def parse_new_rnn():
data = layer.data(name="word",
type=data_type.dense_vector(dict_dim))
label = layer.data(name="label",
type=data_type.dense_vector(label_dim))
emb = layer.embedding(input=data, size=word_dim)
boot_layer = layer.data(name="boot",
type=data_type.dense_vector(10))
boot_layer = layer.fc(name='boot_fc', input=boot_layer, size=10)
def step(y, wid):
z = layer.embedding(input=wid, size=word_dim)
mem = layer.memory(name="rnn_state",
size=hidden_dim,
boot_layer=boot_layer)
out = layer.fc(input=[y, z, mem],
size=hidden_dim,
act=activation.Tanh(),
bias_attr=True,
name="rnn_state")
return out
out = layer.recurrent_group(name="rnn",
step=step,
input=[emb, data])
rep = layer.last_seq(input=out)
prob = layer.fc(size=label_dim,
input=rep,
act=activation.Softmax(),
bias_attr=True)
cost = layer.classification_cost(input=prob, label=label)
return str(layer.parse_network(cost))
def test_evaluator(self):
img = layer.data(name='pixel2', type=data_type.dense_vector(784))
output = layer.fc(input=img,
size=10,
act=activation.Softmax(),
name='fc_here')
lbl = layer.data(name='label2', type=data_type.integer_value(10))
cost = layer.cross_entropy_cost(input=output, label=lbl)
evaluator.classification_error(input=output, label=lbl)
print layer.parse_network(cost)
print layer.parse_network(output)
def network(self):
"""
Implements the detail of the model.
"""
self.check_and_create_data()
self.create_shared_params()
q_enc = self.get_enc(self.q_ids, type='q')
a_enc = self.get_enc(self.a_ids, type='q')
q_proj_left = layer.fc(size=self.emb_dim * 2,
bias_attr=False,
param_attr=Attr.Param(self.name + '_left.wq'),
input=q_enc)
q_proj_right = layer.fc(size=self.emb_dim * 2,
bias_attr=False,
param_attr=Attr.Param(self.name + '_right.wq'),
input=q_enc)
left_match = self.recurrent_group(
self.name + '_left',
[layer.StaticInput(q_enc),
layer.StaticInput(q_proj_left), a_enc],
reverse=False)
right_match = self.recurrent_group(
self.name + '_right',
[layer.StaticInput(q_enc),
layer.StaticInput(q_proj_right), a_enc],
reverse=True)
match_seq = layer.concat(input=[left_match, right_match])
with layer.mixed(size=match_seq.size,
act=Act.Identity(),
layer_attr=Attr.ExtraLayerAttribute(drop_rate=0.2),
bias_attr=False) as dropped:
dropped += layer.identity_projection(match_seq)
match_result = layer.pooling(input=dropped,
pooling_type=paddle.pooling.Max())
cls = layer.fc(input=match_result,
act=Act.Softmax(),
size=self.label_dim)
return cls
import paddle.v2.layer as layer
import paddle.v2.pooling as pooling
import paddle.v2.networks as networks
pixel = layer.data(name='pixel', type=data_type.dense_vector(128))
label = layer.data(name='label', type=data_type.integer_value(10))
weight = layer.data(name='weight', type=data_type.dense_vector(1))
combine_weight = layer.data(name='weight_combine',
type=data_type.dense_vector(10))
score = layer.data(name='score', type=data_type.dense_vector(1))
hidden = layer.fc(input=pixel,
size=100,
act=activation.Sigmoid(),
param_attr=attr.Param(name='hidden'))
inference = layer.fc(input=hidden, size=10, act=activation.Softmax())
conv = layer.img_conv(input=pixel,
filter_size=1,
filter_size_y=1,
num_channels=8,
num_filters=16,
act=activation.Linear())
class ImageLayerTest(unittest.TestCase):
def test_conv_layer(self):
conv_shift = layer.conv_shift(a=pixel, b=score)
print layer.parse_network(conv, conv_shift)
def test_pooling_layer(self):
maxpool = layer.img_pool(input=conv,
