Python keras.backend.ones_like() Examples

def get_constants(self, x):
      constants = []
      if 0 < self.dropout_U < 1:
          ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
          ones = K.concatenate([ones] * self.output_dim, 1)
          B_U = K.in_train_phase(K.dropout(ones, self.dropout_U), ones)
          constants.append(B_U)
      else:
          constants.append(K.cast_to_floatx(1.))
      if self.consume_less == 'cpu' and 0 < self.dropout_W < 1:
          input_shape = self.input_spec[0].shape
          input_dim = input_shape[-1]
          ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
          ones = K.concatenate([ones] * input_dim, 1)
          B_W = K.in_train_phase(K.dropout(ones, self.dropout_W), ones)
          constants.append(B_W)
      else:
          constants.append(K.cast_to_floatx(1.))
      return constants 

def call(self, inputs, mask=None):
        """
        Extract the GRU output for the target document index for the forward
        and backwards GRU outputs, and then concatenate them. If the target word index
        is at index l, and there are T total document words, the desired output
        in the forward pass is at GRU_f[l] (ignoring the batched case) and the
        desired output of the backwards pass is at GRU_b[T-l].

        We need to get these two vectors and concatenate them. To do so, we'll
        reverse the backwards GRU, which allows us to use the same index/mask for both.
        """
        # TODO(nelson): deal with case where cloze token appears multiple times
        # in a question.
        word_indices, gru_f, gru_b = inputs
        index_mask = K.cast(K.equal((K.ones_like(word_indices) * self.target_index),
                                    word_indices), "float32")
        gru_mask = K.repeat_elements(K.expand_dims(index_mask, -1), K.int_shape(gru_f)[-1], K.ndim(gru_f) - 1)
        masked_gru_f = switch(gru_mask, gru_f, K.zeros_like(gru_f))
        selected_gru_f = K.sum(masked_gru_f, axis=1)
        masked_gru_b = switch(gru_mask, gru_b, K.zeros_like(gru_b))
        selected_gru_b = K.sum(masked_gru_b, axis=1)
        selected_bigru = K.concatenate([selected_gru_f, selected_gru_b], axis=-1)
        return selected_bigru 

def get_constants(self, x):
        constants = []
        if 0 < self.dropout_U < 1:
            ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
            ones = K.concatenate([ones] * self.output_dim, 1)
            B_U = [K.in_train_phase(K.dropout(ones, self.dropout_U), ones) for _ in range(3)]
            constants.append(B_U)
        else:
            constants.append([K.cast_to_floatx(1.) for _ in range(3)])

        if 0 < self.dropout_W < 1:
            input_shape = self.input_spec[0].shape
            input_dim = input_shape[-1]
            ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
            ones = K.concatenate([ones] * input_dim, 1)
            B_W = [K.in_train_phase(K.dropout(ones, self.dropout_W), ones) for _ in range(3)]
            constants.append(B_W)
        else:
            constants.append([K.cast_to_floatx(1.) for _ in range(3)])
        return constants 

def get_constants(self, x):
		constants = []
		if 0 < self.dropout_U < 1:
			ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
			ones = K.tile(ones, (1, self.hidden_recurrent_dim))
			B_U = K.in_train_phase(K.dropout(ones, self.dropout_U), ones)
			constants.append(B_U)
		else:
			constants.append(K.cast_to_floatx(1.))
        
		if self.consume_less == 'cpu' and 0 < self.dropout_W < 1:
			input_shape = self.input_spec[0].shape
			input_dim = input_shape[-1]
			ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
			ones = K.tile(ones, (1, input_dim))
			B_W = K.in_train_phase(K.dropout(ones, self.dropout_W), ones)
			constants.append(B_W)
		else:
			constants.append(K.cast_to_floatx(1.))

