startup_program=None):
tmp = layers.conv2d(
input=input,
filter_size=filter_size,
......@@ -26,10 +26,13 @@ def resnet_cifar10(input, depth=32, program=None, init_program=None):
padding=padding,
act=None,
bias_attr=False,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
return layers.batch_norm(
input=tmp, act=act, program=program, init_program=init_program)
input=tmp,
act=act,
main_program=main_program,
startup_program=startup_program)
def shortcut(input, ch_in, ch_out, stride, program, init_program):
if ch_in != ch_out:
......@@ -42,16 +45,16 @@ def resnet_cifar10(input, depth=32, program=None, init_program=None):
ch_in,
ch_out,
stride,
program=program,
init_program=init_program):
main_program=main_program,
startup_program=startup_program):
tmp = conv_bn_layer(
input,
ch_out,
3,
stride,
1,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
tmp = conv_bn_layer(
tmp,
ch_out,
......@@ -59,21 +62,22 @@ def resnet_cifar10(input, depth=32, program=None, init_program=None):
1,
1,
act=None,
program=program,
init_program=init_program)
short = shortcut(input, ch_in, ch_out, stride, program, init_program)
main_program=main_program,
startup_program=startup_program)
short = shortcut(input, ch_in, ch_out, stride, main_program,
startup_program)
return layers.elementwise_add(
x=tmp,
y=short,
act='relu',
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
def layer_warp(block_func, input, ch_in, ch_out, count, stride, program,
init_program):
tmp = block_func(input, ch_in, ch_out, stride, program, init_program)
startup_program):
tmp = block_func(input, ch_in, ch_out, stride, program, startup_program)
for i in range(1, count):
tmp = block_func(tmp, ch_out, ch_out, 1, program, init_program)
tmp = block_func(tmp, ch_out, ch_out, 1, program, startup_program)
return tmp
assert (depth - 2) % 6 == 0
......@@ -84,8 +88,8 @@ def resnet_cifar10(input, depth=32, program=None, init_program=None):
filter_size=3,
stride=1,
padding=1,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
res1 = layer_warp(
basicblock,
conv1,
......@@ -93,8 +97,8 @@ def resnet_cifar10(input, depth=32, program=None, init_program=None):
16,
n,
1,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
res2 = layer_warp(
basicblock,
res1,
......@@ -102,8 +106,8 @@ def resnet_cifar10(input, depth=32, program=None, init_program=None):
32,
n,
2,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
res3 = layer_warp(
basicblock,
res2,
......@@ -111,25 +115,25 @@ def resnet_cifar10(input, depth=32, program=None, init_program=None):
64,
n,
2,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
pool = layers.pool2d(
input=res3,
pool_size=8,
pool_type='avg',
pool_stride=1,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
return pool
def vgg16_bn_drop(input, program=None, init_program=None):
def vgg16_bn_drop(input, main_program=None, startup_program=None):
def conv_block(input,
num_filter,
groups,
dropouts,
program=None,
init_program=None):
main_program=None,
startup_program=None):
return nets.img_conv_group(
input=input,
pool_size=2,
......@@ -140,38 +144,50 @@ def vgg16_bn_drop(input, program=None, init_program=None):
conv_with_batchnorm=True,
conv_batchnorm_drop_rate=dropouts,
pool_type='max',
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
conv1 = conv_block(input, 64, 2, [0.3, 0], program, init_program)
conv2 = conv_block(conv1, 128, 2, [0.4, 0], program, init_program)
conv3 = conv_block(conv2, 256, 3, [0.4, 0.4, 0], program, init_program)
conv4 = conv_block(conv3, 512, 3, [0.4, 0.4, 0], program, init_program)
conv5 = conv_block(conv4, 512, 3, [0.4, 0.4, 0], program, init_program)
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)
drop = layers.dropout(
x=conv5, dropout_prob=0.5, program=program, init_program=init_program)
x=conv5,
dropout_prob=0.5,
main_program=main_program,
startup_program=startup_program)
fc1 = layers.fc(input=drop,
size=512,
act=None,
param_attr={"initializer": XavierInitializer()},
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
reshape1 = layers.reshape(
x=fc1,
shape=list(fc1.shape + (1, 1)),
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
bn = layers.batch_norm(
input=reshape1, act='relu', program=program, init_program=init_program)
input=reshape1,
act='relu',
main_program=main_program,
startup_program=startup_program)
drop2 = layers.dropout(
x=bn, dropout_prob=0.5, program=program, init_program=init_program)
x=bn,
dropout_prob=0.5,
main_program=main_program,
startup_program=startup_program)
fc2 = layers.fc(input=drop2,
size=512,
act=None,
param_attr={"initializer": XavierInitializer()},
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
return fc2
......@@ -209,7 +225,7 @@ train_reader = paddle.batch(
place = core.CPUPlace()
exe = Executor(place)
exe.run(g_init_program, feed={}, fetch_list=[])
exe.run(g_startup_program, feed={}, fetch_list=[])
for pass_id in range(PASS_NUM):
batch_id = 0
......@@ -227,7 +243,7 @@ for pass_id in range(PASS_NUM):
tensor_img.set(img_data, place)
tensor_y.set(y_data, place)
outs = exe.run(g_program,
outs = exe.run(g_main_program,
feed={"pixel": tensor_img,
"label": tensor_y},
fetch_list=[avg_cost, accuracy])
......
