Python tensorflow.sub() Examples

def __init__(self, n_input, n_hidden, transfer_function = tf.nn.softplus, optimizer = tf.train.AdamOptimizer(),
                 dropout_probability = 0.95):
        self.n_input = n_input
        self.n_hidden = n_hidden
        self.transfer = transfer_function
        self.dropout_probability = dropout_probability
        self.keep_prob = tf.placeholder(tf.float32)

        network_weights = self._initialize_weights()
        self.weights = network_weights

        # model
        self.x = tf.placeholder(tf.float32, [None, self.n_input])
        self.hidden = self.transfer(tf.add(tf.matmul(tf.nn.dropout(self.x, self.keep_prob), self.weights['w1']),
                                           self.weights['b1']))
        self.reconstruction = tf.add(tf.matmul(self.hidden, self.weights['w2']), self.weights['b2'])

        # cost
        self.cost = 0.5 * tf.reduce_sum(tf.pow(tf.sub(self.reconstruction, self.x), 2.0))
        self.optimizer = optimizer.minimize(self.cost)

        init = tf.initialize_all_variables()
        self.sess = tf.Session()
        self.sess.run(init) 

def __init__(self, n_input, n_hidden, transfer_function = tf.nn.softplus, optimizer = tf.train.AdamOptimizer(),
                 dropout_probability = 0.95):
        self.n_input = n_input
        self.n_hidden = n_hidden
        self.transfer = transfer_function
        self.dropout_probability = dropout_probability
        self.keep_prob = tf.placeholder(tf.float32)

        network_weights = self._initialize_weights()
        self.weights = network_weights

        # model
        self.x = tf.placeholder(tf.float32, [None, self.n_input])
        self.hidden = self.transfer(tf.add(tf.matmul(tf.nn.dropout(self.x, self.keep_prob), self.weights['w1']),
                                           self.weights['b1']))
        self.reconstruction = tf.add(tf.matmul(self.hidden, self.weights['w2']), self.weights['b2'])

        # cost
        self.cost = 0.5 * tf.reduce_sum(tf.pow(tf.sub(self.reconstruction, self.x), 2.0))
        self.optimizer = optimizer.minimize(self.cost)

        init = tf.initialize_all_variables()
        self.sess = tf.Session()
        self.sess.run(init) 

def testFloatBasic(self):
    x = np.linspace(-5, 20, 15).reshape(1, 3, 5).astype(np.float32)
    y = np.linspace(20, -5, 15).reshape(1, 3, 5).astype(np.float32)
    self._compareBoth(x, y, np.add, tf.add, also_compare_variables=True)
    self._compareBoth(x, y, np.subtract, tf.sub)
    self._compareBoth(x, y, np.multiply, tf.mul)
    self._compareBoth(x, y + 0.1, np.true_divide, tf.truediv)
    self._compareBoth(x, y + 0.1, np.floor_divide, tf.floordiv)
    self._compareBoth(x, y, np.add, _ADD)
    self._compareBoth(x, y, np.subtract, _SUB)
    self._compareBoth(x, y, np.multiply, _MUL)
    self._compareBoth(x, y + 0.1, np.true_divide, _TRUEDIV)
    self._compareBoth(x, y + 0.1, np.floor_divide, _FLOORDIV)
    try:
      from scipy import special  # pylint: disable=g-import-not-at-top
      a_pos_small = np.linspace(0.1, 2, 15).reshape(1, 3, 5).astype(np.float32)
      x_pos_small = np.linspace(0.1, 10, 15).reshape(1, 3, 5).astype(np.float32)
      self._compareBoth(a_pos_small, x_pos_small, special.gammainc, tf.igamma)
      self._compareBoth(a_pos_small, x_pos_small, special.gammaincc, tf.igammac)
      # Need x > 1
      self._compareBoth(x_pos_small + 1, a_pos_small, special.zeta, tf.zeta)
      n_small = np.arange(0, 15).reshape(1, 3, 5).astype(np.float32)
      self._compareBoth(n_small, x_pos_small, special.polygamma, tf.polygamma)
    except ImportError as e:
      tf.logging.warn("Cannot test special functions: %s" % str(e)) 

