with tf.variable_scope("pooler"): # We "pool" the model by simply taking the hidden state corresponding # to the first token. We assume that this has been pre-trained first_token_tensor = tf.squeeze(self.sequence_output[:, 0:1, :], axis=1) self.pooled_output = tf.layers.dense( first_token_tensor, config.hidden_size, activation=tf.tanh, kernel_initializer=create_initializer(config.initializer_range))
def build(self, inputs_shape): if inputs_shape[-1] is None: raise ValueError("Expected inputs.shape[-1] to be known, saw shape: %s" % str(inputs_shape))
def call(self, inputs, state): """Long short-term memory cell (LSTM). Args: inputs: `2-D` tensor with shape `[batch_size, input_size]`. state: An `LSTMStateTuple` of state tensors, each shaped `[batch_size, num_units]`, if `state_is_tuple` has been set to `True`. Otherwise, a `Tensor` shaped `[batch_size, 2 * num_units]`. Returns: A pair containing the new hidden state, and the new state (either a `LSTMStateTuple` or a concatenated state, depending on `state_is_tuple`). """ sigmoid = math_ops.sigmoid one = constant_op.constant(1, dtype=dtypes.int32) # Parameters of gates are concatenated into one multiply for efficiency. if self._state_is_tuple: c, h = state else: c, h = array_ops.split(value=state, num_or_size_splits=2, axis=one)
# i = input_gate, j = new_input, f = forget_gate, o = output_gate i, j, f, o = array_ops.split( value=gate_inputs, num_or_size_splits=4, axis=one)
forget_bias_tensor = constant_op.constant(self._forget_bias, dtype=f.dtype) # Note that using `add` and `multiply` instead of `+` and `*` gives a # performance improvement. So using those at the cost of readability. add = math_ops.add multiply = math_ops.multiply new_c = add(multiply(c, sigmoid(add(f, forget_bias_tensor))), multiply(sigmoid(i), self._activation(j))) new_h = multiply(self._activation(new_c), sigmoid(o))