return h1_t, h2_t, h3_t, y_hat
((h1_t, h2_t, h3_t, y_hat),
updates) =\
theano.scan(fn=inner_fn,
sequences=[x],
outputs_info=[h1_init_state,
h2_init_state,
h3_init_state,
None])
reshaped_y = y.reshape((y.shape[0]*y.shape[1], -1))
reshaped_y = onehot.fprop([reshaped_y])
reshaped_y_hat = y_hat.reshape((y_hat.shape[0]*y_hat.shape[1], -1))
cost = NllMul(reshaped_y, reshaped_y_hat)
cost = cost.mean()
cost.name = 'cost'
model.inputs = [x, y]
model._params = params
model.nodes = nodes
model.set_updates(update_list)
optimizer = Adam(
lr=0.001
)
extension = [
GradientClipping(batch_size=batch_size),
EpochCount(100),
def fprop(self, X):
cost = NllMul(X[0], X[1])
if self.use_sum:
return cost.sum()
else:
return cost.mean()
def fprop(self, X):
cost = NllMul(X[0], X[1])
if self.use_sum:
return cost.sum()
else:
return cost.mean()