		return constants 

def get_constants(self, x):
		constants = []
		if 0 < self.dropout_U < 1:
			ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
			ones = K.tile(ones, (1, self.input_dim))
			B_U = [K.in_train_phase(K.dropout(ones, self.dropout_U), ones) for _ in range(4)]
			constants.append(B_U)
		else:
			constants.append([K.cast_to_floatx(1.) for _ in range(4)])

		if 0 < self.dropout_W < 1:
			input_shape = K.int_shape(x)
			input_dim = input_shape[-1]
			ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
			ones = K.tile(ones, (1, int(input_dim)))
			B_W = [K.in_train_phase(K.dropout(ones, self.dropout_W), ones) for _ in range(4)]
			constants.append(B_W)
		else:
			constants.append([K.cast_to_floatx(1.) for _ in range(4)])
		return constants 

def get_constants(self, x):
    constants = []
    if 0 < self.dropout_U < 1:
      ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
      ones = K.tile(ones, (1, self.output_dim))
      B_U = [K.in_train_phase(K.dropout(ones, self.dropout_U), ones) for _ in range(3)]
      constants.append(B_U)
    else:
      constants.append([K.cast_to_floatx(1.) for _ in range(3)])

    if 0 < self.dropout_W < 1:
      input_shape = self.input_spec[0].shape
      input_dim = input_shape[-1]
      ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
      ones = K.tile(ones, (1, input_dim))
      B_W = [K.in_train_phase(K.dropout(ones, self.dropout_W), ones) for _ in range(3)]
      constants.append(B_W)
    else:
      constants.append([K.cast_to_floatx(1.) for _ in range(3)])
    return constants 

def get_constants(self, x):
        constants = []
        if 0 < self.dropout_U < 1:
            ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
            ones = K.concatenate([ones] * self.output_dim, 1)
            B_U = [K.in_train_phase(K.dropout(ones, self.dropout_U), ones) for _ in range(4)]
            constants.append(B_U)
        else:
            constants.append([K.cast_to_floatx(1.) for _ in range(4)])

        if 0 < self.dropout_W < 1:
            input_shape = self.input_spec[0].shape
            input_dim = input_shape[-1]
            ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
            ones = K.concatenate([ones] * input_dim, 1)
            B_W = [K.in_train_phase(K.dropout(ones, self.dropout_W), ones) for _ in range(4)]
            constants.append(B_W)
        else:
            constants.append([K.cast_to_floatx(1.) for _ in range(4)])
        return constants 

def get_constants(self, x):
        constants = []
        if 0 < self.dropout_U < 1:
            ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
            ones = K.tile(ones, (1, self.output_dim))
            B_U = [K.in_train_phase(K.dropout(ones, self.dropout_U), ones) for _ in range(4)]
            constants.append(B_U)
        else:
            constants.append([K.cast_to_floatx(1.) for _ in range(4)])

        if 0 < self.dropout_W < 1:
            input_shape = self.input_spec[0].shape
            input_dim = input_shape[-1]
            ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
            ones = K.tile(ones, (1, int(input_dim)))
            B_W = [K.in_train_phase(K.dropout(ones, self.dropout_W), ones) for _ in range(4)]
            constants.append(B_W)
        else:
            constants.append([K.cast_to_floatx(1.) for _ in range(4)])
        return constants 

def call(self, inputs, mask=None):
        assert(isinstance(inputs, list) and len(inputs) == 5)
        uQ, WQ_u, WQ_v, v, VQ_r = inputs
        uQ_mask = mask[0] if mask is not None else None

        ones = K.ones_like(K.sum(uQ, axis=1, keepdims=True)) # (B, 1, 2H)
        s_hat = K.dot(uQ, WQ_u)
        s_hat += K.dot(ones, K.dot(WQ_v, VQ_r))
        s_hat = K.tanh(s_hat)
        s = K.dot(s_hat, v)
        s = K.batch_flatten(s)

        a = softmax(s, mask=uQ_mask, axis=1)

        rQ = K.batch_dot(uQ, a, axes=[1, 1])

        return rQ 

def _ternarize(W, H=1):
    '''The weights' ternarization function, 

    # References:
    - [Recurrent Neural Networks with Limited Numerical Precision](http://arxiv.org/abs/1608.06902)
    - [Ternary Weight Networks](http://arxiv.org/abs/1605.04711)
    '''
    W /= H

    ones = K.ones_like(W)
    zeros = K.zeros_like(W)
    Wt = switch(W > 0.5, ones, switch(W <= -0.5, -ones, zeros))