def testDoubleBasic(self):
    x = np.linspace(-5, 20, 15).reshape(1, 3, 5).astype(np.float64)
    y = np.linspace(20, -5, 15).reshape(1, 3, 5).astype(np.float64)
    self._compareBoth(x, y, np.add, tf.add)
    self._compareBoth(x, y, np.subtract, tf.sub)
    self._compareBoth(x, y, np.multiply, tf.mul)
    self._compareBoth(x, y + 0.1, np.true_divide, tf.truediv)
    self._compareBoth(x, y + 0.1, np.floor_divide, tf.floordiv)
    self._compareBoth(x, y, np.add, _ADD)
    self._compareBoth(x, y, np.subtract, _SUB)
    self._compareBoth(x, y, np.multiply, _MUL)
    self._compareBoth(x, y + 0.1, np.true_divide, _TRUEDIV)
    self._compareBoth(x, y + 0.1, np.floor_divide, _FLOORDIV)
    try:
      from scipy import special  # pylint: disable=g-import-not-at-top
      a_pos_small = np.linspace(0.1, 2, 15).reshape(1, 3, 5).astype(np.float32)
      x_pos_small = np.linspace(0.1, 10, 15).reshape(1, 3, 5).astype(np.float32)
      self._compareBoth(a_pos_small, x_pos_small, special.gammainc, tf.igamma)
      self._compareBoth(a_pos_small, x_pos_small, special.gammaincc, tf.igammac)
    except ImportError as e:
      tf.logging.warn("Cannot test special functions: %s" % str(e)) 

def testInt32Basic(self):
    x = np.arange(1, 13, 2).reshape(1, 3, 2).astype(np.int32)
    y = np.arange(1, 7, 1).reshape(1, 3, 2).astype(np.int32)
    self._compareBoth(x, y, np.add, tf.add)
    self._compareBoth(x, y, np.subtract, tf.sub)
    self._compareBoth(x, y, np.multiply, tf.mul)
    self._compareBoth(x, y, np.true_divide, tf.truediv)
    self._compareBoth(x, y, np.floor_divide, tf.floordiv)
    self._compareBoth(x, y, np.mod, tf.mod)
    self._compareBoth(x, y, np.add, _ADD)
    self._compareBoth(x, y, np.subtract, _SUB)
    self._compareBoth(x, y, np.multiply, _MUL)
    self._compareBoth(x, y, np.true_divide, _TRUEDIV)
    self._compareBoth(x, y, np.floor_divide, _FLOORDIV)
    self._compareBoth(x, y, np.mod, _MOD)
    # _compareBoth tests on GPU only for floating point types, so test
    # _MOD for int32 on GPU by calling _compareGpu
    self._compareGpu(x, y, np.mod, _MOD) 

def tf_mse(a, b, reduction_indices=None, name='mse'):
    """
    Mean squared error for TensorFlow.

    :param a: First input tensor
    :type b: tf.Tensor
    :param a: Second input tensor
    :type b: tf.Tensor
    :param reduction_indices: Dimensions to reduce. If None all dimensions are reduced.
    :type reduction_indices: List or None
    :param name: Variable scope name
    :type reduction_indices: String

    :returns: MSE between a and b
    :rtype: tf.Tensor
    """
    with tf.variable_scope(name):
        return tf.reduce_mean(tf.pow(tf.sub(a, b), 2),
                              reduction_indices=reduction_indices) 

def _ImageProcessing(image_buffer, shape):
  """Convert a PNG string into an input tensor.

