Python math_ops.sigmoid方法代码示例

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sigmoid [as 别名]
def call(self, inputs, state):
    """Gated recurrent unit (GRU) with nunits cells."""
    with vs.variable_scope("gates"):  # Reset gate and update gate.
      # We start with bias of 1.0 to not reset and not update.
      bias_ones = self._bias_initializer
      if self._bias_initializer is None:
        dtype = [a.dtype for a in [inputs, state]][0]
        bias_ones = init_ops.constant_initializer(1.0, dtype=dtype)
      value = math_ops.sigmoid(
          _linear([inputs, state], 2 * self._num_units, True, bias_ones,
                  self._kernel_initializer))
      r, u = array_ops.split(value=value, num_or_size_splits=2, axis=1)
    with vs.variable_scope("candidate"):
      c = self._activation(
          _linear([inputs, r * state], self._num_units, True,
                  self._bias_initializer, self._kernel_initializer))
    new_h = u * state + (1 - u) * c
    return new_h, new_h 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sigmoid [as 别名]
def _kl_bernoulli_bernoulli(a, b, name=None):
  """Calculate the batched KL divergence KL(a || b) with a and b Bernoulli.

  Args:
    a: instance of a Bernoulli distribution object.
    b: instance of a Bernoulli distribution object.
    name: (optional) Name to use for created operations.
      default is "kl_bernoulli_bernoulli".

  Returns:
    Batchwise KL(a || b)
  """
  with ops.name_scope(name, "kl_bernoulli_bernoulli",
                      values=[a.logits, b.logits]):
    delta_probs0 = nn.softplus(-b.logits) - nn.softplus(-a.logits)
    delta_probs1 = nn.softplus(b.logits) - nn.softplus(a.logits)
    return (math_ops.sigmoid(a.logits) * delta_probs0
            + math_ops.sigmoid(-a.logits) * delta_probs1) 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sigmoid [as 别名]
def _highway(self, inp, out):
    input_size = inp.get_shape().with_rank(2)[1].value
    carry_weight = vs.get_variable("carry_w", [input_size, input_size])
    carry_bias = vs.get_variable(
        "carry_b", [input_size],
        initializer=init_ops.constant_initializer(
            self._carry_bias_init))
    carry = math_ops.sigmoid(nn_ops.xw_plus_b(inp, carry_weight, carry_bias))
    if self._couple_carry_transform_gates:
      transform = 1 - carry
    else:
      transform_weight = vs.get_variable("transform_w",
                                         [input_size, input_size])
      transform_bias = vs.get_variable(
          "transform_b", [input_size],
          initializer=init_ops.constant_initializer(
              -self._carry_bias_init))
      transform = math_ops.sigmoid(nn_ops.xw_plus_b(inp,
                                                    transform_weight,
                                                    transform_bias))
    return inp * carry + out * transform 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sigmoid [as 别名]
def call(self, inputs, state):
    """LSTM cell with layer normalization and recurrent dropout."""
    c, h = state
    args = array_ops.concat([inputs, h], 1)
    concat = self._linear(args)

    i, j, f, o = array_ops.split(value=concat, num_or_size_splits=4, axis=1)
    if self._layer_norm:
      i = self._norm(i, "input")
      j = self._norm(j, "transform")
      f = self._norm(f, "forget")
      o = self._norm(o, "output")

    g = self._activation(j)
    if (not isinstance(self._keep_prob, float)) or self._keep_prob < 1:
      g = nn_ops.dropout(g, self._keep_prob, seed=self._seed)

    new_c = (c * math_ops.sigmoid(f + self._forget_bias)
             + math_ops.sigmoid(i) * g)
    if self._layer_norm:
      new_c = self._norm(new_c, "state")
    new_h = self._activation(new_c) * math_ops.sigmoid(o)