    Wt *= H

    return Wt 

def get_constants(self, inputs, training=None):
        constants = []
        '''if 0 < self.dropout_U < 1:
            ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
            ones = K.tile(ones, (1, self.units))
            B_U = [K.in_train_phase(K.dropout(ones, self.dropout_U), ones) for _ in range(3)]
            constants.append(B_U)
        else:
            constants.append([K.cast_to_floatx(1.) for _ in range(3)])

        if 0 < self.dropout_W < 1:
            input_shape = K.int_shape(x)
            input_dim = input_shape[-1]
            ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
            ones = K.tile(ones, (1, int(input_dim)))
            B_W = [K.in_train_phase(K.dropout(ones, self.dropout_W), ones) for _ in range(3)]
            constants.append(B_W)
        else:'''
        constants.append([K.cast_to_floatx(1.) for _ in range(3)])
        return constants 

def get_constants(self, inputs, training=None):
        constants = []
        '''if 0 < self.dropout_U < 1:
            ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
            ones = K.tile(ones, (1, self.units))
            B_U = [K.in_train_phase(K.dropout(ones, self.dropout_U), ones) for _ in range(3)]
            constants.append(B_U)
        else:
            constants.append([K.cast_to_floatx(1.) for _ in range(3)])

        if 0 < self.dropout_W < 1:
            input_shape = K.int_shape(x)
            input_dim = input_shape[-1]
            ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
            ones = K.tile(ones, (1, int(input_dim)))
            B_W = [K.in_train_phase(K.dropout(ones, self.dropout_W), ones) for _ in range(3)]
            constants.append(B_W)
        else:'''
        constants.append([K.cast_to_floatx(1.) for _ in range(3)])
        return constants 

def get_constants(self, inputs, training=None):
        constants = []
        '''if 0 < self.dropout_U < 1:
            ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
            ones = K.tile(ones, (1, self.units))
            B_U = [K.in_train_phase(K.dropout(ones, self.dropout_U), ones) for _ in range(3)]
            constants.append(B_U)
        else:
            constants.append([K.cast_to_floatx(1.) for _ in range(3)])

        if 0 < self.dropout_W < 1:
            input_shape = K.int_shape(x)
            input_dim = input_shape[-1]
            ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
            ones = K.tile(ones, (1, int(input_dim)))
            B_W = [K.in_train_phase(K.dropout(ones, self.dropout_W), ones) for _ in range(3)]
            constants.append(B_W)
        else:'''
        constants.append([K.cast_to_floatx(1.) for _ in range(3)])
        return constants 

def call(self, x, mask=None):
        mean = super(IntraAttention, self).call(x, mask)
        # x: (batch_size, input_length, input_dim)
        # mean: (batch_size, input_dim)
        ones = K.expand_dims(K.mean(K.ones_like(x), axis=(0, 2)), dim=0)  # (1, input_length)
        # (batch_size, input_length, input_dim)
        tiled_mean = K.permute_dimensions(K.dot(K.expand_dims(mean), ones), (0, 2, 1))
        if mask is not None:
            if K.ndim(mask) > K.ndim(x):
                # Assuming this is because of the bug in Bidirectional. Temporary fix follows.
                # TODO: Fix Bidirectional.
                mask = K.any(mask, axis=(-2, -1))
            if K.ndim(mask) < K.ndim(x):
                mask = K.expand_dims(mask)
            x = switch(mask, x, K.zeros_like(x))
        # (batch_size, input_length, proj_dim)
        projected_combination = K.tanh(K.dot(x, self.vector_projector) + K.dot(tiled_mean, self.mean_projector))
        scores = K.dot(projected_combination, self.scorer)  # (batch_size, input_length)
        weights = K.softmax(scores)  # (batch_size, input_length)
        attended_x = K.sum(K.expand_dims(weights) * x, axis=1)  # (batch_size, input_dim)
        return attended_x 

def get_constants(self, x):
        constants = []
        if 0 < self.dropout_U < 1:
            ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
            ones = K.tile(ones, (1, self.output_dim))
            B_U = [K.in_train_phase(K.dropout(ones, self.dropout_U), ones) for _ in range(3)]
            constants.append(B_U)
        else:
            constants.append([K.cast_to_floatx(1.) for _ in range(3)])

        if 0 < self.dropout_W < 1:
            input_shape = K.int_shape(x)
            input_dim = input_shape[-1]
            ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
            ones = K.tile(ones, (1, int(input_dim)))
            B_W = [K.in_train_phase(K.dropout(ones, self.dropout_W), ones) for _ in range(3)]
            constants.append(B_W)
        else:
            constants.append([K.cast_to_floatx(1.) for _ in range(3)])
        return constants 