  We allow for fixed and variable sizes.
  Does fixed conversion to floats in the range [-1.28, 1.27].
  Args:
    image_buffer: Tensor containing a PNG encoded image.
    shape:          ImageShape with the desired shape of the input.
  Returns:
    image:        Decoded, normalized image in the range [-1.28, 1.27].
  """
  image = tf.image.decode_png(image_buffer, channels=shape.depth)
  image.set_shape([shape.height, shape.width, shape.depth])
  image = tf.cast(image, tf.float32)
  image = tf.sub(image, 128.0)
  image = tf.mul(image, 1 / 100.0)
  return image 

def __init__(self, n_input, n_hidden, transfer_function = tf.nn.softplus, optimizer = tf.train.AdamOptimizer(),
                 scale = 0.1):
        self.n_input = n_input
        self.n_hidden = n_hidden
        self.transfer = transfer_function
        self.scale = tf.placeholder(tf.float32)
        self.training_scale = scale
        network_weights = self._initialize_weights()
        self.weights = network_weights

        # model
        self.x = tf.placeholder(tf.float32, [None, self.n_input])
        self.hidden = self.transfer(tf.add(tf.matmul(self.x + scale * tf.random_normal((n_input,)),
                self.weights['w1']),
                self.weights['b1']))
        self.reconstruction = tf.add(tf.matmul(self.hidden, self.weights['w2']), self.weights['b2'])

        # cost
        self.cost = 0.5 * tf.reduce_sum(tf.pow(tf.sub(self.reconstruction, self.x), 2.0))
        self.optimizer = optimizer.minimize(self.cost)

        init = tf.initialize_all_variables()
        self.sess = tf.Session()
        self.sess.run(init) 

def class_balanced_binary_class_cross_entropy(pred, label, name='cross_entropy_loss'):
    """
    The class-balanced cross entropy loss for binary classification,
    as in `Holistically-Nested Edge Detection
    <http://arxiv.org/abs/1504.06375>`_.

    :param pred: size: b x ANYTHING. the predictions in [0,1].
    :param label: size: b x ANYTHING. the ground truth in {0,1}.
    :returns: class-balanced binary classification cross entropy loss
    """
    z = batch_flatten(pred)
    y = tf.cast(batch_flatten(label), tf.float32)

    count_neg = tf.reduce_sum(1. - y)
    count_pos = tf.reduce_sum(y)
    beta = count_neg / (count_neg + count_pos)

    eps = 1e-8
    loss_pos = -beta * tf.reduce_mean(y * tf.log(tf.abs(z) + eps), 1)
    loss_neg = (1. - beta) * tf.reduce_mean((1. - y) * tf.log(tf.abs(1. - z) + eps), 1)
    cost = tf.sub(loss_pos, loss_neg)
    cost = tf.reduce_mean(cost, name=name)
    return cost 

def _activation_summary(x):
    """Helper to create summaries for activations.
    
    Creates a summary that provides a histogram of activations.
    Creates a summary that measure the sparsity of activations.
    
    Args:
      x: Tensor
    Returns:
      nothing
    """
    # Remove 'tower_[0-9]/' from the name in case this is a multi-GPU training
    # session. This helps the clarity of presentation on tensorboard.
    tensor_name = re.sub('%s_[0-9]*/' % LSPGlobals.TOWER_NAME, '', x.op.name)
    tf.histogram_summary(tensor_name + '/activations', x)
    tf.scalar_summary(tensor_name + '/sparsity', tf.nn.zero_fraction(x)) 