    new_state = rnn_cell_impl.LSTMStateTuple(new_c, new_h)
    return new_h, new_state 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sigmoid [as 别名]
def __call__(self, inputs, state, scope=None):
    """Gated recurrent unit (GRU) with nunits cells."""
    with vs.variable_scope(scope or "gru_cell"):
      with vs.variable_scope("gates"):  # Reset gate and update gate.
        # We start with bias of 1.0 to not reset and not update.
        r, u = array_ops.split(
            value=_linear(
                [inputs, state], 2 * self._num_units, True, 1.0, scope=scope),
            num_or_size_splits=2,
            axis=1)
        r, u = sigmoid(r), sigmoid(u)
      with vs.variable_scope("candidate"):
        c = self._activation(_linear([inputs, r * state],
                                     self._num_units, True,
                                     scope=scope))
      new_h = u * state + (1 - u) * c
    return new_h, new_h 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sigmoid [as 别名]
def __init__(self,
               p=None,
               dtype=dtypes.int32,
               validate_args=False,
               allow_nan_stats=True,
               name="BernoulliWithSigmoidP"):
    parameters = locals()
    parameters.pop("self")
    with ops.name_scope(name) as ns:
      super(BernoulliWithSigmoidP, self).__init__(
          p=nn.sigmoid(p, name="sigmoid_p"),
          dtype=dtype,
          validate_args=validate_args,
          allow_nan_stats=allow_nan_stats,
          name=ns)
    self._parameters = parameters 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sigmoid [as 别名]
def _kl_bernoulli_bernoulli(a, b, name=None):
  """Calculate the batched KL divergence KL(a || b) with a and b Bernoulli.

  Args:
    a: instance of a Bernoulli distribution object.
    b: instance of a Bernoulli distribution object.
    name: (optional) Name to use for created operations.
      default is "kl_bernoulli_bernoulli".

  Returns:
    Batchwise KL(a || b)
  """
  with ops.name_scope(name, "kl_bernoulli_bernoulli", [a.logits, b.logits]):
    return (math_ops.sigmoid(a.logits) * (-nn.softplus(-a.logits) +
                                          nn.softplus(-b.logits)) +
            math_ops.sigmoid(-a.logits) * (-nn.softplus(a.logits) +
                                           nn.softplus(b.logits))) 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sigmoid [as 别名]
def __call__(self, inputs, state, scope=None):
        """Attention GRU with nunits cells."""
        with vs.variable_scope(scope or "attention_gru_cell"):
            with vs.variable_scope("gates"):  # Reset gate and update gate.
                # We start with bias of 1.0 to not reset and not update.
                if inputs.get_shape()[-1] != self._num_units + 1:
                    raise ValueError("Input should be passed as word input concatenated with 1D attention on end axis")
                # extract input vector and attention
                inputs, g = array_ops.split(inputs,
                        num_or_size_splits=[self._num_units,1],
                        axis=1)
                r = _linear([inputs, state], self._num_units, True)
                r = sigmoid(r)
            with vs.variable_scope("candidate"):
                r = r*_linear(state, self._num_units, False)
            with vs.variable_scope("input"):
                x = _linear(inputs, self._num_units, True)
            h_hat = self._activation(r + x)

            new_h = (1 - g) * state + g * h_hat
        return new_h, new_h 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sigmoid [as 别名]
def __call__(self, inputs, state, scope=None):
        """Run one step of SRU."""
        with tf.variable_scope(scope or type(self).__name__):  # "SRUCell"
            with tf.variable_scope("x_hat"):
                x = linear([inputs], self._num_units, False)
            with tf.variable_scope("gates"):
                concat = tf.sigmoid(linear([inputs], 2 * self._num_units, True))
                f, r = tf.split(concat, 2, axis = 1)
            with tf.variable_scope("candidates"):
                c = self._activation(f * state + (1 - f) * x)
                # variational dropout as suggested in the paper (disabled)
                # if self._is_training and Params.dropout is not None:
                #     c = tf.nn.dropout(c, keep_prob = 1 - Params.dropout)
            # highway connection
            # Our implementation is slightly different to the paper
            # https://arxiv.org/abs/1709.02755 in a way that highway network
            # uses x_hat instead of the cell inputs. Check equation (7) from the original
            # paper for SRU.
            h = r * c + (1 - r) * x
        return h, c 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sigmoid [as 别名]
def __call__(self, inputs, state, k_size=3, scope=None):
    """Convolutional Long short-term memory cell (ConvLSTM)."""
    with vs.variable_scope(scope or type(self).__name__): # "ConvLSTMCell"
      if self._state_is_tuple:
        c, h = state
      else:
        c, h = array_ops.split(3, 2, state)