python/paddle/v2/framework/tests/test_inference_model_io.py
浏览文件 @ 51d4afaa
......@@ -3,7 +3,7 @@ import paddle.v2.framework.layers as layers
import paddle.v2.framework.core as core
import paddle.v2.framework.optimizer as optimizer
from paddle.v2.framework.framework import Program, g_program
from paddle.v2.framework.framework import Program, g_main_program
from paddle.v2.framework.io import save_inference_model, load_inference_model
import paddle.v2.framework.executor as executor
import unittest
......@@ -20,28 +20,28 @@ class TestBook(unittest.TestCase):
name='x',
shape=[2],
data_type='float32',
program=program,
init_program=init_program)
main_program=program,
startup_program=init_program)
y = layers.data(
name='y',
shape=[1],
data_type='float32',
program=program,
init_program=init_program)
main_program=program,
startup_program=init_program)
y_predict = layers.fc(input=x,
size=1,
act=None,
program=program,
init_program=init_program)
main_program=program,
startup_program=init_program)
cost = layers.square_error_cost(
input=y_predict,
label=y,
program=program,
init_program=init_program)
main_program=program,
startup_program=init_program)
avg_cost = layers.mean(
x=cost, program=program, init_program=init_program)
x=cost, main_program=program, startup_program=init_program)
sgd_optimizer = optimizer.SGDOptimizer(learning_rate=0.001)
opts = sgd_optimizer.minimize(avg_cost, init_program)
......
python/paddle/v2/framework/tests/test_layers.py
浏览文件 @ 51d4afaa
import paddle.v2.framework.layers as layers
import paddle.v2.framework.nets as nets
from paddle.v2.framework.framework import Program, g_program
from paddle.v2.framework.framework import Program, g_main_program
import paddle.v2.framework.core as core
import unittest
......@@ -9,15 +9,15 @@ class TestBook(unittest.TestCase):
def test_fit_a_line(self):
program = Program()
x = layers.data(
name='x', shape=[13], data_type='float32', program=program)
y_predict = layers.fc(input=x, size=1, act=None, program=program)
name='x', shape=[13], data_type='float32', main_program=program)
y_predict = layers.fc(input=x, size=1, act=None, main_program=program)
y = layers.data(
name='y', shape=[1], data_type='float32', program=program)
name='y', shape=[1], data_type='float32', main_program=program)
cost = layers.square_error_cost(
input=y_predict, label=y, program=program)
input=y_predict, label=y, main_program=program)
avg_cost = layers.mean(x=cost, program=program)
avg_cost = layers.mean(x=cost, main_program=program)
self.assertIsNotNone(avg_cost)
program.append_backward(avg_cost)
print str(program)
......@@ -27,26 +27,42 @@ class TestBook(unittest.TestCase):
# Change g_program, so the rest layers use `g_program`
images = layers.data(
name='pixel', shape=[784], data_type='float32', program=program)
name='pixel',
shape=[784],
data_type='float32',
main_program=program)
label = layers.data(
name='label', shape=[1], data_type='int32', program=program)
hidden1 = layers.fc(input=images, size=128, act='relu', program=program)
hidden2 = layers.fc(input=hidden1, size=64, act='relu', program=program)
name='label', shape=[1], data_type='int32', main_program=program)
hidden1 = layers.fc(input=images,
size=128,
act='relu',
main_program=program)
hidden2 = layers.fc(input=hidden1,
size=64,
act='relu',
main_program=program)
predict = layers.fc(input=hidden2,
size=10,
act='softmax',
program=program)
cost = layers.cross_entropy(input=predict, label=label, program=program)
avg_cost = layers.mean(x=cost, program=program)
main_program=program)
cost = layers.cross_entropy(
input=predict, label=label, main_program=program)
avg_cost = layers.mean(x=cost, main_program=program)
self.assertIsNotNone(avg_cost)
print str(program)
