return h1_t, h2_t, h3_t
((h1_temp, h2_temp, h3_temp), updates) = theano.scan(fn=inner_fn,
sequences=[x],
outputs_info=[s1_0, s2_0, s3_0])
ts, _, _ = y.shape
post_scan_shape = ((ts*batch_size, -1))
h1_in = h1_temp.reshape(post_scan_shape)
h2_in = h2_temp.reshape(post_scan_shape)
h3_in = h3_temp.reshape(post_scan_shape)
y_hat_in = output.fprop([h1_in, h2_in, h3_in])
cost = NllMulInd(y.flatten(), y_hat_in)
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),
Monitoring(freq=100,
((h1_temp, h2_temp, h3_temp),
updates) = theano.scan(fn=inner_fn,
sequences=[x],
outputs_info=[s1_0, s2_0, s3_0])
ts, _, _ = y.shape
post_scan_shape = ((ts * batch_size, -1))
h1_in = h1_temp.reshape(post_scan_shape)
h2_in = h2_temp.reshape(post_scan_shape)
h3_in = h3_temp.reshape(post_scan_shape)
y_hat_in = output.fprop([h1_in, h2_in, h3_in])
cost = NllMulInd(y.flatten(), y_hat_in)
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),
Monitoring(freq=100, ddout=[cost]),
Picklize(freq=100, path=save_path)
]
