Transformer

def conv_hidden_relu(inputs,
                     hidden_size,
                     output_size,
                     kernel_size=(1, 1),
                     second_kernel_size=(1, 1),
                     summaries=True,
                     dropout=0.0,
                     **kwargs):
  """Hidden layer with RELU activation followed by linear projection."""
  name = kwargs.pop("name") if "name" in kwargs else None
  with tf.variable_scope(name, "conv_hidden_relu", [inputs]):
    if inputs.get_shape().ndims == 3:
      is_3d = True
      inputs = tf.expand_dims(inputs, 2)
    else:
      is_3d = False
    conv_f1 = conv if kernel_size == (1, 1) else separable_conv
    h = conv_f1(
        inputs,
        hidden_size,
        kernel_size,
        activation=tf.nn.relu,
        name="conv1",
        **kwargs)
    if dropout != 0.0:
      h = tf.nn.dropout(h, 1.0 - dropout)
    if summaries and not tf.get_variable_scope().reuse:
      tf.summary.histogram("hidden_density_logit",
                           relu_density_logit(
                               h, list(range(inputs.shape.ndims - 1))))
    conv_f2 = conv if second_kernel_size == (1, 1) else separable_conv
    ret = conv_f2(h, output_size, second_kernel_size, name="conv2", **kwargs)
    if is_3d:
      ret = tf.squeeze(ret, 2)
    return ret

def conv(inputs, filters, kernel_size, **kwargs):
  return conv_internal(tf.layers.conv2d, inputs, filters, kernel_size, **kwargs)


def conv1d(inputs, filters, kernel_size, **kwargs):
  return tf.squeeze(
      conv(tf.expand_dims(inputs, 2), filters, (kernel_size, 1), **kwargs), 2)