def test_simple_conv2d(self):
program = Program()
images = layers.data(
name='pixel', shape=[3, 48, 48], data_type='int32', program=program)
name='pixel',
shape=[3, 48, 48],
data_type='int32',
main_program=program)
layers.conv2d(
input=images, num_filters=3, filter_size=[4, 4], program=program)
input=images,
num_filters=3,
filter_size=[4, 4],
main_program=program)
print str(program)
......@@ -57,9 +73,9 @@ class TestBook(unittest.TestCase):
name='pixel',
shape=[1, 28, 28],
data_type='float32',
program=program)
main_program=program)
label = layers.data(
name='label', shape=[1], data_type='int32', program=program)
name='label', shape=[1], data_type='int32', main_program=program)
conv_pool_1 = nets.simple_img_conv_pool(
input=images,
filter_size=5,
......@@ -67,7 +83,7 @@ class TestBook(unittest.TestCase):
pool_size=2,
pool_stride=2,
act="relu",
program=program)
main_program=program)
conv_pool_2 = nets.simple_img_conv_pool(
input=conv_pool_1,
filter_size=5,
......@@ -75,14 +91,15 @@ class TestBook(unittest.TestCase):
pool_size=2,
pool_stride=2,
act="relu",
program=program)
main_program=program)
predict = layers.fc(input=conv_pool_2,
size=10,
act="softmax",
program=program)
cost = layers.cross_entropy(input=predict, label=label, program=program)
avg_cost = layers.mean(x=cost, program=program)
main_program=program)
cost = layers.cross_entropy(
input=predict, label=label, main_program=program)
avg_cost = layers.mean(x=cost, main_program=program)
program.append_backward(avg_cost)
......@@ -93,58 +110,58 @@ class TestBook(unittest.TestCase):
dict_size = 10000
embed_size = 32
first_word = layers.data(
name='firstw', shape=[1], data_type='int64', program=program)
name='firstw', shape=[1], data_type='int64', main_program=program)
second_word = layers.data(
name='secondw', shape=[1], data_type='int64', program=program)
name='secondw', shape=[1], data_type='int64', main_program=program)
third_word = layers.data(
name='thirdw', shape=[1], data_type='int64', program=program)
name='thirdw', shape=[1], data_type='int64', main_program=program)
forth_word = layers.data(
name='forthw', shape=[1], data_type='int64', program=program)
name='forthw', shape=[1], data_type='int64', main_program=program)
next_word = layers.data(
name='nextw', shape=[1], data_type='int64', program=program)
name='nextw', shape=[1], data_type='int64', main_program=program)
embed_first = layers.embedding(
input=first_word,
size=[dict_size, embed_size],
data_type='float32',
param_attr={'name': 'shared_w'},
program=program)
main_program=program)
embed_second = layers.embedding(
input=second_word,
size=[dict_size, embed_size],
data_type='float32',
param_attr={'name': 'shared_w'},
program=program)
main_program=program)
embed_third = layers.embedding(
input=third_word,
size=[dict_size, embed_size],
data_type='float32',
param_attr={'name': 'shared_w'},
program=program)
main_program=program)
embed_forth = layers.embedding(
input=forth_word,
size=[dict_size, embed_size],
data_type='float32',
param_attr={'name': 'shared_w'},
program=program)
main_program=program)
concat_embed = layers.concat(
input=[embed_first, embed_second, embed_third, embed_forth],
axis=1,
program=program)
main_program=program)
hidden1 = layers.fc(input=concat_embed,
size=256,
act='sigmoid',
program=program)
main_program=program)
predict_word = layers.fc(input=hidden1,
size=dict_size,
act='softmax',
program=program)
main_program=program)
cost = layers.cross_entropy(
input=predict_word, label=next_word, program=program)
avg_cost = layers.mean(x=cost, program=program)
input=predict_word, label=next_word, main_program=program)
avg_cost = layers.mean(x=cost, main_program=program)
self.assertIsNotNone(avg_cost)
print str(program)
......