def __init__(self):
        self.x = tf.placeholder(tf.float32, [None, 115, 200, 3])
        self.y_ = tf.placeholder(tf.float32, [None, 1])
        (self.h_conv1, _) = conv_layer(self.x, conv=(5, 5), stride=2, n_filters=24, use_bias=True)
        (self.h_conv2, _) = conv_layer(self.h_conv1, conv=(5, 5), stride=2, n_filters=36, use_bias=True)
        (self.h_conv3, _) = conv_layer(self.h_conv2, conv=(5, 5), stride=2, n_filters=48, use_bias=True)
        (self.h_conv4, _) = conv_layer(self.h_conv3, conv=(3, 3), stride=1, n_filters=64, use_bias=True)
        (self.h_conv5, _) = conv_layer(self.h_conv4, conv=(3, 3), stride=1, n_filters=64, use_bias=True)
        self.h_conv5_flat = flattened(self.h_conv5)
        (self.h_fc1_drop, _, _, self.keep_prob_fc1) = fc_layer(x=self.h_conv5_flat, n_neurons=512, activation=tf.nn.relu, use_bias=True, dropout=True)
        (self.h_fc2_drop, _, _, self.keep_prob_fc2) = fc_layer(self.h_fc1_drop, 100, tf.nn.relu, True, True)
        (self.h_fc3_drop, _, _, self.keep_prob_fc3) = fc_layer(self.h_fc2_drop, 50, tf.nn.relu, True, True)
        (self.h_fc4_drop, _, _, self.keep_prob_fc4) = fc_layer(self.h_fc3_drop, 10, tf.nn.relu, True, True)
        W_fc5 = weight_variable([10, 1])
        b_fc5 = bias_variable([1])
        self.y_out = tf.matmul(self.h_fc4_drop, W_fc5) + b_fc5
        self.loss = tf.reduce_mean(tf.abs(tf.sub(self.y_, self.y_out))) 

def __init__(self):
        self.x = tf.placeholder(tf.float32, [None, 115, 200, 3])
        self.y_ = tf.placeholder(tf.float32, [None, 1])
        (self.h_conv1, _) = conv_layer(self.x, conv=(5, 5), stride=2, n_filters=24, use_bias=True)
        (self.h_conv2, _) = conv_layer(self.h_conv1, conv=(5, 5), stride=2, n_filters=36, use_bias=True)
        (self.h_conv3, _) = conv_layer(self.h_conv2, conv=(5, 5), stride=2, n_filters=48, use_bias=True)
        (self.h_conv4, _) = conv_layer(self.h_conv3, conv=(3, 3), stride=1, n_filters=64, use_bias=True)
        (self.h_conv5, _) = conv_layer(self.h_conv4, conv=(3, 3), stride=1, n_filters=64, use_bias=True)
        self.h_conv5_flat = flattened(self.h_conv5)
        (self.h_fc1_drop, _, _, self.keep_prob_fc1) = fc_layer(x=self.h_conv5_flat, n_neurons=512, activation=tf.nn.relu, use_bias=True, dropout=True)
        (self.h_fc2_drop, _, _, self.keep_prob_fc2) = fc_layer(self.h_fc1_drop, 100, tf.nn.relu, True, True)
        (self.h_fc3_drop, _, _, self.keep_prob_fc3) = fc_layer(self.h_fc2_drop, 50, tf.nn.relu, True, True)
        (self.h_fc4_drop, _, _, self.keep_prob_fc4) = fc_layer(self.h_fc3_drop, 10, tf.nn.relu, True, True)
        W_fc5 = weight_variable([10, 1])
        b_fc5 = bias_variable([1])
        self.y_out = tf.matmul(self.h_fc4_drop, W_fc5) + b_fc5
        self.loss = tf.reduce_mean(tf.abs(tf.sub(self.y_, self.y_out))) 

def loss(logits, labels):
    """Calculates Mean Pixel Error.
    