def weighted_bce_dice_loss(y_true, y_pred):
    y_true = K.cast(y_true, 'float32')
    y_pred = K.cast(y_pred, 'float32')
    # if we want to get same size of output, kernel size must be odd number
    if K.int_shape(y_pred)[1] == 128:
        kernel_size = 11
    elif K.int_shape(y_pred)[1] == 256:
        kernel_size = 21
    elif K.int_shape(y_pred)[1] == 512:
        kernel_size = 21
    elif K.int_shape(y_pred)[1] == 1024:
        kernel_size = 41
    else:
        raise ValueError('Unexpected image size')
    averaged_mask = K.pool2d(
        y_true, pool_size=(kernel_size, kernel_size), strides=(1, 1), padding='same', pool_mode='avg')
    border = K.cast(K.greater(averaged_mask, 0.005), 'float32') * K.cast(K.less(averaged_mask, 0.995), 'float32')
    weight = K.ones_like(averaged_mask)
    w0 = K.sum(weight)
    weight += border * 2
    w1 = K.sum(weight)
    weight *= (w0 / w1)
    loss = weighted_bce_loss(y_true, y_pred, weight) + (1 - weighted_dice_coeff(y_true, y_pred, weight))
    return loss 

def contingency_table(y, z):
    """Compute contingency table."""
    y = K.round(y)
    z = K.round(z)

    def count_matches(a, b):
        tmp = K.concatenate([a, b])
        return K.sum(K.cast(K.all(tmp, -1), K.floatx()))

    ones = K.ones_like(y)
    zeros = K.zeros_like(y)
    y_ones = K.equal(y, ones)
    y_zeros = K.equal(y, zeros)
    z_ones = K.equal(z, ones)
    z_zeros = K.equal(z, zeros)

    tp = count_matches(y_ones, z_ones)
    tn = count_matches(y_zeros, z_zeros)
    fp = count_matches(y_zeros, z_ones)
    fn = count_matches(y_ones, z_zeros)

    return (tp, tn, fp, fn) 

def weighted_dice_loss(y_true, y_pred):
    y_true = K.cast(y_true, 'float32')
    y_pred = K.cast(y_pred, 'float32')
    # if we want to get same size of output, kernel size must be odd number
    if K.int_shape(y_pred)[1] == 128:
        kernel_size = 11
    elif K.int_shape(y_pred)[1] == 256:
        kernel_size = 21
    elif K.int_shape(y_pred)[1] == 512:
        kernel_size = 21
    elif K.int_shape(y_pred)[1] == 1024:
        kernel_size = 41
    else:
        raise ValueError('Unexpected image size')
    averaged_mask = K.pool2d(
        y_true, pool_size=(kernel_size, kernel_size), strides=(1, 1), padding='same', pool_mode='avg')
    border = K.cast(K.greater(averaged_mask, 0.005), 'float32') * K.cast(K.less(averaged_mask, 0.995), 'float32')
    weight = K.ones_like(averaged_mask)
    w0 = K.sum(weight)
    weight += border * 2
    w1 = K.sum(weight)
    weight *= (w0 / w1)
    loss = 1 - weighted_dice_coeff(y_true, y_pred, weight)
    return loss 

def get_constants(self, x):
      constants = []
      if 0 < self.dropout_U < 1:
          ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
          ones = K.concatenate([ones] * self.output_dim, 1)
          B_U = K.in_train_phase(K.dropout(ones, self.dropout_U), ones)
          constants.append(B_U)
      else:
          constants.append(K.cast_to_floatx(1.))
      if self.consume_less == 'cpu' and 0 < self.dropout_W < 1:
          input_shape = self.input_spec[0].shape
          input_dim = input_shape[-1]
          ones = K.ones_like(K.reshape(x[:, 0, 0], (-1, 1)))
          ones = K.concatenate([ones] * input_dim, 1)
          B_W = K.in_train_phase(K.dropout(ones, self.dropout_W), ones)
          constants.append(B_W)
      else:
          constants.append(K.cast_to_floatx(1.))
      return constants 

def tile_vector(vector, matrix):
    """
    NOTE: If your matrix has known shape (i.e., the relevant dimension from `K.int_shape(matrix) is
    not None`), you should just use `K.repeat_elements(vector)` instead of this.  This method
    works, however, when the number of rows in your matrix is unknown at graph compilation time.