python/paddle/v2/framework/tests/test_lod_rank_table.py
浏览文件 @ 51d4afaa
from paddle.v2.framework.layers import lod_rank_table, data
from paddle.v2.framework.executor import Executor
from paddle.v2.framework.framework import g_program
from paddle.v2.framework.framework import g_main_program
import paddle.v2.framework.core as core
import numpy
import unittest
......@@ -19,7 +19,7 @@ class TestLoDRankTable(unittest.TestCase):
tensor.set(numpy.random.random(size=(17, 100)), cpu)
tensor.set_lod([[0, 1, 3], [0, 5, 6, 7], [0, 3, 4, 9, 10, 13, 16, 17]])
exe.run(g_program, scope=scope, feed={'x': tensor})
exe.run(g_main_program, scope=scope, feed={'x': tensor})
var = scope.find_var(rank_table.name)
table = var.get_lod_rank_table()
self.assertEqual([(0, 5), (1, 1), (2, 1)], table.items())
......
python/paddle/v2/framework/tests/test_operator_desc.py
浏览文件 @ 51d4afaa
import unittest
from paddle.v2.framework.framework import Variable, Program, g_program
from paddle.v2.framework.framework import Variable, Program, g_main_program
import paddle.v2.framework.core as core
class TestOperator(unittest.TestCase):
def test_error_type(self):
block = g_program.create_block()
block = g_main_program.create_block()
try:
block.append_op()
self.assertFail()
......
python/paddle/v2/framework/tests/test_parameter.py
浏览文件 @ 51d4afaa
import unittest
from paddle.v2.framework.framework import g_program
from paddle.v2.framework.framework import g_main_program
import paddle.v2.framework.core as core
class TestParameter(unittest.TestCase):
def test_param(self):
b = g_program.create_block()
b = g_main_program.create_block()
param = b.create_parameter(
name='fc.w',
shape=[784, 100],
......
python/paddle/v2/framework/tests/test_program.py
浏览文件 @ 51d4afaa
......@@ -2,35 +2,35 @@ import unittest
import paddle.v2.framework.core as core
from paddle.v2.framework.framework import Program
from paddle.v2.framework.framework import g_program
from paddle.v2.framework.framework import g_main_program
class TestProgram(unittest.TestCase):
def test_program(self):
b = g_program.current_block()
b = g_main_program.current_block()
self.assertEqual(-1, b.parent_idx)
self.assertEqual(0, b.idx)
b = g_program.create_block()
b = g_main_program.create_block()
self.assertEqual(1, b.idx)
self.assertEqual(0, b.parent_idx)
b = g_program.create_block()
b = g_main_program.create_block()
self.assertEqual(2, b.idx)
self.assertEqual(1, b.parent_idx)
g_program.rollback()
g_main_program.rollback()
b = g_program.current_block()
b = g_main_program.current_block()
self.assertEqual(1, b.idx)
self.assertEqual(0, b.parent_idx)
b = g_program.create_block()
b = g_main_program.create_block()
self.assertEqual(3, b.idx)
self.assertEqual(1, b.parent_idx)
g_program.rollback()
b = g_program.current_block()
g_main_program.rollback()
b = g_main_program.current_block()
self.assertEqual(1, b.idx)
self.assertEqual(0, b.parent_idx)
......
python/paddle/v2/framework/tests/test_recognize_digits_conv.py
浏览文件 @ 51d4afaa
......@@ -4,26 +4,26 @@ import paddle.v2.framework.nets as nets
import paddle.v2.framework.core as core
import paddle.v2.framework.optimizer as optimizer
from paddle.v2.framework.framework import Program, g_program
from paddle.v2.framework.framework import Program, g_main_program
from paddle.v2.framework.executor import Executor
import numpy as np
init_program = Program()
program = Program()
startup_program = Program()
main_program = Program()
images = layers.data(
name='pixel',
shape=[1, 28, 28],
data_type='float32',
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
label = layers.data(
name='label',
shape=[1],
data_type='int64',
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
conv_pool_1 = nets.simple_img_conv_pool(
input=images,
filter_size=5,
......@@ -31,8 +31,8 @@ conv_pool_1 = nets.simple_img_conv_pool(
pool_size=2,
pool_stride=2,
act="relu",
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
conv_pool_2 = nets.simple_img_conv_pool(
input=conv_pool_1,
filter_size=5,
......@@ -40,24 +40,30 @@ conv_pool_2 = nets.simple_img_conv_pool(
pool_size=2,
pool_stride=2,
act="relu",
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
predict = layers.fc(input=conv_pool_2,
size=10,
act="softmax",
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
cost = layers.cross_entropy(
input=predict, label=label, program=program, init_program=init_program)
avg_cost = layers.mean(x=cost, program=program)
input=predict,
label=label,
main_program=main_program,
startup_program=startup_program)
avg_cost = layers.mean(x=cost, main_program=main_program)
accuracy = layers.accuracy(
input=predict, label=label, program=program, init_program=init_program)
input=predict,
label=label,
main_program=main_program,
startup_program=startup_program)
# 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, init_program)
opts = optimizer.minimize(avg_cost, startup_program)
BATCH_SIZE = 50
PASS_NUM = 3
......@@ -69,7 +75,7 @@ train_reader = paddle.batch(
place = core.CPUPlace()
exe = Executor(place)
exe.run(init_program, feed={}, fetch_list=[])
exe.run(startup_program, feed={}, fetch_list=[])
for pass_id in range(PASS_NUM):
count = 0
......@@ -84,7 +90,7 @@ for pass_id in range(PASS_NUM):
tensor_img.set(img_data, place)
tensor_y.set(y_data, place)
outs = exe.run(program,
outs = exe.run(main_program,
feed={"pixel": tensor_img,
"label": tensor_y},
fetch_list=[avg_cost, accuracy])
......
