def __init__(self,
dnn_layer_dims,
dnn_input_dim,
lr_input_dim,
model_type=ModelType.create_classification(),
is_infer=False):
'''
@dnn_layer_dims: list of integer
DNN每一层的维度
@dnn_input_dim: int
DNN输入层的大小
@lr_input_dim: int
LR输入层大小
@is_infer: bool
是否建立预估模型
'''
self.dnn_layer_dims = dnn_layer_dims
self.dnn_input_dim = dnn_input_dim
self.lr_input_dim = lr_input_dim
self.model_type = model_type
self.is_infer = is_infer
self._declare_input_layers()
self.dnn = self._build_dnn_submodel_(self.dnn_layer_dims)
self.lr = self._build_lr_submodel_()
# 模型预测
if self.model_type.is_classification():
self.model = self._build_classification_model(self.dnn, self.lr)
if self.model_type.is_regression():
self.model = self._build_regression_model(self.dnn, self.lr)
def __init__(self,
dnn_layer_dims,
dnn_input_dim,
lr_input_dim,
model_type=ModelType.create_classification(),
is_infer=False):
'''
@dnn_layer_dims: list of integer
dims of each layer in dnn
@dnn_input_dim: int
size of dnn's input layer
@lr_input_dim: int
size of lr's input layer
@is_infer: bool
whether to build a infer model
'''
self.dnn_layer_dims = dnn_layer_dims
self.dnn_input_dim = dnn_input_dim
self.lr_input_dim = lr_input_dim
self.model_type = model_type
self.is_infer = is_infer
self._declare_input_layers()
self.dnn = self._build_dnn_submodel_(self.dnn_layer_dims)
self.lr = self._build_lr_submodel_()
# model's prediction
# TODO(superjom) rename it to prediction
if self.model_type.is_classification():
self.model = self._build_classification_model(self.dnn, self.lr)
if self.model_type.is_regression():
self.model = self._build_regression_model(self.dnn, self.lr)
def __init__(self,
dnn_dims=[],
vocab_sizes=[],
model_type=ModelType.create_classification(),
model_arch=ModelArch.create_rnn(),
share_semantic_generator=False,
class_num=2,
share_embed=False,
is_infer=False):
"""
init dssm network
:param dnn_dims: list of int (dimentions of each layer in semantic vector generator.)
:param vocab_sizes: 2d tuple (size of both left and right items.)
:param model_type: classification
:param model_arch: model architecture
:param share_semantic_generator: bool (whether to share the semantic vector generator for both left and right.)
:param class_num: number of categories.
:param share_embed: bool (whether to share the embeddings between left and right.)
:param is_infer: inference
"""
assert len(vocab_sizes) == 2, (
"vocab sizes specify the sizes left and right inputs, dim is 2.")
assert len(dnn_dims) > 1, "more than two layers is needed."
self.dnn_dims = dnn_dims
self.vocab_sizes = vocab_sizes
self.share_semantic_generator = share_semantic_generator
self.share_embed = share_embed
self.model_type = ModelType(model_type)
self.model_arch = ModelArch(model_arch)
self.class_num = class_num
self.is_infer = is_infer
logger.warning("build DSSM model with config of %s, %s" %
(self.model_type, self.model_arch))
logger.info("vocabulary sizes: %s" % str(self.vocab_sizes))
_model_arch = {
"rnn": self.create_rnn,
"cnn": self.create_cnn,
"fc": self.create_fc,
}
def _model_arch_creater(emb, prefix=""):
sent_vec = _model_arch.get(str(model_arch))(emb, prefix)
dnn = self.create_dnn(sent_vec, prefix)
return dnn
self.model_arch_creater = _model_arch_creater
self.model_type_creater = self._build_classification_model
def train(data_path=None,
model_type=ModelType.create_classification(),
batch_size=100,
num_passes=50,
class_num=None,
num_workers=1,
use_gpu=False):
'''
Train the DNN.
