269e11a506f1dfa80d95f27b3e2d3df845c80ae3,texar/modules/encoders/transformer_encoders.py,TransformerEncoder,__init__,#TransformerEncoder#Any#Any#Any#,34

Before Change

        EncoderBase.__init__(self, hparams)
        self._embedding = None
        self._vocab_size = vocab_size
        with tf.variable_scope(self.variable_scope):
            if self._hparams.embedding_enabled:
                if embedding is None and vocab_size is None:
                    raise ValueError("If `embedding` is not provided, "
                                     "`vocab_size` must be specified.")
                if isinstance(embedding, tf.Variable):
                    self._embedding = embedding
                else:
                    self._embedding = layers.get_embedding(
                        self._hparams.embedding, embedding, vocab_size,
                        variable_scope="enc_embed")
                embed_dim = self._hparams.embedding.dim
                if self._hparams.zero_pad:
                    self._embedding = tf.concat((tf.zeros(shape=[1, embed_dim]),
                                                self._embedding[1:, :]), 0)
                if self._hparams.embedding.trainable:
                    self._add_trainable_variable(self._embedding)

    @staticmethod
    def default_hparams():
        Returns a dictionary of hyperparameters with default values.
        The dictionary has the following structure and default values.

After Change

                                             self._embedding[1:, :]), 0)
            if self._hparams.embedding.trainable:
                self._add_trainable_variable(self._embedding)
            if self._vocab_size is None:
                self._vocab_size = self._embedding.get_shape().as_list()[0]

    @staticmethod
    def default_hparams():
        Returns a dictionary of hyperparameters with default values.
        The dictionary has the following structure and default values.

Instances