python/paddle/v2/framework/tests/test_recognize_digits_mlp.py
浏览文件 @ 51d4afaa
......@@ -11,14 +11,14 @@ from paddle.v2.framework.initializer import UniformInitializer
import numpy as np
BATCH_SIZE = 128
init_program = Program()
program = Program()
startup_program = Program()
main_program = Program()
image = layers.data(
name='x',
shape=[784],
data_type='float32',
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
param_attr = {
'name': None,
......@@ -30,38 +30,45 @@ param_attr = {
hidden1 = layers.fc(input=image,
size=128,
act='relu',
program=program,
init_program=init_program,
main_program=main_program,
startup_program=startup_program,
param_attr=param_attr)
hidden2 = layers.fc(input=hidden1,
size=64,
act='relu',
program=program,
init_program=init_program,
main_program=main_program,
startup_program=startup_program,
param_attr=param_attr)
predict = layers.fc(input=hidden2,
size=10,
act='softmax',
program=program,
init_program=init_program,
main_program=main_program,
startup_program=startup_program,
param_attr=param_attr)
label = layers.data(
name='y',
shape=[1],
data_type='int64',
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
cost = layers.cross_entropy(
input=predict, label=label, program=program, init_program=init_program)
avg_cost = layers.mean(x=cost, program=program, init_program=init_program)
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)
accuracy = layers.accuracy(
input=predict, label=label, program=program, init_program=init_program)
input=predict,
label=label,
main_program=main_program,
startup_program=startup_program)
optimizer = optimizer.MomentumOptimizer(learning_rate=0.001, momentum=0.9)
opts = optimizer.minimize(avg_cost, init_program)
opts = optimizer.minimize(avg_cost, startup_program)
train_reader = paddle.batch(
paddle.reader.shuffle(
......@@ -71,7 +78,7 @@ train_reader = paddle.batch(
place = core.CPUPlace()
exe = Executor(place)
exe.run(init_program, feed={}, fetch_list=[])
exe.run(startup_program, feed={}, fetch_list=[])
PASS_NUM = 100
for pass_id in range(PASS_NUM):
......@@ -86,7 +93,7 @@ for pass_id in range(PASS_NUM):
tensor_y = core.LoDTensor()
tensor_y.set(y_data, place)
outs = exe.run(program,
outs = exe.run(main_program,
feed={'x': tensor_x,
'y': tensor_y},
fetch_list=[avg_cost, accuracy])
......
