def build_training_graph(self):
self.run_extension('ext_regularize_pre_grad')
self.grads = OrderedDict(izip(self.params,
T.grad(self.cost, self.params)))
self.run_extension('ext_grad')
grads = self.optimizer.get_updates(self.grads)
for key, val in grads.items():
self.updates[key] = val
self.run_extension('ext_regularize_post_grad')
return self.build_theano_graph(self.inputs, self.outputs, self.updates)
unit='tanh',
init_W=init_W,
init_U=init_U,
init_b=init_b)
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)
