Python backend.log方法代码示例

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import log [as 别名]
def amplitude_to_decibel(x, amin=1e-10, dynamic_range=80.0):
    """[K] Convert (linear) amplitude to decibel (log10(x)).

    Parameters
    ----------
    x: Keras *batch* tensor or variable. It has to be batch because of sample-wise `K.max()`.

    amin: minimum amplitude. amplitude smaller than `amin` is set to this.

    dynamic_range: dynamic_range in decibel

    """
    log_spec = 10 * K.log(K.maximum(x, amin)) / np.log(10).astype(K.floatx())
    if K.ndim(x) > 1:
        axis = tuple(range(K.ndim(x))[1:])
    else:
        axis = None

    log_spec = log_spec - K.max(log_spec, axis=axis, keepdims=True)  # [-?, 0]
    log_spec = K.maximum(log_spec, -1 * dynamic_range)  # [-80, 0]
    return log_spec 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import log [as 别名]
def focal_loss_binary(y_true, y_pred):
    """Binary cross-entropy focal loss
    """
    gamma = 2.0
    alpha = 0.25

    pt_1 = tf.where(tf.equal(y_true, 1),
                    y_pred,
                    tf.ones_like(y_pred))
    pt_0 = tf.where(tf.equal(y_true, 0),
                    y_pred,
                    tf.zeros_like(y_pred))

    epsilon = K.epsilon()
    # clip to prevent NaN and Inf
    pt_1 = K.clip(pt_1, epsilon, 1. - epsilon)
    pt_0 = K.clip(pt_0, epsilon, 1. - epsilon)

    weight = alpha * K.pow(1. - pt_1, gamma)
    fl1 = -K.sum(weight * K.log(pt_1))
    weight = (1 - alpha) * K.pow(pt_0, gamma)
    fl0 = -K.sum(weight * K.log(1. - pt_0))

    return fl1 + fl0 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import log [as 别名]
def focal_loss_categorical(y_true, y_pred):
    """Categorical cross-entropy focal loss"""
    gamma = 2.0
    alpha = 0.25

    # scale to ensure sum of prob is 1.0
    y_pred /= K.sum(y_pred, axis=-1, keepdims=True)

    # clip the prediction value to prevent NaN and Inf
    epsilon = K.epsilon()
    y_pred = K.clip(y_pred, epsilon, 1. - epsilon)

    # calculate cross entropy
    cross_entropy = -y_true * K.log(y_pred)

    # calculate focal loss
    weight = alpha * K.pow(1 - y_pred, gamma)
    cross_entropy *= weight

    return K.sum(cross_entropy, axis=-1) 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import log [as 别名]
def mi_loss(self, y_true, y_pred):
        """ MINE loss function

        Arguments:
            y_true (tensor): Not used since this is
                unsupervised learning
            y_pred (tensor): stack of predictions for
                joint T(x,y) and marginal T(x,y)
        """
        size = self.args.batch_size
        # lower half is pred for joint dist
        pred_xy = y_pred[0: size, :]

        # upper half is pred for marginal dist
        pred_x_y = y_pred[size : y_pred.shape[0], :]
        loss = K.mean(K.exp(pred_x_y))
        loss = K.clip(loss, K.epsilon(), np.finfo(float).max)
        loss = K.mean(pred_xy) - K.log(loss)
        return -loss 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import log [as 别名]
def surv_likelihood(n_intervals):
  """Create custom Keras loss function for neural network survival model. 
  Arguments
      n_intervals: the number of survival time intervals
  Returns
      Custom loss function that can be used with Keras
  """
  def loss(y_true, y_pred):
    """
    Required to have only 2 arguments by Keras.
    Arguments
        y_true: Tensor.
          First half of the values is 1 if individual survived that interval, 0 if not.
          Second half of the values is for individuals who failed, and is 1 for time interval during which failure occured, 0 for other intervals.
          See make_surv_array function.
        y_pred: Tensor, predicted survival probability (1-hazard probability) for each time interval.
    Returns
        Vector of losses for this minibatch.
    """
    cens_uncens = 1. + y_true[:,0:n_intervals] * (y_pred-1.) #component for all individuals
    uncens = 1. - y_true[:,n_intervals:2*n_intervals] * y_pred #component for only uncensored individuals
    return K.sum(-K.log(K.clip(K.concatenate((cens_uncens,uncens)),K.epsilon(),None)),axis=-1) #return -log likelihood
  return loss 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import log [as 别名]
def convert_log(node, params, layers, lambda_func, node_name, keras_name):
    """
    Convert Log layer
    :param node: current operation node
    :param params: operation attributes
    :param layers: available keras layers
    :param lambda_func: function for keras Lambda layer
    :param node_name: internal converter name
    :param keras_name: resulting layer name
    :return: None
    """
    if len(node.input) != 1:
        assert AttributeError('More than 1 input for log layer.')