python/paddle/v2/framework/tests/test_recommender_system.py
浏览文件 @ 51d4afaa
......@@ -4,13 +4,13 @@ import paddle.v2.framework.nets as nets
import paddle.v2.framework.core as core
import paddle.v2.framework.optimizer as optimizer
from paddle.v2.framework.framework import Program, g_program
from paddle.v2.framework.framework import Program, g_main_program
from paddle.v2.framework.executor import Executor
import numpy as np
init_program = Program()
program = Program()
startup_program = Program()
main_program = Program()
is_sparse = True
use_gpu = False
BATCH_SIZE = 256
......@@ -26,8 +26,8 @@ def get_usr_combined_features():
name='user_id',
shape=[1],
data_type='int64',
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
usr_emb = layers.embedding(
input=uid,
......@@ -35,13 +35,13 @@ def get_usr_combined_features():
size=[USR_DICT_SIZE, 32],
param_attr={'name': 'user_table'},
is_sparse=is_sparse,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
usr_fc = layers.fc(input=usr_emb,
size=32,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
USR_GENDER_DICT_SIZE = 2
......@@ -49,75 +49,75 @@ def get_usr_combined_features():
name='gender_id',
shape=[1],
data_type='int64',
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
usr_gender_emb = layers.embedding(
input=usr_gender_id,
size=[USR_GENDER_DICT_SIZE, 16],
param_attr={'name': 'gender_table'},
is_sparse=is_sparse,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
usr_gender_fc = layers.fc(input=usr_gender_emb,
size=16,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
USR_AGE_DICT_SIZE = len(paddle.dataset.movielens.age_table)
usr_age_id = layers.data(
name='age_id',
shape=[1],
data_type="int64",
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
usr_age_emb = layers.embedding(
input=usr_age_id,
size=[USR_AGE_DICT_SIZE, 16],
is_sparse=is_sparse,
param_attr={'name': 'age_table'},
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
usr_age_fc = layers.fc(input=usr_age_emb,
size=16,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
USR_JOB_DICT_SIZE = paddle.dataset.movielens.max_job_id() + 1
usr_job_id = layers.data(
name='job_id',
shape=[1],
data_type="int64",
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
usr_job_emb = layers.embedding(
input=usr_job_id,
size=[USR_JOB_DICT_SIZE, 16],
param_attr={'name': 'job_table'},
is_sparse=is_sparse,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
usr_job_fc = layers.fc(input=usr_job_emb,
size=16,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
concat_embed = layers.concat(
input=[usr_fc, usr_gender_fc, usr_age_fc, usr_job_fc],
axis=1,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
usr_combined_features = layers.fc(input=concat_embed,
size=200,
act="tanh",
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
return usr_combined_features
......@@ -130,8 +130,8 @@ def get_mov_combined_features():
name='movie_id',
shape=[1],
data_type='int64',
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
mov_emb = layers.embedding(
input=mov_id,
......@@ -139,13 +139,13 @@ def get_mov_combined_features():
size=[MOV_DICT_SIZE, 32],
param_attr={'name': 'movie_table'},
is_sparse=is_sparse,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
mov_fc = layers.fc(input=mov_emb,
size=32,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
CATEGORY_DICT_SIZE = len(paddle.dataset.movielens.movie_categories())
......@@ -153,21 +153,21 @@ def get_mov_combined_features():
name='category_id',
shape=[1],
data_type='int64',
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
mov_categories_emb = layers.embedding(
input=category_id,
size=[CATEGORY_DICT_SIZE, 32],
is_sparse=is_sparse,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
mov_categories_hidden = layers.sequence_pool(
input=mov_categories_emb,
pool_type="sum",
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
MOV_TITLE_DICT_SIZE = len(paddle.dataset.movielens.get_movie_title_dict())
......@@ -175,15 +175,15 @@ def get_mov_combined_features():
name='movie_title',
shape=[1],
data_type='int64',
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
mov_title_emb = layers.embedding(
input=mov_title_id,
size=[MOV_TITLE_DICT_SIZE, 32],
is_sparse=is_sparse,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
mov_title_conv = nets.sequence_conv_pool(
input=mov_title_emb,
......@@ -191,21 +191,21 @@ def get_mov_combined_features():
filter_size=3,
act="tanh",
pool_type="sum",
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
concat_embed = layers.concat(
input=[mov_fc, mov_categories_hidden, mov_title_conv],
axis=1,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
# FIXME(dzh) : need tanh operator
mov_combined_features = layers.fc(input=concat_embed,
size=200,
act="tanh",
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
return mov_combined_features
......@@ -218,24 +218,26 @@ def model():
inference = layers.cos_sim(
X=usr_combined_features,
Y=mov_combined_features,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
label = layers.data(
name='score',
shape=[1],
data_type='float32',
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
square_cost = layers.square_error_cost(
input=inference,
label=label,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
avg_cost = layers.mean(
x=square_cost, program=program, init_program=init_program)
x=square_cost,
main_program=main_program,
startup_program=startup_program)
return avg_cost
......@@ -243,8 +245,8 @@ def model():
def main():
cost = model()
sgd_optimizer = optimizer.SGDOptimizer(learning_rate=0.2)
opts = sgd_optimizer.minimize(cost, init_program=init_program)
block = program.block(0)
opts = sgd_optimizer.minimize(cost, startup_program=startup_program)
block = main_program.block(0)
if use_gpu:
place = core.GPUPlace(0)
......@@ -252,7 +254,7 @@ def main():
place = core.CPUPlace()
exe = Executor(place)
exe.run(init_program, feed={}, fetch_list=[])
exe.run(startup_program, feed={}, fetch_list=[])
train_reader = paddle.batch(
paddle.reader.shuffle(
......@@ -301,7 +303,7 @@ def main():
PASS_NUM = 100
for pass_id in range(PASS_NUM):
for data in train_reader():
outs = exe.run(program,
outs = exe.run(main_program,
feed=func_feed(feeding, data),
fetch_list=[cost])
out = np.array(outs[0])
......