    This method takes a (collection of) vector(s) (shape: (batch_size, vector_dim)), and tiles that
    vector a number of times, giving a matrix of shape (batch_size, tile_length, vector_dim).  (I
    say "vector" and "matrix" here because I'm ignoring the batch_size).  We need the matrix as
    input so we know what the tile_length is - the matrix is otherwise ignored.

    This is necessary in a number of places in the code.  For instance, if you want to do a dot
    product of a vector with all of the vectors in a matrix, the most efficient way to do that is
    to tile the vector first, then do an element-wise product with the matrix, then sum out the
    last mode.  So, we capture this functionality here.

    This is not done as a Keras Layer, however; if you want to use this function, you'll need to do
    it _inside_ of a Layer somehow, either in a Lambda or in the call() method of a Layer you're
    writing.
    """
    # Tensorflow can't use unknown sizes at runtime, so we have to make use of the broadcasting
    # ability of TF and Theano instead to create the tiled sentence encoding.

    # Shape: (tile_length, batch_size, vector_dim)
    k_ones = K.permute_dimensions(K.ones_like(matrix), [1, 0, 2])

    # Now we have a (tile_length, batch_size, vector_dim)*(batch_size, vector_dim)
    # elementwise multiplication which is broadcast. We then reshape back.
    tiled_vector = K.permute_dimensions(k_ones * vector, [1, 0, 2])
    return tiled_vector 

def _trans(theta):
    tx = theta[:,3:4]
    ty = theta[:,4:5]
    tz = theta[:,5:6]
    zero = K.zeros_like(tx)
    one = K.ones_like(tx)
    first = K.reshape(K.concatenate([one,zero,zero,tx],axis=1),(-1,1,4))
    second = K.reshape(K.concatenate([zero,one,zero,ty],axis=1),(-1,1,4))
    third = K.reshape(K.concatenate([zero,zero,one,tz],axis=1),(-1,1,4))
    trans = K.concatenate([first,second,third],axis=1)
    trans = trans.reshape((trans.shape[0],3,4))

    return trans 

def _sample_weights(y, mask=None):
    """Compute sample weights."""
    if mask is None:
        weights = K.ones_like(y)
    else:
        weights = 1 - K.cast(K.equal(y, mask), K.floatx())
    return weights 

def call(self, inputs, mask=None):
        # tensor_a, mask_a are of shape (batch size, length_a)
        # tensor_b mask_b are of shape (batch size, length_b)
        tensor_a, tensor_b = inputs
        if mask is None:
            mask_b = K.ones_like(tensor_b)
        else:
            mask_b = mask[1]
        length_a = K.int_shape(tensor_a)[1]
        length_b = K.int_shape(tensor_b)[1]
        # change the indices that are masked in b to -1, since no indices
        # in the document will ever be -1.
        tensor_b = K.cast(switch(mask_b, tensor_b, -1*K.ones_like(tensor_b)), "int32")

        # reshape tensor_a to shape (batch_size, length_a, length_b)
        tensor_a_tiled = K.repeat_elements(K.expand_dims(tensor_a, 2),
                                           length_b,
                                           axis=2)
        # reshape tensor_b to shape (batch_size, length_a, length_b)
        tensor_b_tiled = K.repeat_elements(K.expand_dims(tensor_b, 1),
                                           length_a,
                                           axis=1)
        overlap_mask = K.cast(K.equal(tensor_a_tiled, tensor_b_tiled), "float32")
        indices_overlap = K.sum(overlap_mask, axis=-1)
        binary_indices_overlap = K.cast(K.not_equal(indices_overlap,
                                                    K.zeros_like(indices_overlap)),
                                        "int32")
        one_hot_overlap = K.cast(K.one_hot(binary_indices_overlap, 2), "float32")
        return one_hot_overlap 