    Args:
      logits: Logits from inference().
      labels: Labels from distorted_inputs or inputs(). 1-D tensor
              of shape [batch_size]
    
    Returns:
      Loss tensor of type float.
    """
    
    labelValidity = tf.sign(labels, name='label_validity')
    
    minop = tf.sub(logits, labels, name='Diff_Op')
    
    absop = tf.abs(minop, name='Abs_Op')
    
    lossValues = tf.mul(labelValidity, absop, name='lossValues')
    
    loss_mean = tf.reduce_mean(lossValues, name='MeanPixelError')
    
    tf.add_to_collection('losses', loss_mean)
    
    return tf.add_n(tf.get_collection('losses'), name='total_loss'), loss_mean 

def test_binary_ops_combined(self):
        # computation
        a = tf.placeholder(tf.float32, shape=(2, 3))
        b = tf.placeholder(tf.float32, shape=(2, 3))
        c = tf.add(a, b)
        d = tf.mul(c, a)
        e = tf.div(d, b)
        f = tf.sub(a, e)
        g = tf.maximum(a, f)

        # value
        a_val = np.random.rand(*tf_obj_shape(a))
        b_val = np.random.rand(*tf_obj_shape(b))

        # test
        self.run(g, tf_feed_dict={a: a_val, b: b_val}) 

def preprocess_image(image, output_height, output_width, is_training):
  """Preprocesses the given image.

  Args:
    image: A `Tensor` representing an image of arbitrary size.
    output_height: The height of the image after preprocessing.
    output_width: The width of the image after preprocessing.
    is_training: `True` if we're preprocessing the image for training and
      `False` otherwise.

  Returns:
    A preprocessed image.
  """
  image = tf.to_float(image)
  image = tf.image.resize_image_with_crop_or_pad(
      image, output_width, output_height)
  image = tf.sub(image, 128.0)
  image = tf.div(image, 128.0)
  return image 

def testCondIndexedSlicesDifferentTypes(self):
    with self.test_session():
      values = tf.constant(10)
      i_32 = tf.convert_to_tensor(0, name="one", dtype=tf.int32)
      i_64 = tf.convert_to_tensor(0, name="one", dtype=tf.int64)
      x = tf.IndexedSlices(values, i_32)
      pred = tf.less(1, 2)
      fn1 = lambda: tf.IndexedSlices(tf.add(x.values, 1), i_32)
      fn2 = lambda: tf.IndexedSlices(tf.sub(x.values, 1), i_64)
      r = tf.cond(pred, fn1, fn2)

      val = r.values.eval()
      ind = r.indices.eval()
    self.assertTrue(check_op_order(x.values.graph))
    self.assertAllEqual(11, val)
    self.assertAllEqual(0, ind)
    self.assertTrue(ind.dtype == np.int64) 

def __init__(self, n_input, n_hidden, transfer_function = tf.nn.softplus, optimizer = tf.train.AdamOptimizer(),
                 scale = 0.1):
        self.n_input = n_input
        self.n_hidden = n_hidden
        self.transfer = transfer_function
        self.scale = tf.placeholder(tf.float32)
        self.training_scale = scale
        network_weights = self._initialize_weights()
        self.weights = network_weights

        # model
        self.x = tf.placeholder(tf.float32, [None, self.n_input])
        self.hidden = self.transfer(tf.add(tf.matmul(self.x + scale * tf.random_normal((n_input,)),
                self.weights['w1']),
                self.weights['b1']))
        self.reconstruction = tf.add(tf.matmul(self.hidden, self.weights['w2']), self.weights['b2'])

        # cost
        self.cost = 0.5 * tf.reduce_sum(tf.pow(tf.sub(self.reconstruction, self.x), 2.0))
        self.optimizer = optimizer.minimize(self.cost)

        init = tf.initialize_all_variables()
        self.sess = tf.Session()
        self.sess.run(init) 

def _ImageProcessing(image_buffer, shape):
  """Convert a PNG string into an input tensor.

  We allow for fixed and variable sizes.
  Does fixed conversion to floats in the range [-1.28, 1.27].
  Args:
    image_buffer: Tensor containing a PNG encoded image.
    shape:          ImageShape with the desired shape of the input.
  Returns:
    image:        Decoded, normalized image in the range [-1.28, 1.27].
  """
  image = tf.image.decode_png(image_buffer, channels=shape.depth)
  image.set_shape([shape.height, shape.width, shape.depth])
  image = tf.cast(image, tf.float32)
  image = tf.sub(image, 128.0)
  image = tf.mul(image, 1 / 100.0)
  return image 

def preprocess_image(image, output_height, output_width, is_training):
  """Preprocesses the given image.

