Python tensorflow.keras.backend.sqrt() Examples

def distance_matrix(self, D):
    """Calcuates the distance matrix from the distance tensor

    B = batch_size, N = max_num_atoms, M = max_num_neighbors, d = num_features

    Parameters
    ----------
    D: tf.Tensor of shape (B, N, M, d)
      Distance tensor.

    Returns
    -------
    R: tf.Tensor of shape (B, N, M)
       Distance matrix.
    """
    R = tf.reduce_sum(tf.multiply(D, D), 3)
    R = tf.sqrt(R)
    return R 

def distance_matrix(self, coordinates, flags):
    """ Generate distance matrix """
    # (TODO YTZ:) faster, less memory intensive way
    # r = tf.reduce_sum(tf.square(coordinates), 2)
    # r = tf.expand_dims(r, -1)
    # inner = 2*tf.matmul(coordinates, tf.transpose(coordinates, perm=[0,2,1]))
    # # inner = 2*tf.matmul(coordinates, coordinates, transpose_b=True)

    # d = r - inner + tf.transpose(r, perm=[0,2,1])
    # d = tf.nn.relu(d) # fix numerical instabilities about diagonal
    # d = tf.sqrt(d) # does this have negative elements? may be unstable for diagonals

    max_atoms = self.max_atoms
    tensor1 = tf.stack([coordinates] * max_atoms, axis=1)
    tensor2 = tf.stack([coordinates] * max_atoms, axis=2)

    # Calculate pairwise distance
    d = tf.sqrt(
        tf.reduce_sum(tf.math.squared_difference(tensor1, tensor2), axis=3) +
        1e-7)

    d = d * flags
    return d 

def build(self, input_shape):
    no_features = int(input_shape[0][2])
    no_A = int(input_shape[1][2])
    self.W = tf.Variable(
        tf.random.truncated_normal(
            [no_features * no_A, self.num_filters],
            stddev=np.sqrt(1.0 / (no_features * (no_A + 1) * 1.0))),
        name='weights',
        dtype=tf.float32)
    self.W_I = tf.Variable(
        tf.random.truncated_normal(
            [no_features, self.num_filters],
            stddev=np.sqrt(1.0 / (no_features * (no_A + 1) * 1.0))),
        name='weights_I',
        dtype=tf.float32)
    self.b = tf.Variable(tf.constant(0.1), name='bias', dtype=tf.float32)
    self.built = True 

def convert_sqrt(node, params, layers, lambda_func, node_name, keras_name):
    """
    Convert Sqrt 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 sqrt 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.sqrt(x)

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

def mcor(y_true, y_pred):
    # Matthews correlation
    y_pred_pos = K.round(K.clip(y_pred, 0, 1))
    y_pred_neg = 1 - y_pred_pos

    y_pos = K.round(K.clip(y_true, 0, 1))
    y_neg = 1 - y_pos

    tp = K.sum(y_pos * y_pred_pos)
    tn = K.sum(y_neg * y_pred_neg)

    fp = K.sum(y_neg * y_pred_pos)
    fn = K.sum(y_pos * y_pred_neg)

    numerator = (tp * tn - fp * fn)
    denominator = K.sqrt((tp + fp) * (tp + fn) * (tn + fp) * (tn + fn))

    return numerator / (denominator + K.epsilon()) 

def loss(self, y_true, y_pred):

        # get the value for the true and fake images
        disc_true = self.disc(y_true)
        disc_pred = self.disc(y_pred)

        # sample a x_hat by sampling along the line between true and pred
        # z = tf.placeholder(tf.float32, shape=[None, 1])
        # shp = y_true.get_shape()[0]
        # WARNING: SHOULD REALLY BE shape=[batch_size, 1] !!!
        # self.batch_size does not work, since it's not None!!!
        alpha = K.random_uniform(shape=[K.shape(y_pred)[0], 1, 1, 1])
        diff = y_pred - y_true
        interp = y_true + alpha * diff

        # take gradient of D(x_hat)
        gradients = K.gradients(self.disc(interp), [interp])[0]
        grad_pen = K.mean(K.square(K.sqrt(K.sum(K.square(gradients), axis=1))-1))