def time_distributed_dense(x, w, b=None, dropout=None,
                           input_dim=None, units=None, timesteps=None):
    """Apply `y . w + b` for every temporal slice y of x.
    # Arguments
        x: input tensor.
        w: weight matrix.
        b: optional bias vector.
        dropout: wether to apply dropout (same dropout mask
            for every temporal slice of the input).
        input_dim: integer; optional dimensionality of the input.
        units: integer; optional dimensionality of the output.
        timesteps: integer; optional number of timesteps.
    # Returns
        Output tensor.
    """
    if not input_dim:
        input_dim = K.shape(x)[2]
    if not timesteps:
        timesteps = K.shape(x)[1]
    if not units:
        units = K.shape(w)[1]

    if dropout is not None and 0. < dropout < 1.:
        # apply the same dropout pattern at every timestep
        ones = K.ones_like(K.reshape(x[:, 0, :], (-1, input_dim)))
        dropout_matrix = K.dropout(ones, dropout)
        expanded_dropout_matrix = K.repeat(dropout_matrix, timesteps)
        x = K.in_train_phase(x * expanded_dropout_matrix, x)

    # collapse time dimension and batch dimension together
    x = K.reshape(x, (-1, input_dim))
    x = K.dot(x, w)
    if b:
        x += b
    # reshape to 3D tensor
    if K.backend() == 'tensorflow':
        x = K.reshape(x, K.stack([-1, timesteps, units]))
        x.set_shape([None, None, units])
    else:
        x = K.reshape(x, (-1, timesteps, units))
    return x 

def call(self, inputs, mask=None):
        if mask is None:
            # It turns out that Keras doesn't like it if you just return inputs, so we need to
            # return a different tensor object.  Just doing a cast apparently doesn't work, either,
            # so we'll add 0.
            return inputs + 0.0
        return switch(mask, inputs, K.ones_like(inputs) * self.replace_with) 

def compute_mask(self, inputs, mask=None):
        # pylint: disable=unused-argument
        tensor_1, tensor_2 = inputs
        tensor_1_mask, tensor_2_mask = mask
        if tensor_1_mask is None:
            tensor_1_mask = K.ones_like(tensor_1)
        if tensor_2_mask is None:
            tensor_2_mask = K.ones_like(tensor_2)
        tensor_1_mask, tensor_2_mask = self.expand_dims_if_necessary(tensor_1_mask, tensor_2_mask)
        return K.cast(tensor_1_mask, 'uint8') * K.cast(tensor_2_mask, 'uint8') 

def weighted_bce_dice_loss(y_true, y_pred):
    y_true = K.cast(y_true, 'float32')
    y_pred = K.cast(y_pred, 'float32')
    # if we want to get same size of output, kernel size must be odd number
    averaged_mask = K.pool2d(
            y_true, pool_size=(11, 11), strides=(1, 1), padding='same', pool_mode='avg')
    border = K.cast(K.greater(averaged_mask, 0.005), 'float32') * K.cast(K.less(averaged_mask, 0.995), 'float32')
    weight = K.ones_like(averaged_mask)
    w0 = K.sum(weight)
    weight += border * 2
    w1 = K.sum(weight)
    weight *= (w0 / w1)
    loss = weighted_bce_loss(y_true, y_pred, weight) + \
    weighted_dice_loss(y_true, y_pred, weight)
    return loss 

def call(self, inputs, **kwargs):
        boxes = inputs[0]
        box_scores = inputs[1]
        box_scores_transpose = tf.transpose(box_scores, perm=[1, 0])
        boxes_number = tf.shape(boxes)[0]
        box_range = tf.range(boxes_number)

        mask = box_scores >= self.score_threshold
        max_boxes_tensor = K.constant(self.max_boxes, dtype='int32')
        classes_ = []
        batch_indexs_ = []
        nms_indexes_ = []
        class_box_range_ = []
        for c in range(self.num_classes):
            class_boxes = tf.boolean_mask(boxes, mask[:, c])
            class_box_scores = tf.boolean_mask(box_scores[:, c], mask[:, c])
            class_box_range = tf.boolean_mask(box_range, mask[:, c])
            nms_index = tf.image.non_max_suppression(
                class_boxes, class_box_scores, max_boxes_tensor, iou_threshold=self.iou_threshold)
            class_box_scores = K.gather(class_box_scores, nms_index)
            class_box_range = K.gather(class_box_range, nms_index)
            classes = K.ones_like(class_box_scores, 'int32') * c
            batch_index = K.zeros_like(class_box_scores, 'int32')
            batch_indexs_.append(batch_index)
            classes_.append(classes)
            nms_indexes_.append(nms_index)
            class_box_range_.append(class_box_range)

