modalities.py 文件源码

def bottom(self, inputs):
    """Transform input from data space to model space.

    Args:
      inputs: A Tensor with shape [batch, ...]
    Returns:
      body_input: A Tensor with shape [batch, ?, ?, body_input_depth].
    """
    with tf.variable_scope(self.name):
      # TODO(aidangomez): Will need to sort out a better audio pipeline
      def xnet_resblock(x, filters, res_relu, name):
        with tf.variable_scope(name):
          # We only stride along the length dimension to preserve the spectral
          # bins (which are tiny in dimensionality relative to length)
          y = common_layers.separable_conv_block(
              x,
              filters, [((1, 1), (3, 3)), ((1, 1), (3, 3))],
              first_relu=True,
              padding="SAME",
              force2d=True,
              name="sep_conv_block")
          y = common_layers.pool(y, (3, 3), "MAX", "SAME", strides=(2, 1))
          return y + common_layers.conv_block(
              x,
              filters, [((1, 1), (1, 1))],
              padding="SAME",
              strides=(2, 1),
              first_relu=res_relu,
              force2d=True,
              name="res_conv0")

      # Bitcast back from int32
      x = tf.bitcast(inputs, tf.float32)
      x.set_shape([None, None, None, 1])
      for i in xrange(self._model_hparams.audio_compression):
        x = xnet_resblock(x, 2**(i + 1), True, "compress_block_%d" % i)
      return xnet_resblock(x, self._body_input_depth, False,
                           "compress_block_final")