python/paddle/v2/framework/tests/test_recurrent_op.py
浏览文件 @ 51d4afaa
......@@ -99,17 +99,17 @@ class RecurrentOpTest1(unittest.TestCase):
batch_size = 1
sent_len = 1
def init_program(self):
self.program = Program()
self.init_program = Program()
def setup_program(self):
self.main_program = Program()
self.startup_program = Program()
self.p_info = {
"program": self.program,
"init_program": self.init_program
"main_program": self.main_program,
"startup_program": self.startup_program
}
self.place = core.CPUPlace()
def setUp(self):
self.init_program()
self.setup_program()
self.data_field = {"x", "h_boot"}
self.input_shape = (self.sent_len, self.batch_size, self.input_dim)
......@@ -131,7 +131,7 @@ class RecurrentOpTest1(unittest.TestCase):
name='h_boot',
**self.p_info)
rnn = StaticRNN(program=self.program)
rnn = StaticRNN(main_program=self.main_program)
with rnn.step():
h_pre = rnn.memory(init=h_boot)
x_t = rnn.step_input(x)
......@@ -153,7 +153,7 @@ class RecurrentOpTest1(unittest.TestCase):
for x in self.data_field
}
exe = Executor(self.place)
out = exe.run(self.program,
out = exe.run(self.main_program,
feed=self.feed_map,
fetch_list=[self.output])
......@@ -165,12 +165,14 @@ class RecurrentOpTest1(unittest.TestCase):
for x in self.data_field
}
fetch_list = [
self.program.global_block().var(x + "@GRAD")
self.main_program.global_block().var(x + "@GRAD")
for x in self.data_field
]
exe = Executor(self.place)
return exe.run(self.program, feed=self.feed_map, fetch_list=fetch_list)
return exe.run(self.main_program,
feed=self.feed_map,
fetch_list=fetch_list)
def test_backward(self):
self.check_forward()
......@@ -237,7 +239,7 @@ class RecurrentOpTest2(RecurrentOpTest1):
sent_len = 2
def setUp(self):
self.init_program()
self.setup_program()
self.data_field = {"x", "h_boot", "W", "U"}
......@@ -260,7 +262,7 @@ class RecurrentOpTest2(RecurrentOpTest1):
name='h_boot',
**self.p_info)
rnn = StaticRNN(program=self.program)
rnn = StaticRNN(main_program=self.main_program)
with rnn.step():
h_pre = rnn.memory(init=h_boot)
x_t = rnn.step_input(x)
......@@ -333,7 +335,7 @@ class RecurrentOpTest3(RecurrentOpTest1):
sent_len = 2
def setUp(self):
self.init_program()
self.setup_program()
self.data_field = {"x", "h_boot1", "h_boot2"}
......@@ -364,7 +366,7 @@ class RecurrentOpTest3(RecurrentOpTest1):
append_batch_size=False,
**self.p_info)
rnn = StaticRNN(program=self.program)
rnn = StaticRNN(main_program=self.main_program)
with rnn.step():
h_pre1 = rnn.memory(init=h_boot1)
h_pre2 = rnn.memory(init=h_boot2)
......
python/paddle/v2/framework/tests/test_understand_sentiment_conv.py
浏览文件 @ 51d4afaa
......@@ -4,7 +4,7 @@ import paddle.v2.framework.nets as nets
import paddle.v2.framework.core as core
import paddle.v2.framework.optimizer as optimizer
from paddle.v2.framework.framework import Program, g_program, g_init_program
from paddle.v2.framework.framework import Program, g_main_program, g_startup_program
from paddle.v2.framework.executor import Executor
import numpy as np
......@@ -70,7 +70,7 @@ def main():
place = core.CPUPlace()
exe = Executor(place)
exe.run(g_init_program)
exe.run(g_startup_program)
for pass_id in xrange(PASS_NUM):
for data in train_data():
......@@ -82,7 +82,7 @@ def main():
tensor_label = core.LoDTensor()
tensor_label.set(label, place)
outs = exe.run(g_program,
outs = exe.run(g_main_program,
feed={"words": tensor_words,
"label": tensor_label},
fetch_list=[cost, acc])
......