  Args:
    image: A `Tensor` representing an image of arbitrary size.
    output_height: The height of the image after preprocessing.
    output_width: The width of the image after preprocessing.
    is_training: `True` if we're preprocessing the image for training and
      `False` otherwise.

  Returns:
    A preprocessed image.
  """
  image = tf.to_float(image)
  image = tf.image.resize_image_with_crop_or_pad(
      image, output_width, output_height)
  image = tf.sub(image, 128.0)
  image = tf.div(image, 128.0)
  return image 

def rescale_images_tf(input_imgs, dtype, scope=None):
    '''Convert input from [0, 1] -> [-1.0, 1.0] floats.
    Args:
        input_imgs: List of input images (scaled between 0 and 1) with the
                    dimensions specified in the cfg
    Return:
        scaled_input_imgs: List of input images after rescaling to [-1, 1]
    '''
    if scope is None:
        cur_scope = 'rescaled'
    else:
        cur_scope = scope
    with tf.variable_scope(cur_scope):
        input_img = tf.cast(input_img, dtype,
                            name='cast_input')
        input_img = tf.mul(input_img, 2., name='rescale_input')
        scaled_input_imgs = tf.sub(input_img, 1., name='normalize_input')
    return scaled_input_imgs 

def testWhileCondGrad_UnknownShape(self):
    with self.test_session() as sess:
      v = tf.placeholder(tf.float32)
      n = tf.convert_to_tensor(100.0, name="n")
      one = tf.convert_to_tensor(1.0, name="one")
      c = lambda x: tf.less(x, n)
      # pylint: disable=undefined-variable
      # for OSS build
      b = lambda x: tf.cond(tf.constant(True),
                            lambda: tf.square(x),
                            lambda: tf.sub(x, one))
      # pylint: enable=undefined-variable
      r = tf.while_loop(c, b, [v])
      r = tf.gradients(r, v)[0]
      r = sess.run(r, feed_dict={v: 2.0})
      self.assertAllClose(1024.0, r) 

def _testStackWhileSwap(self, use_gpu):
    with self.test_session(use_gpu=use_gpu):
      n = tf.constant(0)
      h = gen_data_flow_ops._stack(tf.float32, stack_name="foo")

      def c(x):
        return tf.less(x, 10)
      def b(x):
        with tf.control_dependencies([x]):
          a = tf.constant(np.ones(2000), dtype=tf.float32)
          v = gen_data_flow_ops._stack_push(h, a, swap_memory=True)
        with tf.control_dependencies([v]):
          return tf.add(x, 1)
      r = tf.while_loop(c, b, [n])

      v = tf.constant(np.zeros(2000), dtype=tf.float32)
      def c1(x, y):
        return tf.greater(x, 0)
      def b1(x, y):
        nx = tf.sub(x, 1)
        ny = y + gen_data_flow_ops._stack_pop(h, tf.float32)
        return [nx, ny]
      rx, ry = tf.while_loop(c1, b1, [r, v],
                             [r.get_shape(), tensor_shape.unknown_shape()])
      self.assertAllClose(np.ones(2000) * 10.0, ry.eval()) 

def softmax_with_base(shape, base_untiled, x, mask=None, name='sig'):
    if mask is not None:
        x += VERY_SMALL_NUMBER * (1.0 - mask)
    base_shape = shape[:-1] + [1]
    for _ in shape:
        base_untiled = tf.expand_dims(base_untiled, -1)
    base = tf.tile(base_untiled, base_shape)

