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_batch_norm(self):
"""Test invoking BatchNorm in eager mode."""
with context.eager_mode():
batch_size = 10
n_features = 5
input = np.random.rand(batch_size, n_features).astype(np.float32)
layer = layers.BatchNorm()
result = layer(input)
assert result.shape == (batch_size, n_features)
assert len(layer.trainable_variables) == 2