h2_t = h2.fprop([[h1_t], [s2_tm1]], params)
h3_t = h3.fprop([[h2_t], [s2_tm1]], params)
output_t = output.fprop([h1_t, h2_t, h3_t], params)
return h1_t, h2_t, h3_t, output_t
((h1_temp, h2_temp, h3_temp, y_hat_temp), updates) =\
theano.scan(fn=inner_fn,
sequences=[x],
outputs_info=[s1_0, s2_0, s3_0, None])
ts, _, _ = y_hat_temp.shape
y_hat_in = y_hat_temp.reshape((ts*batch_size, -1))
y_in = y.reshape((ts*batch_size, -1))
cost = NllBin(y_in, y_hat_in)
cost_temp = cost.reshape((ts, batch_size))
cost = cost_temp * mask
nll = cost.sum() / mask.sum()
cost = cost.sum(axis=0).mean()
cost.name = 'cost'
nll.name = 'nll'
model.inputs = [x, y, mask]
model.params = params
model.nodes = nodes
optimizer = RMSProp(
lr=0.0001,
mom=0.95
)
h2_t = h2.fprop([[h1_t], [s2_tm1]])
h3_t = h3.fprop([[h2_t], [s2_tm1]])
output_t = output.fprop([h1_t, h2_t, h3_t])
return h1_t, h2_t, h3_t, output_t
((h1_temp, h2_temp, h3_temp, y_hat_temp), updates) =\
theano.scan(fn=inner_fn,
sequences=[x],
outputs_info=[s1_0, s2_0, s3_0, None])
ts, _, _ = y_hat_temp.shape
y_hat_in = y_hat_temp.reshape((ts * batch_size, -1))
y_in = y.reshape((ts * batch_size, -1))
cost = NllBin(y_in, y_hat_in)
cost_temp = cost.reshape((ts, batch_size))
cost = cost_temp * mask
nll = cost.sum() / mask.sum()
cost = cost.sum(axis=0).mean()
cost.name = 'cost'
nll.name = 'nll'
model.inputs = [x, y, mask]
model._params = params
model.nodes = nodes
optimizer = RMSProp(lr=0.0001, mom=0.95)
extension = [
GradientClipping(batch_size=batch_size),
EpochCount(100),