      # batch_size * height * width * channel
      concat = _conv([inputs, h], 4 * self._num_units, k_size, True)

      # i = input_gate, j = new_input, f = forget_gate, o = output_gate
      i, j, f, o = array_ops.split(3, 4, concat)

      new_c = (c * sigmoid(f + self._forget_bias) + sigmoid(i) *
               self._activation(j))
      new_h = self._activation(new_c) * sigmoid(o)

      if self._state_is_tuple:
        new_state = LSTMStateTuple(new_c, new_h)
      else:
        new_state = array_ops.concat(3, [new_c, new_h])
      return new_h, new_state 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sigmoid [as 别名]
def convlstm(input, state, activation=math_ops.sigmoid, kernel_shape=[3, 3],
             norm='batch', is_training=True, reuse=False, name='convlstm'):
    with tf.variable_scope(name, reuse=reuse):
        output_size = input.get_shape().as_list()[-1]
        cell = rnn_cell.ConvLSTMCell(conv_ndims=2,
                                     input_shape=input.get_shape().as_list()[1:],
                                     output_channels=output_size,
                                     kernel_shape=kernel_shape,
                                     skip_connection=False,
                                     initializers=tf.truncated_normal_initializer(stddev=0.02),
                                     activation=activation,
                                     name=name)

        if state is None:
            state = cell.zero_state(input.get_shape().as_list()[0], input.dtype)
        output, new_state = cell(input, state)

        output = bn_act(output, is_training, norm=norm, activation_fn=None)
    return output, new_state 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sigmoid [as 别名]
def call(self, inputs, state, scope=None):
    cell, hidden = state
    new_hidden = _conv([inputs, hidden],
                       self._kernel_shape,
                       4*self._output_channels,
                       self._use_bias)
    gates = array_ops.split(value=new_hidden,
                            num_or_size_splits=4,
                            axis=self._conv_ndims+1)

    input_gate, new_input, forget_gate, output_gate = gates
    new_cell = math_ops.sigmoid(forget_gate + self._forget_bias) * cell
    new_cell += math_ops.sigmoid(input_gate) * math_ops.tanh(new_input)
    output = math_ops.tanh(new_cell) * self._activation(output_gate)

    if self._skip_connection:
      output = array_ops.concat([output, inputs], axis=-1)
    new_state = rnn_cell_impl.LSTMStateTuple(new_cell, output)
    return output, new_state 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sigmoid [as 别名]
def __call__(self, inputs, state, scope=None):
    """Long short-term memory cell (LSTM)."""
    with vs.variable_scope(scope or type(self).__name__):  # "BasicLSTMCell"
      # Parameters of gates are concatenated into one multiply for efficiency.
      if self._state_is_tuple:
        c, h = state
      else:
        c, h = array_ops.split(1, 2, state)
      concat = _linear([inputs, h], 4 * self._num_units, True)

      # i = input_gate, j = new_input, f = forget_gate, o = output_gate
      i, j, f, o = array_ops.split(1, 4, concat)

      new_c = (c * sigmoid(f + self._forget_bias) + sigmoid(i) *
               self._activation(j))
      new_h = self._activation(new_c) * sigmoid(o)

      if self._state_is_tuple:
        new_state = LSTMStateTuple(new_c, new_h)
      else:
        new_state = array_ops.concat(1, [new_c, new_h])
      return new_h, new_state 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sigmoid [as 别名]
def predictions(self, examples):
    """Add operations to compute predictions by the model.

    If logistic_loss is being used, predicted probabilities are returned.
    Otherwise, (raw) linear predictions (w*x) are returned.

    Args:
      examples: Examples to compute predictions on.

    Returns:
      An Operation that computes the predictions for examples.

    Raises:
      ValueError: if examples are not well defined.
    """
    self._assertSpecified(
        ['example_weights', 'sparse_features', 'dense_features'], examples)
    self._assertList(['sparse_features', 'dense_features'], examples)

    result = self._linear_predictions(examples)
    if self._options['loss_type'] == 'logistic_loss':
      # Convert logits to probability for logistic loss predictions.
      with name_scope('sdca/logistic_prediction'):
        result = math_ops.sigmoid(result)
    return result 

# 需要导入模块: from tensorflow.python.ops import math_ops [as 别名]
# 或者: from tensorflow.python.ops.math_ops import sigmoid [as 别名]
def __init__(self,
               p=None,
               dtype=dtypes.int32,
               validate_args=False,
               allow_nan_stats=True,
               name="BernoulliWithSigmoidP"):
    parameters = locals()
    parameters.pop("self")
    with ops.name_scope(name) as ns:
      super(BernoulliWithSigmoidP, self).__init__(
          p=nn.sigmoid(p),
          dtype=dtype,
          validate_args=validate_args,
          allow_nan_stats=allow_nan_stats,
          name=ns)
    self._parameters = parameters