        classes_ = K.concatenate(classes_, axis=0)
        batch_indexs_ = K.concatenate(batch_indexs_, axis=0)
        class_box_range_ = K.concatenate(class_box_range_, axis=0)

        boxes_1 = tf.expand_dims(boxes, 0)
        classes_1 = tf.expand_dims(classes_, 1)
        batch_indexs_ = tf.expand_dims(batch_indexs_, 1)
        class_box_range_ = tf.expand_dims(class_box_range_, 1)
        box_scores_transpose_1 = tf.expand_dims(box_scores_transpose, 0)
        nms_final_ = K.concatenate([batch_indexs_, classes_1, class_box_range_], axis=1)
        nms_final_1 = tf.expand_dims(nms_final_, 0)
        return [boxes_1, box_scores_transpose_1, nms_final_1] 

def call(self, inputs, output_shape=None):
        """
        Seen on https://github.com/tensorflow/tensorflow/issues/2169
        Replace with unpool op when/if issue merged
        Add theano backend
        """
        updates, mask = inputs[0], inputs[1]
        with K.tf.variable_scope(self.name):
            mask = K.cast(mask, 'int32')
            input_shape = K.tf.shape(updates, out_type='int32')
            #  calculation new shape
            if output_shape is None:
                output_shape = (input_shape[0], input_shape[1] * self.size[0], input_shape[2] * self.size[1], input_shape[3])
            self.output_shape1 = output_shape

            # calculation indices for batch, height, width and feature maps
            one_like_mask = K.ones_like(mask, dtype='int32')
            batch_shape = K.concatenate([[input_shape[0]], [1], [1], [1]], axis=0)
            batch_range = K.reshape(K.tf.range(output_shape[0], dtype='int32'), shape=batch_shape)
            b = one_like_mask * batch_range
            y = mask // (output_shape[2] * output_shape[3])
            x = (mask // output_shape[3]) % output_shape[2]
            feature_range = K.tf.range(output_shape[3], dtype='int32')
            f = one_like_mask * feature_range

            # transpose indices & reshape update values to one dimension
            updates_size = K.tf.size(updates)
            indices = K.transpose(K.reshape(K.stack([b, y, x, f]), [4, updates_size]))
            values = K.reshape(updates, [updates_size])
            ret = K.tf.scatter_nd(indices, values, output_shape)
            return ret 

def tile_scalar(scalar, vector):
    """
    NOTE: If your vector has known shape (i.e., the relevant dimension from `K.int_shape(vector) is
    not None`), you should just use `K.repeat_elements(scalar)` instead of this.  This method
    works, however, when the number of entries in your vector is unknown at graph compilation time.

    This method takes a (collection of) scalar(s) (shape: (batch_size, 1)), and tiles that
    scala a number of times, giving a vector of shape (batch_size, tile_length).  (I say "scalar"
    and "vector" here because I'm ignoring the batch_size).  We need the vector as input so we know
    what the tile_length is - the vector is otherwise ignored.

    This is not done as a Keras Layer, however; if you want to use this function, you'll need to do
    it _inside_ of a Layer somehow, either in a Lambda or in the call() method of a Layer you're
    writing.

    TODO(matt): we could probably make a more general `tile_tensor` method, which can do this for
    any dimenionsality.  There is another place in the code where we do this with a matrix and a
    tensor; all three of these can probably be one function.
    """
    # Tensorflow can't use unknown sizes at runtime, so we have to make use of the broadcasting
    # ability of TF and Theano instead to create the tiled sentence encoding.

    # Shape: (tile_length, batch_size)
    k_ones = K.permute_dimensions(K.ones_like(vector), [1, 0])

    # Now we have a (tile_length, batch_size) * (batch_size, 1) elementwise multiplication which is
    # broadcast. We then reshape back.
    tiled_scalar = K.permute_dimensions(k_ones * K.squeeze(scalar, axis=1), [1, 0])
    return tiled_scalar