def _create_encoder(self, n_layers, dropout):
"""Create the encoder layers."""
prev_layer = self._features
for i in range(len(self._filter_sizes)):
filter_size = self._filter_sizes[i]
kernel_size = self._kernel_sizes[i]
if dropout > 0.0:
prev_layer = layers.Dropout(dropout, in_layers=prev_layer)
prev_layer = layers.Conv1D(
filters=filter_size,
kernel_size=kernel_size,
in_layers=prev_layer,
activation_fn=tf.nn.relu)
prev_layer = layers.Flatten(prev_layer)
prev_layer = layers.Dense(
self._decoder_dimension, in_layers=prev_layer, activation_fn=tf.nn.relu)
prev_layer = layers.BatchNorm(prev_layer)
if self._variational:
self._embedding_mean = layers.Dense(
self._embedding_dimension,
in_layers=prev_layer,
name='embedding_mean')
self._embedding_stddev = layers.Dense(
self._embedding_dimension, in_layers=prev_layer, name='embedding_std')
prev_layer = layers.CombineMeanStd(
[self._embedding_mean, self._embedding_stddev], training_only=True)
return prev_layer
def test_combine_mean_std(self):
"""Test invoking CombineMeanStd in eager mode."""
with context.eager_mode():
mean = np.random.rand(5, 3).astype(np.float32)
std = np.random.rand(5, 3).astype(np.float32)
layer = layers.CombineMeanStd(training_only=True,
noise_epsilon=0.01)
result1 = layer(mean, std, training=False)
assert np.array_equal(result1, mean) # No noise in test mode
result2 = layer(mean, std, training=True)
assert not np.array_equal(result2, mean)
assert np.allclose(result2, mean, atol=0.1)
def _create_encoder(self, n_layers, dropout):
"""Create the encoder layers."""
prev_layer = self._features
for i in range(n_layers):
if dropout > 0.0:
prev_layer = layers.Dropout(dropout, in_layers=prev_layer)
prev_layer = layers.GRU(
self._embedding_dimension, self.batch_size, in_layers=prev_layer)
prev_layer = layers.Gather(in_layers=[prev_layer, self._gather_indices])
if self._variational:
self._embedding_mean = layers.Dense(
self._embedding_dimension, in_layers=prev_layer)
self._embedding_stddev = layers.Dense(
self._embedding_dimension, in_layers=prev_layer)
prev_layer = layers.CombineMeanStd(
[self._embedding_mean, self._embedding_stddev], training_only=True)
return prev_layer