    c_shape = shape[:-1] + [shape[-1] + 1]
    c = tf.concat(len(shape)-1, [base, x])
    c_flat = tf.reshape(c, [reduce(mul, shape[:-1], 1), c_shape[-1]])
    p_flat = tf.nn.softmax(c_flat)
    p_cat = tf.reshape(p_flat, c_shape)
    s_aug = tf.slice(p_cat, [0 for _ in shape], [i for i in shape[:-1]] + [1])
    s = tf.squeeze(s_aug, [len(shape)-1])
    sig = tf.sub(1.0, s, name="sig")
    p = tf.slice(p_cat, [0 for _ in shape[:-1]] + [1], shape)
    return sig, p 

def cost(training, classes, inputs, kernel_type="gaussian", C=1, gamma=1):
    """Returns the kernelised cost to be minimised."""
    beta = tf.Variable(tf.zeros([inputs, 1]))
    offset = tf.Variable(tf.zeros([1]))

    if kernel_type == "linear":
        kernel = linear_kernel(training, inputs, training, inputs)
    elif kernel_type == "gaussian":
        kernel = gaussian_kernel(training, inputs, training, inputs, gamma)

    x = tf.reshape(tf.div(tf.matmul(tf.matmul(
        beta, kernel, transpose_a=True), beta), tf.constant([2.0])), [1])
    y = tf.sub(tf.ones([1]), tf.mul(classes, tf.add(
        tf.matmul(kernel, beta, transpose_a=True), offset)))
    z = tf.mul(tf.reduce_sum(tf.reduce_max(
        tf.concat(1, [y, tf.zeros_like(y)]), reduction_indices=1)),
        tf.constant([C], dtype=tf.float32))
    cost = tf.add(x, z)

    return beta, offset, cost 

def _activation_summary(x):
    """Helper to create summaries for activations.

    Creates a summary that provides a histogram of activations.
    Creates a summary that measure the sparsity of activations.

    Args:
      x: Tensor
    Returns:
      nothing
    """
    # Remove 'tower_[0-9]/' from the name in case this is a multi-GPU training
    # session. This helps the clarity of presentation on tensorboard.
    tensor_name = re.sub('%s_[0-9]*/' % TOWER_NAME, '', x.op.name)
    tf.histogram_summary(tensor_name + '/activations', x)
    tf.scalar_summary(tensor_name + '/sparsity', tf.nn.zero_fraction(x)) 

def class_balanced_binary_class_cross_entropy(pred, label, name='cross_entropy_loss'):
    """
    The class-balanced cross entropy loss for binary classification,
    as in `Holistically-Nested Edge Detection
    <http://arxiv.org/abs/1504.06375>`_.

    :param pred: size: b x ANYTHING. the predictions in [0,1].
    :param label: size: b x ANYTHING. the ground truth in {0,1}.
    :returns: class-balanced binary classification cross entropy loss
    """
    z = batch_flatten(pred)
    y = tf.cast(batch_flatten(label), tf.float32)

    count_neg = tf.reduce_sum(1. - y)
    count_pos = tf.reduce_sum(y)
    beta = count_neg / (count_neg + count_pos)

    eps = 1e-8
    loss_pos = -beta * tf.reduce_mean(y * tf.log(tf.abs(z) + eps), 1)
    loss_neg = (1. - beta) * tf.reduce_mean((1. - y) * tf.log(tf.abs(1. - z) + eps), 1)
    cost = tf.sub(loss_pos, loss_neg)
    cost = tf.reduce_mean(cost, name=name)
    return cost 

def __init__(self, x_size, y_size, w_stddev, **kwargs):
        self.x_size = x_size
        self.y_size = y_size
        self.w_stddev = w_stddev

        self.X = tf.placeholder(tf.float32, shape=[None, self.x_size], name='X')
        self.Y = tf.placeholder(tf.float32, shape=[None, self.y_size], name='Y')
        self.Z = tf.placeholder(tf.float32, shape=[None, self.x_size], name='Z')
        self.W = tf.Variable(tf.random_normal((self.x_size, self.y_size), stddev=self.w_stddev), name='W')

