Python tensorflow.contrib.rnn.python.ops.core_rnn_cell._linear() Examples

The following are 3 code examples of tensorflow.contrib.rnn.python.ops.core_rnn_cell._linear(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module tensorflow.contrib.rnn.python.ops.core_rnn_cell , or try the search function .
Example #1
Source File: deeppyramid_utils.py    From BERT with Apache License 2.0 6 votes vote down vote up 
def linear(args, output_size, bias, bias_start=0.0, scope=None, squeeze=False, wd=0.0, input_keep_prob=1.0,
           is_train=None):
    with tf.variable_scope(scope or "linear"):
        if args is None or (nest.is_sequence(args) and not args):
            raise ValueError("`args` must be specified")
        if not nest.is_sequence(args):
            args = [args]

        flat_args = [flatten(arg, 1) for arg in args]
        # if input_keep_prob < 1.0:
        assert is_train is not None
        flat_args = [tf.cond(is_train, lambda: tf.nn.dropout(arg, input_keep_prob), lambda: arg)
                         for arg in flat_args]
        flat_out = _linear(flat_args, output_size, bias)
        out = reconstruct(flat_out, args[0], 1)
        if squeeze:
            out = tf.squeeze(out, [len(args[0].get_shape().as_list())-1])

    return out
Example #2
Source File: nn.py    From BERT with Apache License 2.0 6 votes vote down vote up 
def linear(args, output_size, bias, bias_start=0.0, scope=None, squeeze=False, wd=0.0, input_keep_prob=1.0,
           is_train=None):
    with tf.variable_scope(scope or "linear"):
        if args is None or (nest.is_sequence(args) and not args):
            raise ValueError("`args` must be specified")
        if not nest.is_sequence(args):
            args = [args]

        flat_args = [flatten(arg, 1) for arg in args]
        # if input_keep_prob < 1.0:
        assert is_train is not None
        flat_args = [tf.cond(is_train, lambda: tf.nn.dropout(arg, input_keep_prob), lambda: arg)
                         for arg in flat_args]
        flat_out = _linear(flat_args, output_size, bias)
        out = reconstruct(flat_out, args[0], 1)
        if squeeze:
            out = tf.squeeze(out, [len(args[0].get_shape().as_list())-1])
        if wd:
            add_wd(wd)

    return out
Example #3
Source File: embed_compress.py    From neuralcompressor with MIT License 5 votes vote down vote up 
def _encode(self, input_matrix, word_ids, embed_size):
        input_embeds = tf.nn.embedding_lookup(input_matrix, word_ids, name="input_embeds")

        M, K = self.M, self.K

        with tf.variable_scope("h"):
            h = tf.nn.tanh(_linear(input_embeds, M * K/2, True))
        with tf.variable_scope("logits"):
            logits = _linear(h, M * K, True)
            logits = tf.log(tf.nn.softplus(logits) + 1e-8)
        logits = tf.reshape(logits, [-1, M, K], name="logits")
        return input_embeds, logits