output = FullyConnectedLayer(name='output',
parent=['h1', 'h2', 'h3'],
parent_dim=[200, 200, 200],
nout=frame_size,
unit='sigmoid',
init_W=init_W,
init_b=init_b)
nodes = [h1, h2, h3, output]
params = OrderedDict()
for node in nodes:
params.update(node.initialize())
params = init_tparams(params)
s1_0 = h1.get_init_state(batch_size)
s2_0 = h2.get_init_state(batch_size)
s3_0 = h3.get_init_state(batch_size)
def inner_fn(x_t, s1_tm1, s2_tm1, s3_tm1):
s1_t = h1.fprop([[x_t], [s1_tm1, s2_tm1, s3_tm1]], params)
s2_t = h2.fprop([[s1_t], [s2_tm1, s1_tm1, s3_tm1]], params)
s3_t = h3.fprop([[s2_t], [s3_tm1], s1_tm1, s2_tm1], params)
y_hat_t = output.fprop([s1_t, s2_t, s3_t], params)
return s1_t, s2_t, s3_t, y_hat_t
((h1_temp, h2_temp, h3_temp, y_hat_temp), updates) =\
theano.scan(fn=inner_fn,
params = flatten([node.get_params().values() for node in nodes])
step_count = sharedX(0, name='step_count')
last_h = np.zeros((batch_size, 400), dtype=np.float32)
h1_tm1 = sharedX(last_h, name='h1_tm1')
h2_tm1 = sharedX(last_h, name='h2_tm1')
h3_tm1 = sharedX(last_h, name='h3_tm1')
update_list = [step_count, h1_tm1, h2_tm1, h3_tm1]
step_count = T.switch(T.le(step_count, reset_freq),
step_count + 1, 0)
s1_0 = T.switch(T.or_(T.cast(T.eq(step_count, 0), 'int32'),
T.cast(T.eq(T.sum(h1_tm1), 0.), 'int32')),
h1.get_init_state(), h1_tm1)
s2_0 = T.switch(T.or_(T.cast(T.eq(step_count, 0), 'int32'),
T.cast(T.eq(T.sum(h2_tm1), 0.), 'int32')),
h2.get_init_state(), h2_tm1)
s3_0 = T.switch(T.or_(T.cast(T.eq(step_count, 0), 'int32'),
T.cast(T.eq(T.sum(h3_tm1), 0.), 'int32')),
h3.get_init_state(), h3_tm1)
def inner_fn(x_t, h1_tm1, h2_tm1, h3_tm1):
h1_t = h1.fprop([[x_t], [h1_tm1, h2_tm1, h3_tm1]])
h2_t = h2.fprop([[x_t, h1_t], [h2_tm1, h1_tm1, h3_tm1]])
h3_t = h3.fprop([[x_t, h2_t], [h3_tm1, h1_tm1, h2_tm1]])
return h1_t, h2_t, h3_t
node.initialize()
params = flatten([node.get_params().values() for node in nodes])
step_count = sharedX(0, name='step_count')
last_h = np.zeros((batch_size, 400), dtype=np.float32)
h1_tm1 = sharedX(last_h, name='h1_tm1')
h2_tm1 = sharedX(last_h, name='h2_tm1')
h3_tm1 = sharedX(last_h, name='h3_tm1')
update_list = [step_count, h1_tm1, h2_tm1, h3_tm1]
step_count = T.switch(T.le(step_count, reset_freq), step_count + 1, 0)
s1_0 = T.switch(
T.or_(T.cast(T.eq(step_count, 0), 'int32'),
T.cast(T.eq(T.sum(h1_tm1), 0.), 'int32')), h1.get_init_state(),
h1_tm1)
s2_0 = T.switch(
T.or_(T.cast(T.eq(step_count, 0), 'int32'),
T.cast(T.eq(T.sum(h2_tm1), 0.), 'int32')), h2.get_init_state(),
h2_tm1)
s3_0 = T.switch(
T.or_(T.cast(T.eq(step_count, 0), 'int32'),
T.cast(T.eq(T.sum(h3_tm1), 0.), 'int32')), h3.get_init_state(),
h3_tm1)
def inner_fn(x_t, h1_tm1, h2_tm1, h3_tm1):
h1_t = h1.fprop([[x_t], [h1_tm1, h2_tm1, h3_tm1]])
h2_t = h2.fprop([[x_t, h1_t], [h2_tm1, h1_tm1, h3_tm1]])