    input_0 = ensure_tf_type(layers[node.input[0]], name="%s_const" % keras_name)

    def target_layer(x):
        import tensorflow.keras.backend as K
        return K.log(x)

    lambda_layer = keras.layers.Lambda(target_layer, name=keras_name)
    layers[node_name] = lambda_layer(input_0)
    lambda_func[keras_name] = target_layer 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import log [as 别名]
def convert_exp(node, params, layers, lambda_func, node_name, keras_name):
    """
    Convert Exp layer
    :param node: current operation node
    :param params: operation attributes
    :param layers: available keras layers
    :param lambda_func: function for keras Lambda layer
    :param node_name: resulting layer name
    :return: None
    """
    if len(node.input) != 1:
        assert AttributeError('More than 1 input for log layer.')

    input_0 = ensure_tf_type(layers[node.input[0]], name="%s_const" % keras_name)

    def target_layer(x):
        import tensorflow.keras.backend as K
        return K.exp(x)

    lambda_layer = keras.layers.Lambda(target_layer, name=keras_name)
    layers[node_name] = lambda_layer(input_0)
    lambda_func[keras_name] = target_layer 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import log [as 别名]
def loss(self, y_true, y_pred):
        """ categorical crossentropy loss """

        if self.crop_indices is not None:
            y_true = utils.batch_gather(y_true, self.crop_indices)
            y_pred = utils.batch_gather(y_pred, self.crop_indices)

        if self.use_float16:
            y_true = K.cast(y_true, 'float16')
            y_pred = K.cast(y_pred, 'float16')

        # scale and clip probabilities
        # this should not be necessary for softmax output.
        y_pred /= K.sum(y_pred, axis=-1, keepdims=True)
        y_pred = K.clip(y_pred, K.epsilon(), 1)

        # compute log probability
        log_post = K.log(y_pred)  # likelihood

        # loss
        loss = - y_true * log_post

        # weighted loss
        if self.weights is not None:
            loss *= self.weights

        if self.vox_weights is not None:
            loss *= self.vox_weights

        # take the total loss
        # loss = K.batch_flatten(loss)
        mloss = K.mean(K.sum(K.cast(loss, 'float32'), -1))
        tf.verify_tensor_all_finite(mloss, 'Loss not finite')
        return mloss 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import log [as 别名]
def logtanh(x, a=1):
    """
    log * tanh

    See Also: arcsinh
    """
    return K.tanh(x) *  K.log(2 + a * abs(x)) 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import log [as 别名]
def customLoss(y_true,y_pred):
  log1 = 1.5 * y_true * K.log(y_pred + 1e-9) * K.pow(1-y_pred, 2)
  log0 = 0.5 * (1 - y_true) * K.log((1 - y_pred) + 1e-9) * K.pow(y_pred, 2)
  return (- K.sum(K.mean(log0 + log1, axis = 0))) 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import log [as 别名]
def _get_scale(alpha, x, q):
  """Gets scaling factor for scaling the tensor per channel.

  Arguments:
    alpha: A float or string. When it is string, it should be either "auto" or
      "auto_po2", and
       scale = sum(x * q, axis=all but last) / sum(q * q, axis=all but last)
     x: A tensor object. Its elements are in float.
     q: A tensor object. Its elements are in quantized format of x.

