def test_tanh_default_output(self):
cases = [
ParameterSet(2, 10, 3, 20, 15)
]
for case in cases:
input = self._make_input(case)
hidden = self._make_hidden(case)
weights = self._make_weights(case)
bias = self._make_bias(case)
def build_network(network):
h = network.add_input(
"input", turret.DataType.FLOAT,
turret.Dimensions.CHW(
case.batch_size, case.seq_len, case.data_size))
h_hidden = network.add_input(
"hidden", turret.DataType.FLOAT,
turret.Dimensions.CHW(
case.batch_size, case.num_layers, case.hidden_size))
h, _ = L.rnn_tanh_v2(h, case.seq_len, weights, bias,
hidden_state=h_hidden)
network.mark_output("output", h)
actual = execute_inference(
{"input": input, "hidden": hidden}, build_network)
expect = unidirection_rnn(
input, hidden, weights, bias, lambda x: np.tanh(x))
self.assertEqual(expect.shape, actual.shape)
self.assertTrue(np.allclose(expect, actual))
def test_brnn_relu_default_output(self):
cases = [ParameterSet(2, 10, 3, 20, 15)]
for case in cases:
input = self._make_input(case)
hidden = self._make_hidden(case)
fwd_weights = self._make_weights(case)
bwd_weights = self._make_weights(case)
fwd_bias = self._make_bias(case)
bwd_bias = self._make_bias(case)
def build_network(network):
h = network.add_input(
"input", turret.DataType.FLOAT,
turret.Dimensions.CHW(case.seq_len, case.batch_size,
case.data_size))
h_hidden = network.add_input(
"hidden", turret.DataType.FLOAT,
turret.Dimensions.CHW(case.num_layers, case.batch_size,
case.hidden_size * 2))
h, _ = L.brnn_relu(h,
case.seq_len,
fwd_weights,
bwd_weights,
fwd_bias,
bwd_bias,
hidden_state=h_hidden)
network.mark_output("output", h)
actual = execute_inference({
"input": input,
"hidden": hidden
},
build_network,
max_batch_size=1)
t_input = input.transpose(0, 2, 1, 3)
t_hidden = hidden.transpose(0, 2, 1, 3)
t_expect = bidirection_rnn(t_input, t_hidden, fwd_weights,
bwd_weights, fwd_bias, bwd_bias,
lambda x: np.maximum(x, 0.0))
expect = t_expect.transpose(0, 2, 1, 3)
self.assertEqual(expect.shape, actual.shape)
self.assertTrue(np.allclose(expect, actual))