        # compute loss
        return (K.mean(disc_pred) - K.mean(disc_true)) + self.lambda_gp * grad_pen 

def mcor(y_true, y_pred):
    # matthews_correlation
    y_pred_pos = K.round(K.clip(y_pred, 0, 1))
    y_pred_neg = 1 - y_pred_pos

    y_pos = K.round(K.clip(y_true, 0, 1))
    y_neg = 1 - y_pos

    tp = K.sum(y_pos * y_pred_pos)
    tn = K.sum(y_neg * y_pred_neg)

    fp = K.sum(y_neg * y_pred_pos)
    fn = K.sum(y_pos * y_pred_neg)

    numerator = (tp * tn - fp * fn)
    denominator = K.sqrt((tp + fp) * (tp + fn) * (tn + fp) * (tn + fn))

    return numerator / (denominator + K.epsilon()) 

def frn_layer_keras(x, tau, beta, gamma, epsilon=1e-6):
    # x: Input tensor of shape [BxHxWxC].
    # tau, beta, gamma: Variables of shape [1, 1, 1, C].
    # eps: A scalar constant or learnable variable.
    # Compute the mean norm of activations per channel.
    nu2 = K.mean(K.square(x), axis=[1, 2], keepdims=True)
    # Perform FRN.
    x = x * 1 / K.sqrt(nu2 + K.abs(epsilon))
    # Return after applying the Offset-ReLU non-linearity.
    return K.maximum(gamma * x + beta, tau) 

def _cosine_dist(x, y):
  """Computes the inner product (cosine distance) between two tensors.

  Parameters
  ----------
  x: tf.Tensor
    Input Tensor
  y: tf.Tensor
    Input Tensor
  """
  denom = (backend.sqrt(backend.sum(tf.square(x)) * backend.sum(tf.square(y))) +
           backend.epsilon())
  return backend.dot(x, tf.transpose(y)) / denom 

def _pairwise_distances(self, inputs: List[Tensor]) -> Tensor:
        emb_c, emb_r = inputs
        bs = K.shape(emb_c)[0]
        embeddings = K.concatenate([emb_c, emb_r], 0)
        dot_product = K.dot(embeddings, K.transpose(embeddings))
        square_norm = K.batch_dot(embeddings, embeddings, axes=1)
        distances = K.transpose(square_norm) - 2.0 * dot_product + square_norm
        distances = distances[0:bs, bs:bs+bs]
        distances = K.clip(distances, 0.0, None)
        mask = K.cast(K.equal(distances, 0.0), K.dtype(distances))
        distances = distances + mask * 1e-16
        distances = K.sqrt(distances)
        distances = distances * (1.0 - mask)
        return distances 

def _euclidian_dist(self, x_pair: List[Tensor]) -> Tensor:
        x1_norm = K.l2_normalize(x_pair[0], axis=1)
        x2_norm = K.l2_normalize(x_pair[1], axis=1)
        diff = x1_norm - x2_norm
        square = K.square(diff)
        _sum = K.sum(square, axis=1)
        _sum = K.clip(_sum, min_value=1e-12, max_value=None)
        dist = K.sqrt(_sum) / 2.
        return dist 

def angle_zyz_difference(ang1=np.zeros(3), ang2=np.zeros(3)):
    loc1_r = np.zeros(ang1.shape)
    loc2_r = np.zeros(ang2.shape)

    rm1 = rotation_matrix_zyz(ang1)
    rm2 = rotation_matrix_zyz(ang2)
    loc1_r_t = np.array([loc1_r, loc1_r, loc1_r])
    loc2_r_t = np.array([loc2_r, loc2_r, loc2_r])

    dif_m = (rm1.dot(np.eye(3) - loc1_r_t)).transpose() - (rm2.dot(np.eye(3) - loc2_r_t)).transpose()
    dif_d = math.sqrt(np.square(dif_m).sum())


    return dif_d 

def correlation_coefficient_loss(y_true, y_pred):
    x = y_true                      
    y = y_pred                                  
    mx = K.mean(x)  

    my = K.mean(y)                                     
    xm, ym = x-mx, y-my                                                
    r_num = K.sum(tf.multiply(xm,ym))                                     
    r_den = K.sqrt(tf.multiply(K.sum(K.square(xm)), K.sum(K.square(ym))))
    r = r_num / r_den
    r = K.maximum(K.minimum(r, 1.0), -1.0)