  Returns:
    A scaling factor tensor or scala for scaling tensor per channel.
  """

  if isinstance(alpha, six.string_types) and "auto" in alpha:
    assert alpha in ["auto", "auto_po2"]
    x_shape = x.shape.as_list()
    len_axis = len(x_shape)
    if len_axis > 1:
      if K.image_data_format() == "channels_last":
        axis = list(range(len_axis - 1))
      else:
        axis = list(range(1, len_axis))
      qx = K.mean(tf.math.multiply(x, q), axis=axis, keepdims=True)
      qq = K.mean(tf.math.multiply(q, q), axis=axis, keepdims=True)
    else:
      qx = K.mean(x * q, axis=0, keepdims=True)
      qq = K.mean(q * q, axis=0, keepdims=True)
    scale = qx / (qq + K.epsilon())
    if alpha == "auto_po2":
      scale = K.pow(2.0,
                    tf.math.round(K.log(scale + K.epsilon()) / np.log(2.0)))
  elif alpha is None:
    scale = 1.0
  elif isinstance(alpha, np.ndarray):
    scale = alpha
  else:
    scale = float(alpha)
  return scale 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import log [as 别名]
def stochastic_round_po2(x):
  """Performs stochastic rounding for the power of two."""
  # TODO(hzhuang): test stochastic_round_po2 and constraint.
  # because quantizer is applied after constraint.
  y = tf.abs(x)
  eps = tf.keras.backend.epsilon()
  log2 = tf.keras.backend.log(2.0)

  x_log2 = tf.round(tf.keras.backend.log(y + eps) / log2)
  po2 = tf.cast(pow(2.0, tf.cast(x_log2, dtype="float32")), dtype="float32")
  left_val = tf.where(po2 > y, x_log2 - 1, x_log2)
  right_val = tf.where(po2 > y, x_log2, x_log2 + 1)
  # sampling in [2**left_val, 2**right_val].
  minval = 2 ** left_val
  maxval = 2 ** right_val
  val = tf.random.uniform(tf.shape(y), minval=minval, maxval=maxval)
  # use y as a threshold to keep the probabliy [2**left_val, y, 2**right_val]
  # so that the mean value of the sample should be y
  x_po2 = tf.where(y < val, left_val, right_val)
  """
  x_log2 = stochastic_round(tf.keras.backend.log(y + eps) / log2)
  sign = tf.sign(x)
  po2 = (
      tf.sign(x) *
      tf.cast(pow(2.0, tf.cast(x_log2, dtype="float32")), dtype="float32")
  )
  """
  return x_po2 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import log [as 别名]
def __call__(self, x):
    non_sign_bits = self.bits - 1
    m = pow(2, non_sign_bits)
    m_i = pow(2, self.integer)
    p = _sigmoid(x / m_i) * m
    rp = 2.0 * (_round_through(p) / m) - 1.0
    u_law_p = tf.sign(rp) * tf.keras.backend.log(
        1 + self.u * tf.abs(rp)) / tf.keras.backend.log(1 + self.u)
    xq = m_i * tf.keras.backend.clip(u_law_p, -1.0 +
                                     (1.0 * self.symmetric) / m, 1.0 - 1.0 / m)
    return xq 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import log [as 别名]
def _need_exponent_sign_bit_check(max_value):
  """Checks whether the sign bit of exponent is needed.

  This is used by quantized_po2 and quantized_relu_po2.

  Args:
    max_value: the maximum value allowed.

  Returns:
    An integer. 1: sign_bit is needed. 0: sign_bit is not needed.
  """

  if max_value is not None:
    if max_value < 0:
      raise ValueError("po2 max_value should be non-negative.")
    if max_value > 1:
      # if max_value is larger than 1,
      #   the exponent could be positive and negative.
      #   e.g., log(max_value) > 0 when max_value > 1
      need_exponent_sign_bit = 1
    else:
      need_exponent_sign_bit = 0
  else:
    # max_value is not specified, so we cannot decide the range.
    # Then we need to put sign_bit for exponent to be safe
    need_exponent_sign_bit = 1
  return need_exponent_sign_bit 

# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import log [as 别名]
def mi_loss(c, q_of_c_given_x):
    """ Mutual information, Equation 5 in [2],
        assuming H(c) is constant
    """
    # mi_loss = -c * log(Q(c|x))
    return -K.mean(K.sum(c * K.log(q_of_c_given_x + K.epsilon()), 
                                   axis=1))