'''
paddle.init(use_gpu=use_gpu, trainer_count=num_workers)
# network config
input_layer = paddle.layer.data(name='input_layer', type=paddle.data_type.dense_vector(feature_dim))
dnn = create_dnn(input_layer)
prediction = None
label = None
cost = None
if args.model_type.is_classification():
prediction = paddle.layer.fc(input=dnn, size=class_num, act=paddle.activation.Softmax())
label = paddle.layer.data(name='label', type=paddle.data_type.integer_value(class_num))
cost = paddle.layer.classification_cost(input=prediction, label=label)
elif args.model_type.is_regression():
prediction = paddle.layer.fc(input=dnn, size=1, act=paddle.activation.Linear())
label = paddle.layer.data(name='label', type=paddle.data_type.dense_vector(1))
cost = paddle.layer.mse_cost(input=prediction, label=label)
# create parameters
parameters = paddle.parameters.create(cost)
# create optimizer
optimizer = paddle.optimizer.Momentum(momentum=0)
trainer = paddle.trainer.SGD(
cost=cost,
extra_layers=paddle.evaluator.auc(input=prediction, label=label),
parameters=parameters, update_equation=optimizer)
feeding = {'input_layer': 0, 'label': 1}
# event_handler to print training and testing info
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 100 == 0:
print "Pass %d, Batch %d, Cost %f, %s" % (
event.pass_id, event.batch_id, event.cost, event.metrics)
if isinstance(event, paddle.event.EndPass):
result = trainer.test(
reader=paddle.batch(reader.test(data_path,
feature_dim+1,
args.model_type.is_classification()),
batch_size=batch_size),
feeding=feeding)
print "Test %d, Cost %f, %s" % (event.pass_id, result.cost, result.metrics)
model_desc = "{type}".format(
type=str(args.model_type))
with open("%sdnn_%s_pass_%05d.tar" %
(args.model_output_prefix, model_desc,
event.pass_id), "w") as f:
parameters.to_tar(f)
# training
trainer.train(
reader=paddle.batch(
paddle.reader.shuffle(reader.train(data_path,
feature_dim+1,
args.model_type.is_classification()),
buf_size=batch_size*10),
batch_size=batch_size),
feeding=feeding,
event_handler=event_handler,
num_passes=num_passes)
def __init__(self,
dnn_dims=[],
vocab_sizes=[],
model_type=ModelType.create_classification(),
model_arch=ModelArch.create_cnn(),
share_semantic_generator=False,
class_num=None,
share_embed=False,
is_infer=False):
"""
:param dnn_dims: The dimention of each layer in the semantic vector
generator.
:type dnn_dims: list of int
:param vocab_sizes: The size of left and right items.
:type vocab_sizes: A list having 2 elements.
:param model_type: The type of task to train the DSSM model. The value
should be "rank: 0", "regression: 1" or
"classification: 2".
:type model_type: int
:param model_arch: A value indicating the model architecture to use.
:type model_arch: int
:param share_semantic_generator: A flag indicating whether to share the
semantic vector between the left and
the right item.
:type share_semantic_generator: bool
:param share_embed: A floag indicating whether to share the embeddings
between the left and the right item.
:type share_embed: bool
:param class_num: The number of categories.
:type class_num: int
"""
assert len(vocab_sizes) == 2, (
"The vocab_sizes specifying the sizes left and right inputs. "
"Its dimension should be 2.")
assert len(dnn_dims) > 1, ("In the DNN model, more than two layers "
"are needed.")
self.dnn_dims = dnn_dims
self.vocab_sizes = vocab_sizes
self.share_semantic_generator = share_semantic_generator
self.share_embed = share_embed
self.model_type = ModelType(model_type)
self.model_arch = ModelArch(model_arch)
self.class_num = class_num
self.is_infer = is_infer
logger.warning("Build DSSM model with config of %s, %s" %
(self.model_type, self.model_arch))
logger.info("The vocabulary size is : %s" % str(self.vocab_sizes))
# bind model architecture
_model_arch = {
"cnn": self.create_cnn,
"fc": self.create_fc,
"rnn": self.create_rnn,
}
def _model_arch_creater(emb, prefix=""):
sent_vec = _model_arch.get(str(model_arch))(emb, prefix)
dnn = self.create_dnn(sent_vec, prefix)
return dnn
self.model_arch_creater = _model_arch_creater
_model_type = {
"classification": self._build_classification_model,
"rank": self._build_rank_model,
"regression": self._build_regression_model,
}
print("model type: ", str(self.model_type))
self.model_type_creater = _model_type[str(self.model_type)]
def train(train_data_path=None,
test_data_path=None,
source_dic_path=None,
target_dic_path=None,
model_type=ModelType.create_classification(),
model_arch=ModelArch.create_cnn(),
batch_size=10,
num_passes=10,
share_semantic_generator=False,
share_embed=False,
class_num=None,
num_workers=1,
use_gpu=False):
'''
Train the DSSM.
