h4 = FullyConnectedLayer(name='h4',
parent=['h1', 'h2', 'h3'],
nout=res,
unit='sigmoid',
init_W=init_W,
init_b=init_b)
cost = MSELayer(name='cost', parent=['h4', 'y'])
nodes = [h1, h2, h3, h4, cost]
rnn = Net(inputs=inputs, inputs_dim=inputs_dim, nodes=nodes)
cost = unpack(rnn.build_recurrent_graph(output_args=[cost]))
cost = cost.mean()
cost.name = 'cost'
model.graphs = [rnn]
optimizer = Adam(
lr=0.001
)
extension = [
GradientClipping(batch_size=batch_size),
EpochCount(100),
Monitoring(freq=100,
ddout=[cost]),
Picklize(freq=200, path=save_path)
]
mainloop = Training(
name='toy_bb_gflstm',
cost = MulCrossEntropyLayer(name='cost', parent=['y', 'h4'])
# You will fill in a list of nodes and fed them to the model constructor
nodes = [c1, c2, h1, h2, h3, h4, cost]
# Your model will build the Theano computational graph
cnn = Net(inputs=inputs, inputs_dim=inputs_dim, nodes=nodes)
cnn.build_graph()
# You can access any output of a node by doing model.nodes[$node_name].out
cost = cnn.nodes['cost'].out
err = error(predict(cnn.nodes['h4'].out), predict(y))
cost.name = 'cost'
err.name = 'error_rate'
model.graphs = [cnn]
# Define your optimizer: Momentum (Nesterov), RMSProp, Adam
optimizer = Adam(
#lr=0.00005
lr=0.0005
)
extension = [
GradientClipping(batch_size=batch_size),
EpochCount(100),
Monitoring(freq=100,
ddout=[cost, err],
data=[Iterator(testdata, batch_size)]),
Picklize(freq=10000,
path=save_path)
cost = MulCrossEntropyLayer(name='cost', parent=['y', 'h4'])
# You will fill in a list of nodes and fed them to the model constructor
nodes = [c1, c2, h1, h2, h3, h4, cost]
# Your model will build the Theano computational graph
cnn = Net(inputs=inputs, inputs_dim=inputs_dim, nodes=nodes)
cnn.build_graph()
# You can access any output of a node by doing model.nodes[$node_name].out
cost = cnn.nodes['cost'].out
err = error(predict(cnn.nodes['h4'].out), predict(y))
cost.name = 'cost'
err.name = 'error_rate'
model.graphs = [cnn]
# Define your optimizer: Momentum (Nesterov), RMSProp, Adam
optimizer = Adam(
#lr=0.00005
lr=0.0005)
extension = [
GradientClipping(batch_size=batch_size),
EpochCount(100),
Monitoring(freq=100,
ddout=[cost, err],
data=[Iterator(test_data, batch_size)]),
Picklize(freq=10000, path=save_path)
]
h4 = FullyConnectedLayer(name='h4',
parent=['h1', 'h2', 'h3'],
nout=res,
unit='sigmoid',
init_W=init_W,
init_b=init_b)
cost = MSELayer(name='cost', parent=['h4', 'y'])
nodes = [h1, h2, h3, h4, cost]
rnn = Net(inputs=inputs, inputs_dim=inputs_dim, nodes=nodes)
cost = unpack(rnn.build_recurrent_graph(output_args=[cost]))
cost = cost.mean()
cost.name = 'cost'
model.graphs = [rnn]
optimizer = Adam(lr=0.001)
extension = [
GradientClipping(batch_size=batch_size),
EpochCount(100),
Monitoring(freq=100, ddout=[cost]),
Picklize(freq=200, path=save_path)
]
mainloop = Training(name='toy_bb_gflstm',
data=Iterator(trdata, batch_size),
model=model,
optimizer=optimizer,
cost=cost,
cost = MulCrossEntropyLayer(name='cost', parent=['onehot', 'h2'])
# You will fill in a list of nodes and fed them to the model constructor
nodes = [onehot, h1, h2, cost]
# Your model will build the Theano computational graph
mlp = Net(inputs=inputs, inputs_dim=inputs_dim, nodes=nodes)
mlp.build_graph()
# You can access any output of a node by doing model.nodes[$node_name].out
cost = mlp.nodes['cost'].out
err = error(predict(mlp.nodes['h2'].out), predict(mlp.nodes['onehot'].out))
cost.name = 'cost'
err.name = 'error_rate'
model.graphs = [mlp]
# Define your optimizer: Momentum (Nesterov), RMSProp, Adam
optimizer = RMSProp(
lr=0.001
)
extension = [
GradientClipping(),
EpochCount(40),
Monitoring(freq=100,
ddout=[cost, err],
data=[Iterator(trdata, batch_size),
Iterator(valdata, batch_size)]),
Picklize(freq=200,
path=save_path)