        self.Y_hat = tf.matmul(self.X, self.W)
        self.Y_error = tf.sub(self.Y_hat, self.Y)
        self.Y_norm = self.l2_norm(self.Y_error)

        self.Y_loss = tf.nn.l2_loss(self.Y_norm)

        self.loss = self.Y_loss 

def calculatCA(_tp1, _tp2, size, _b_size):
        first = True
        tp1 = tf.split(0, _b_size, _tp1)
        tp2 = tf.split(0, _b_size, _tp2)
        for i in range(_b_size):
            input1 = tf.reshape(tp1[i], shape=[size, 1])
            input2 = tf.reshape(tp2[i], shape=[size, 1])

            upper = tf.matmul(tf.transpose(tf.sub(input1, tf.reduce_mean(input1))), tf.sub(input2, tf.reduce_mean(input2)))        
            _tp1 = tf.reduce_sum(tf.mul(tf.sub(input1, tf.reduce_mean(input1)), tf.sub(input1, tf.reduce_mean(input1))))
            _tp2 = tf.reduce_sum(tf.mul(tf.sub(input2, tf.reduce_mean(input2)), tf.sub(input2, tf.reduce_mean(input2))))
            down = tf.sqrt(tf.mul(_tp1, _tp2))
            factor = tf.abs(tf.div(upper, down))
            
            if first:
                output = factor
                first = False
            else:
                output = tf.concat(1, [output, factor])

        return tf.transpose(output)
    
    # Create model 

def calculatCA(_tp1, _tp2, size, _b_size):
        first = True
        tp1 = tf.split(0, _b_size, _tp1)
        tp2 = tf.split(0, _b_size, _tp2)
        for i in range(_b_size):
            input1 = tf.reshape(tp1[i], shape=[size, 1])
            input2 = tf.reshape(tp2[i], shape=[size, 1])

            upper = tf.matmul(tf.transpose(tf.sub(input1, tf.reduce_mean(input1))), tf.sub(input2, tf.reduce_mean(input2)))        
            _tp1 = tf.reduce_sum(tf.mul(tf.sub(input1, tf.reduce_mean(input1)), tf.sub(input1, tf.reduce_mean(input1))))
            _tp2 = tf.reduce_sum(tf.mul(tf.sub(input2, tf.reduce_mean(input2)), tf.sub(input2, tf.reduce_mean(input2))))
            down = tf.sqrt(tf.mul(_tp1, _tp2))
            factor = tf.abs(tf.div(upper, down))
            
            if first:
                output = factor
                first = False
            else:
                output = tf.concat(1, [output, factor])

        return tf.transpose(output)
    
    # Create model 

def calculatCA(_tp1, _tp2, size, _b_size):
        first = True
        tp1 = tf.split(0, _b_size, _tp1)
        tp2 = tf.split(0, _b_size, _tp2)
        for i in range(_b_size):
            input1 = tf.reshape(tp1[i], shape=[size, 1])
            input2 = tf.reshape(tp2[i], shape=[size, 1])

            upper = tf.matmul(tf.transpose(tf.sub(input1, tf.reduce_mean(input1))), tf.sub(input2, tf.reduce_mean(input2)))        
            _tp1 = tf.reduce_sum(tf.mul(tf.sub(input1, tf.reduce_mean(input1)), tf.sub(input1, tf.reduce_mean(input1))))
            _tp2 = tf.reduce_sum(tf.mul(tf.sub(input2, tf.reduce_mean(input2)), tf.sub(input2, tf.reduce_mean(input2))))
            down = tf.sqrt(tf.mul(_tp1, _tp2))
            factor = tf.abs(tf.div(upper, down))
            
            if first:
                output = factor
                first = False
            else:
                output = tf.concat(1, [output, factor])

        return tf.transpose(output)

    # Create model