Yu Yang
8 years ago
commit
5905d0e88e
@ -1,92 +0,0 @@
|
||||
import paddle.v2 as paddle
|
||||
|
||||
|
||||
def seqToseq_net_v2(source_dict_dim, target_dict_dim):
|
||||
### Network Architecture
|
||||
word_vector_dim = 512 # dimension of word vector
|
||||
decoder_size = 512 # dimension of hidden unit in GRU Decoder network
|
||||
encoder_size = 512 # dimension of hidden unit in GRU Encoder network
|
||||
|
||||
#### Encoder
|
||||
src_word_id = paddle.layer.data(
|
||||
name='source_language_word',
|
||||
type=paddle.data_type.integer_value_sequence(source_dict_dim))
|
||||
src_embedding = paddle.layer.embedding(
|
||||
input=src_word_id,
|
||||
size=word_vector_dim,
|
||||
param_attr=paddle.attr.ParamAttr(name='_source_language_embedding'))
|
||||
src_forward = paddle.networks.simple_gru(
|
||||
input=src_embedding, size=encoder_size)
|
||||
src_backward = paddle.networks.simple_gru(
|
||||
input=src_embedding, size=encoder_size, reverse=True)
|
||||
encoded_vector = paddle.layer.concat(input=[src_forward, src_backward])
|
||||
|
||||
#### Decoder
|
||||
with paddle.layer.mixed(size=decoder_size) as encoded_proj:
|
||||
encoded_proj += paddle.layer.full_matrix_projection(
|
||||
input=encoded_vector)
|
||||
|
||||
backward_first = paddle.layer.first_seq(input=src_backward)
|
||||
|
||||
with paddle.layer.mixed(
|
||||
size=decoder_size, act=paddle.activation.Tanh()) as decoder_boot:
|
||||
decoder_boot += paddle.layer.full_matrix_projection(
|
||||
input=backward_first)
|
||||
|
||||
def gru_decoder_with_attention(enc_vec, enc_proj, current_word):
|
||||
|
||||
decoder_mem = paddle.layer.memory(
|
||||
name='gru_decoder', size=decoder_size, boot_layer=decoder_boot)
|
||||
|
||||
context = paddle.networks.simple_attention(
|
||||
encoded_sequence=enc_vec,
|
||||
encoded_proj=enc_proj,
|
||||
decoder_state=decoder_mem)
|
||||
|
||||
with paddle.layer.mixed(size=decoder_size * 3) as decoder_inputs:
|
||||
decoder_inputs += paddle.layer.full_matrix_projection(input=context)
|
||||
decoder_inputs += paddle.layer.full_matrix_projection(
|
||||
input=current_word)
|
||||
|
||||
gru_step = paddle.layer.gru_step(
|
||||
name='gru_decoder',
|
||||
input=decoder_inputs,
|
||||
output_mem=decoder_mem,
|
||||
size=decoder_size)
|
||||
|
||||
with paddle.layer.mixed(
|
||||
size=target_dict_dim,
|
||||
bias_attr=True,
|
||||
act=paddle.activation.Softmax()) as out:
|
||||
out += paddle.layer.full_matrix_projection(input=gru_step)
|
||||
return out
|
||||
|
||||
decoder_group_name = "decoder_group"
|
||||
group_input1 = paddle.layer.StaticInputV2(input=encoded_vector, is_seq=True)
|
||||
group_input2 = paddle.layer.StaticInputV2(input=encoded_proj, is_seq=True)
|
||||
group_inputs = [group_input1, group_input2]
|
||||
|
||||
trg_embedding = paddle.layer.embedding(
|
||||
input=paddle.layer.data(
|
||||
name='target_language_word',
|
||||
type=paddle.data_type.integer_value_sequence(target_dict_dim)),
|
||||
size=word_vector_dim,
|
||||
param_attr=paddle.attr.ParamAttr(name='_target_language_embedding'))
|
||||
group_inputs.append(trg_embedding)
|
||||
|
||||
# For decoder equipped with attention mechanism, in training,
|
||||
# target embeding (the groudtruth) is the data input,
|
||||
# while encoded source sequence is accessed to as an unbounded memory.
|
||||
# Here, the StaticInput defines a read-only memory
|
||||
# for the recurrent_group.
|
||||
decoder = paddle.layer.recurrent_group(
|
||||
name=decoder_group_name,
|
||||
step=gru_decoder_with_attention,
|
||||
input=group_inputs)
|
||||
|
||||
lbl = paddle.layer.data(
|
||||
name='target_language_next_word',
|
||||
type=paddle.data_type.integer_value_sequence(target_dict_dim))
|
||||
cost = paddle.layer.classification_cost(input=decoder, label=lbl)
|
||||
|
||||
return cost
|
||||
@ -0,0 +1,60 @@
|
||||
import unittest
|
||||
import sys
|
||||
|
||||
try:
|
||||
import py_paddle
|
||||
|
||||
del py_paddle
|
||||
except ImportError:
|
||||
print >> sys.stderr, "It seems swig of Paddle is not installed, this " \
|
||||
"unittest will not be run."
|
||||
sys.exit(0)
|
||||
|
||||
import paddle.v2.parameters as parameters
|
||||
from paddle.proto.ParameterConfig_pb2 import ParameterConfig
|
||||
import random
|
||||
import cStringIO
|
||||
import numpy
|
||||
|
||||
|
||||
def __rand_param_config__(name):
|
||||
conf = ParameterConfig()
|
||||
conf.name = name
|
||||
size = 1
|
||||
for i in xrange(2):
|
||||
dim = random.randint(1, 1000)
|
||||
conf.dims.append(dim)
|
||||
size *= dim
|
||||
conf.size = size
|
||||
assert conf.IsInitialized()
|
||||
return conf
|
||||
|
||||
|
||||
class TestParameters(unittest.TestCase):
|
||||
def test_serialization(self):
|
||||
params = parameters.Parameters()
|
||||
params.__append_config__(__rand_param_config__("param_0"))
|
||||
params.__append_config__(__rand_param_config__("param_1"))
|
||||
|
||||
for name in params.names():
|
||||
param = params.get(name)
|
||||
param[:] = numpy.random.uniform(
|
||||
-1.0, 1.0, size=params.get_shape(name))
|
||||
params.set(name, param)
|
||||
|
||||
tmp_file = cStringIO.StringIO()
|
||||
params.to_tar(tmp_file)
|
||||
tmp_file.seek(0)
|
||||
params_dup = parameters.Parameters.from_tar(tmp_file)
|
||||
|
||||
self.assertEqual(params_dup.names(), params.names())
|
||||
|
||||
for name in params.names():
|
||||
self.assertEqual(params.get_shape(name), params_dup.get_shape(name))
|
||||
p0 = params.get(name)
|
||||
p1 = params_dup.get(name)
|
||||
self.assertTrue(numpy.isclose(p0, p1).all())
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
Loading…
Reference in new issue