    return 1 - K.square(r) 

def _euclidean_distance(x, y):
    return K.sqrt(K.maximum(K.sum(K.square(x - y), axis=-1, keepdims=True), K.epsilon())) 

def earth_movers_distance(y_true, y_pred):
    cdf_true = K.cumsum(y_true, axis=-1)
    cdf_pred = K.cumsum(y_pred, axis=-1)
    emd = K.sqrt(K.mean(K.square(cdf_true - cdf_pred), axis=-1))
    return K.mean(emd) 

def call(self, inputs):

        #To channels last
        x = tf.transpose(inputs[0], [0, 3, 1, 2])

        #Get weight and bias modulations
        #Make sure w's shape is compatible with self.kernel
        w = K.expand_dims(K.expand_dims(K.expand_dims(inputs[1], axis = 1), axis = 1), axis = -1)

        #Add minibatch layer to weights
        wo = K.expand_dims(self.kernel, axis = 0)

        #Modulate
        weights = wo * (w+1)

        #Demodulate
        if self.demod:
            d = K.sqrt(K.sum(K.square(weights), axis=[1,2,3], keepdims = True) + 1e-8)
            weights = weights / d

        #Reshape/scale input
        x = tf.reshape(x, [1, -1, x.shape[2], x.shape[3]]) # Fused => reshape minibatch to convolution groups.
        w = tf.reshape(tf.transpose(weights, [1, 2, 3, 0, 4]), [weights.shape[1], weights.shape[2], weights.shape[3], -1])

        x = tf.nn.conv2d(x, w,
                strides=self.strides,
                padding="SAME",
                data_format="NCHW")

        # Reshape/scale output.
        x = tf.reshape(x, [-1, self.filters, x.shape[2], x.shape[3]]) # Fused => reshape convolution groups back to minibatch.
        x = tf.transpose(x, [0, 2, 3, 1])

        return x 

def build(self, input_shape):
    no_features = int(input_shape[0][-1])
    self.W = tf.Variable(
        tf.random.truncated_normal(
            [no_features, self.num_vertices],
            stddev=1.0 / np.sqrt(no_features)),
        name='weights',
        dtype=tf.float32)
    self.b = tf.Variable(tf.constant(0.1), name='bias', dtype=tf.float32)
    self.built = True 

def call(self, inputs, **kwargs):
        input_shape = K.int_shape(inputs)
        tensor_input_shape = K.shape(inputs)

        # Prepare broadcasting shape.
        reduction_axes = list(range(len(input_shape)))
        del reduction_axes[self.axis]
        broadcast_shape = [1] * len(input_shape)
        broadcast_shape[self.axis] = input_shape[self.axis] // self.groups
        broadcast_shape.insert(1, self.groups)

        reshape_group_shape = K.shape(inputs)
        group_axes = [reshape_group_shape[i] for i in range(len(input_shape))]
        group_axes[self.axis] = input_shape[self.axis] // self.groups
        group_axes.insert(1, self.groups)

        # reshape inputs to new group shape
        group_shape = [group_axes[0], self.groups] + group_axes[2:]
        group_shape = K.stack(group_shape)
        inputs = K.reshape(inputs, group_shape)

        group_reduction_axes = list(range(len(group_axes)))
        group_reduction_axes = group_reduction_axes[2:]

        mean = K.mean(inputs, axis=group_reduction_axes, keepdims=True)
        variance = K.var(inputs, axis=group_reduction_axes, keepdims=True)

        inputs = (inputs - mean) / (K.sqrt(variance + self.epsilon))

        # prepare broadcast shape
        inputs = K.reshape(inputs, group_shape)
        outputs = inputs

        # In this case we must explicitly broadcast all parameters.
        if self.scale:
            broadcast_gamma = K.reshape(self.gamma, broadcast_shape)
            outputs = outputs * broadcast_gamma

        if self.center:
            broadcast_beta = K.reshape(self.beta, broadcast_shape)
            outputs = outputs + broadcast_beta

        outputs = K.reshape(outputs, tensor_input_shape)

        return outputs