def test_without_std_share_network_output_values(self, mock_normal,
output_dim, hidden_dim,
init_std):
mock_normal.return_value = 0.5
model = GaussianLSTMModel(output_dim=output_dim,
hidden_dim=hidden_dim,
std_share_network=False,
hidden_nonlinearity=None,
recurrent_nonlinearity=None,
hidden_w_init=self.default_initializer,
recurrent_w_init=self.default_initializer,
output_w_init=self.default_initializer,
init_std=init_std)
step_hidden_var = tf.compat.v1.placeholder(shape=(self.batch_size,
hidden_dim),
name='step_hidden',
dtype=tf.float32)
step_cell_var = tf.compat.v1.placeholder(shape=(self.batch_size,
hidden_dim),
name='step_cell',
dtype=tf.float32)
(_, step_mean_var, step_log_std_var, step_hidden, step_cell,
hidden_init_var, cell_init_var) = model.build(self.input_var,
self.step_input_var,
step_hidden_var,
step_cell_var)
hidden1 = hidden2 = np.full((self.batch_size, hidden_dim),
hidden_init_var.eval())
cell1 = cell2 = np.full((self.batch_size, hidden_dim),
cell_init_var.eval())
for _ in range(self.time_step):
mean1, log_std1, hidden1, cell1 = self.sess.run(
[step_mean_var, step_log_std_var, step_hidden, step_cell],
feed_dict={
self.step_input_var: self.obs_input,
step_hidden_var: hidden1,
step_cell_var: cell1
})
hidden2, cell2 = recurrent_step_lstm(input_val=self.obs_input,
num_units=hidden_dim,
step_hidden=hidden2,
step_cell=cell2,
w_x_init=0.1,
w_h_init=0.1,
b_init=0.,
nonlinearity=None,
gate_nonlinearity=None)
output_nonlinearity = np.full(
(np.prod(hidden2.shape[1:]), output_dim), 0.1)
output2 = np.matmul(hidden2, output_nonlinearity)
assert np.allclose(mean1, output2)
expected_log_std = np.full((self.batch_size, output_dim),
np.log(init_std))
assert np.allclose(log_std1, expected_log_std)
assert np.allclose(hidden1, hidden2)
assert np.allclose(cell1, cell2)
def test_output_value_trainable_hidden_and_cell(self, time_step, input_dim,
output_dim):
obs_inputs = np.full((self.batch_size, time_step, input_dim), 1.)
obs_input = np.full((self.batch_size, input_dim), 1.)
_input_var = tf.compat.v1.placeholder(tf.float32,
shape=(None, None, input_dim),
name='input')
_step_input_var = tf.compat.v1.placeholder(tf.float32,
shape=(None, input_dim),
name='input')
_output_nonlinearity = tf.keras.layers.Dense(
units=output_dim,
activation=None,
kernel_initializer=tf.constant_initializer(1))
with tf.compat.v1.variable_scope('LSTM'):
self.lstm = lstm(all_input_var=_input_var,
name='lstm',
lstm_cell=self.lstm_cell,
step_input_var=_step_input_var,
step_hidden_var=self._step_hidden_var,
step_cell_var=self._step_cell_var,
hidden_state_init_trainable=True,
cell_state_init_trainable=True,
output_nonlinearity_layer=_output_nonlinearity)
self.sess.run(tf.compat.v1.global_variables_initializer())
# Compute output by doing t step() on the lstm cell
outputs_t, _, h_t, c_t, hidden_init, cell_init = self.lstm
hidden = np.full((self.batch_size, self.hidden_dim),
hidden_init.eval())
cell = np.full((self.batch_size, self.hidden_dim), cell_init.eval())
hidden, cell = self.sess.run(
[h_t, c_t],
feed_dict={
_step_input_var: obs_input,
self._step_hidden_var: hidden,
self._step_cell_var: cell
})
with tf.compat.v1.variable_scope('LSTM/lstm', reuse=True):
hidden_init_var = tf.compat.v1.get_variable(name='initial_hidden')
cell_init_var = tf.compat.v1.get_variable(name='initial_cell')
assert hidden_init_var in tf.compat.v1.trainable_variables()
assert cell_init_var in tf.compat.v1.trainable_variables()
full_output1 = self.sess.run(outputs_t,
feed_dict={_input_var: obs_inputs})
hidden2 = np.full((self.batch_size, self.hidden_dim),
hidden_init.eval())
cell2 = np.full((self.batch_size, self.hidden_dim), cell_init.eval())
stack_hidden = None
for i in range(time_step):
hidden2, cell2 = recurrent_step_lstm(
input_val=obs_inputs[:, i, :],
num_units=self.hidden_dim,
step_hidden=hidden2,
step_cell=cell2,
w_x_init=1.,
w_h_init=1.,
b_init=0.,
nonlinearity=np.tanh,
gate_nonlinearity=lambda x: 1. / (1. + np.exp(-x)))
if stack_hidden is None:
stack_hidden = hidden2[:, np.newaxis, :]
else:
stack_hidden = np.concatenate(
(stack_hidden, hidden2[:, np.newaxis, :]), axis=1)
output_nonlinearity = np.full((np.prod(hidden2.shape[1:]), output_dim),
1.)
full_output2 = np.matmul(stack_hidden, output_nonlinearity)
assert np.allclose(full_output1, full_output2)