'''
default_train_path = './data/rank/train.txt'
default_test_path = './data/rank/test.txt'
default_dic_path = './data/vocab.txt'
if not model_type.is_rank():
default_train_path = './data/classification/train.txt'
default_test_path = './data/classification/test.txt'
use_default_data = not train_data_path
if use_default_data:
train_data_path = default_train_path
test_data_path = default_test_path
source_dic_path = default_dic_path
target_dic_path = default_dic_path
dataset = reader.Dataset(
train_path=train_data_path,
test_path=test_data_path,
source_dic_path=source_dic_path,
target_dic_path=target_dic_path,
model_type=model_type,
)
train_reader = paddle.batch(paddle.reader.shuffle(dataset.train,
buf_size=1000),
batch_size=batch_size)
test_reader = paddle.batch(paddle.reader.shuffle(dataset.test,
buf_size=1000),
batch_size=batch_size)
paddle.init(use_gpu=use_gpu, trainer_count=num_workers)
cost, prediction, label = DSSM(
dnn_dims=layer_dims,
vocab_sizes=[
len(load_dic(path)) for path in [source_dic_path, target_dic_path]
],
model_type=model_type,
model_arch=model_arch,
share_semantic_generator=share_semantic_generator,
class_num=class_num,
share_embed=share_embed)()
parameters = paddle.parameters.create(cost)
adam_optimizer = paddle.optimizer.Adam(
learning_rate=1e-3,
regularization=paddle.optimizer.L2Regularization(rate=1e-3),
model_average=paddle.optimizer.ModelAverage(average_window=0.5))
trainer = paddle.trainer.SGD(
cost=cost,
extra_layers=paddle.evaluator.auc(input=prediction, label=label)
if not model_type.is_rank() else None,
parameters=parameters,
update_equation=adam_optimizer)
feeding = {}
if model_type.is_classification() or model_type.is_regression():
feeding = {'source_input': 0, 'target_input': 1, 'label_input': 2}
else:
feeding = {
'source_input': 0,
'left_target_input': 1,
'right_target_input': 2,
'label_input': 3
}
def _event_handler(event):
'''
Define batch handler
'''
if isinstance(event, paddle.event.EndIteration):
# output train log
if event.batch_id % args.num_batches_to_log == 0:
logger.info(
"Pass %d, Batch %d, Cost %f, %s" %
(event.pass_id, event.batch_id, event.cost, event.metrics))
# test model
if event.batch_id > 0 and event.batch_id % args.num_batches_to_test == 0:
if test_reader is not None:
if model_type.is_classification():
result = trainer.test(reader=test_reader,
feeding=feeding)
logger.info("Test at Pass %d, %s" %
(event.pass_id, result.metrics))
else:
result = None
# save model
if event.batch_id > 0 and event.batch_id % args.num_batches_to_save_model == 0:
model_desc = "{type}_{arch}".format(type=str(args.model_type),
arch=str(args.model_arch))
with open(
"%sdssm_%s_pass_%05d.tar" %
(args.model_output_prefix, model_desc, event.pass_id),
"w") as f:
parameters.to_tar(f)
trainer.train(reader=train_reader,
event_handler=_event_handler,
feeding=feeding,
num_passes=num_passes)
logger.info("Training has finished.")
def __init__(self,
dnn_dims=[],
vocab_sizes=[],
model_type=ModelType.create_classification(),
model_arch=ModelArch.create_cnn(),
share_semantic_generator=False,
class_num=None,
share_embed=False,
is_infer=False):
'''
@dnn_dims: list of int
dimentions of each layer in semantic vector generator.
@vocab_sizes: 2-d tuple
size of both left and right items.
@model_type: int
type of task, should be 'rank: 0', 'regression: 1' or 'classification: 2'
@model_arch: int
model architecture
@share_semantic_generator: bool
whether to share the semantic vector generator for both left and right.
@share_embed: bool
whether to share the embeddings between left and right.
@class_num: int
number of categories.
'''
assert len(
vocab_sizes
) == 2, "vocab_sizes specify the sizes left and right inputs, and dim should be 2."
assert len(dnn_dims) > 1, "more than two layers is needed."
self.dnn_dims = dnn_dims
self.vocab_sizes = vocab_sizes
self.share_semantic_generator = share_semantic_generator
self.share_embed = share_embed
self.model_type = ModelType(model_type)
self.model_arch = ModelArch(model_arch)
self.class_num = class_num
self.is_infer = is_infer
logger.warning("build DSSM model with config of %s, %s" %
(self.model_type, self.model_arch))
logger.info("vocabulary sizes: %s" % str(self.vocab_sizes))
# bind model architecture
_model_arch = {
'cnn': self.create_cnn,
'fc': self.create_fc,
'rnn': self.create_rnn,
}
def _model_arch_creater(emb, prefix=''):
sent_vec = _model_arch.get(str(model_arch))(emb, prefix)
dnn = self.create_dnn(sent_vec, prefix)
return dnn
self.model_arch_creater = _model_arch_creater
# build model type
_model_type = {
'classification': self._build_classification_model,
'rank': self._build_rank_model,
'regression': self._build_regression_model,
}
print 'model type: ', str(self.model_type)
self.model_type_creater = _model_type[str(self.model_type)]