python/paddle/v2/framework/tests/test_variable.py
浏览文件 @ 51d4afaa
import unittest
from paddle.v2.framework.framework import Variable, g_program, Program
from paddle.v2.framework.framework import Variable, g_main_program, Program
import paddle.v2.framework.core as core
import numpy as np
......@@ -18,7 +18,7 @@ class TestVariable(unittest.TestCase):
self.assertRaises(ValueError, lambda: convert("int8"))
def test_var(self):
b = g_program.current_block()
b = g_main_program.current_block()
w = b.create_var(
dtype="float64", shape=[784, 100], lod_level=0, name="fc.w")
self.assertNotEqual(str(w), "")
......
python/paddle/v2/framework/tests/test_word2vec.py
浏览文件 @ 51d4afaa
......@@ -3,13 +3,13 @@ import paddle.v2.framework.layers as layers
import paddle.v2.framework.core as core
import paddle.v2.framework.optimizer as optimizer
from paddle.v2.framework.framework import Program, g_program
from paddle.v2.framework.framework import Program, g_main_program
from paddle.v2.framework.executor import Executor
import numpy as np
init_program = Program()
program = Program()
startup_program = Program()
main_program = Program()
embed_size = 32
hidden_size = 256
......@@ -24,32 +24,32 @@ first_word = layers.data(
name='firstw',
shape=[1],
data_type='int64',
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
second_word = layers.data(
name='secondw',
shape=[1],
data_type='int64',
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
third_word = layers.data(
name='thirdw',
shape=[1],
data_type='int64',
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
forth_word = layers.data(
name='forthw',
shape=[1],
data_type='int64',
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
next_word = layers.data(
name='nextw',
shape=[1],
data_type='int64',
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
embed_first = layers.embedding(
input=first_word,
......@@ -57,16 +57,16 @@ embed_first = layers.embedding(
data_type='float32',
is_sparse=is_sparse,
param_attr={'name': 'shared_w'},
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
embed_second = layers.embedding(
input=second_word,
size=[dict_size, embed_size],
data_type='float32',
is_sparse=is_sparse,
param_attr={'name': 'shared_w'},
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
embed_third = layers.embedding(
input=third_word,
......@@ -74,42 +74,43 @@ embed_third = layers.embedding(
data_type='float32',
is_sparse=is_sparse,
param_attr={'name': 'shared_w'},
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
embed_forth = layers.embedding(
input=forth_word,
size=[dict_size, embed_size],
data_type='float32',
is_sparse=is_sparse,
param_attr={'name': 'shared_w'},
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
concat_embed = layers.concat(
input=[embed_first, embed_second, embed_third, embed_forth],
axis=1,
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
hidden1 = layers.fc(input=concat_embed,
size=hidden_size,
act='sigmoid',
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
predict_word = layers.fc(input=hidden1,
size=dict_size,
act='softmax',
program=program,
init_program=init_program)
main_program=main_program,
startup_program=startup_program)
cost = layers.cross_entropy(
input=predict_word,
label=next_word,
program=program,
init_program=init_program)
avg_cost = layers.mean(x=cost, program=program, init_program=init_program)
main_program=main_program,
startup_program=startup_program)
avg_cost = layers.mean(
x=cost, main_program=main_program, startup_program=startup_program)
sgd_optimizer = optimizer.SGDOptimizer(learning_rate=0.001)
opts = sgd_optimizer.minimize(avg_cost, init_program)
opts = sgd_optimizer.minimize(avg_cost, startup_program)
train_reader = paddle.batch(
paddle.dataset.imikolov.train(word_dict, N), batch_size)
......@@ -117,7 +118,7 @@ train_reader = paddle.batch(
place = core.CPUPlace()
exe = Executor(place)
exe.run(init_program, feed={}, fetch_list=[])
exe.run(startup_program, feed={}, fetch_list=[])
PASS_NUM = 100
for pass_id in range(PASS_NUM):
for data in train_reader():
......@@ -145,7 +146,7 @@ for pass_id in range(PASS_NUM):
next_tensor = core.LoDTensor()
next_tensor.set(next_data, place)
outs = exe.run(program,
outs = exe.run(main_program,
feed={
'firstw': first_tensor,
'secondw': second_tensor,
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或