def test():
data = conf_helps.data_layer(name="word", size=dict_dim)
label = conf_helps.data_layer(name="label", size=label_dim)
emb = conf_helps.embedding_layer(input=data, size=word_dim)
boot_layer = conf_helps.data_layer(name="boot", size=10)
boot_layer = conf_helps.fc_layer(
name='boot_fc', input=boot_layer, size=10)
def step(y, wid):
z = conf_helps.embedding_layer(input=wid, size=word_dim)
mem = conf_helps.memory(
name="rnn_state",
size=hidden_dim,
boot_layer=boot_layer)
out = conf_helps.fc_layer(
input=[y, z, mem],
size=hidden_dim,
act=conf_helps.TanhActivation(),
bias_attr=True,
name="rnn_state")
return out
out = conf_helps.recurrent_group(
name="rnn", step=step, input=[emb, data])
rep = conf_helps.last_seq(input=out)
prob = conf_helps.fc_layer(
size=label_dim,
input=rep,
act=conf_helps.SoftmaxActivation(),
bias_attr=True)
conf_helps.outputs(
conf_helps.classification_cost(
input=prob, label=label))
def test():
data = conf_helps.data_layer(name="word", size=dict_dim)
label = conf_helps.data_layer(name="label", size=label_dim)
emb = conf_helps.embedding_layer(input=data, size=word_dim)
boot_layer = conf_helps.data_layer(name="boot", size=10)
boot_layer = conf_helps.fc_layer(name='boot_fc',
input=boot_layer,
size=10)
def step(y, wid):
z = conf_helps.embedding_layer(input=wid, size=word_dim)
mem = conf_helps.memory(name="rnn_state",
size=hidden_dim,
boot_layer=boot_layer)
out = conf_helps.fc_layer(input=[y, z, mem],
size=hidden_dim,
act=conf_helps.TanhActivation(),
bias_attr=True,
name="rnn_state")
return out
out = conf_helps.recurrent_group(name="rnn",
step=step,
input=[emb, data])
rep = conf_helps.last_seq(input=out)
prob = conf_helps.fc_layer(size=label_dim,
input=rep,
act=conf_helps.SoftmaxActivation(),
bias_attr=True)
conf_helps.outputs(
conf_helps.classification_cost(input=prob, label=label))
def step(y):
mem = conf_helps.memory(name="rnn_state", size=hidden_dim)
out = conf_helps.fc_layer(input=[y, mem],
size=hidden_dim,
act=activation.Tanh(),
bias_attr=True,
name="rnn_state")
return out
def step(y):
mem = conf_helps.memory(name="rnn_state", size=hidden_dim)
out = conf_helps.fc_layer(
input=[y, mem],
size=hidden_dim,
act=activation.Tanh(),
bias_attr=True,
name="rnn_state")
return out
def step(y, wid):
z = conf_helps.embedding_layer(input=wid, size=word_dim)
mem = conf_helps.memory(name="rnn_state",
size=hidden_dim,
boot_layer=boot_layer)
out = conf_helps.fc_layer(input=[y, z, mem],
size=hidden_dim,
act=conf_helps.TanhActivation(),
bias_attr=True,
name="rnn_state")
return out
def step(y, wid):
z = conf_helps.embedding_layer(input=wid, size=word_dim)
mem = conf_helps.memory(
name="rnn_state",
size=hidden_dim,
boot_layer=boot_layer)
out = conf_helps.fc_layer(
input=[y, z, mem],
size=hidden_dim,
act=conf_helps.TanhActivation(),
bias_attr=True,
name="rnn_state")
return out
padding=1,
stride=1,
num_channels=1,
num_filters=6,
filter_size=5,
act=paddle.LinearActivation())
pool_1 = paddle.img_pool_layer(input=conv_1,
stride=2,
pool_size=2,
pool_type=paddle.MaxPooling())
conv_2 = paddle.img_conv_layer(input=pool_1,
stride=1,
num_filters=16,
filter_size=5,
act=paddle.LinearActivation())
pool_2 = paddle.img_pool_layer(input=conv_2,
stride=2,
pool_size=2,
pool_type=paddle.MaxPooling())
fc_1 = paddle.fc_layer(input=pool_2, size=500, act=paddle.SigmoidActivation())
fc_2 = paddle.fc_layer(input=fc_1, size=10, act=paddle.SoftmaxActivation())
label = paddle.data_layer(name='label', size=10)
cost = paddle.classification_cost(input=fc_2, label=label)
paddle.outputs(cost)