Python v1.multiply方法代码示例

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import multiply [as 别名]
def kl_divergence(mu, log_var, mu_p=0.0, log_var_p=0.0):
  """KL divergence of diagonal gaussian N(mu,exp(log_var)) and N(0,1).

  Args:
    mu: mu parameter of the distribution.
    log_var: log(var) parameter of the distribution.
    mu_p: optional mu from a learned prior distribution
    log_var_p: optional log(var) from a learned prior distribution
  Returns:
    the KL loss.
  """

  batch_size = shape_list(mu)[0]
  prior_distribution = tfp.distributions.Normal(
      mu_p, tf.exp(tf.multiply(0.5, log_var_p)))
  posterior_distribution = tfp.distributions.Normal(
      mu, tf.exp(tf.multiply(0.5, log_var)))
  kld = tfp.distributions.kl_divergence(posterior_distribution,
                                        prior_distribution)
  return tf.reduce_sum(kld) / to_float(batch_size) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import multiply [as 别名]
def testSpectralNorm(self):
    # Test that after 20 calls to apply_spectral_norm, the spectral
    # norm of the normalized matrix is close to 1.0
    with tf.Graph().as_default():
      weights = tf.get_variable("w", dtype=tf.float32, shape=[2, 3, 50, 100])
      weights = tf.multiply(weights, 10.0)
      normed_weight, assign_op = common_layers.apply_spectral_norm(weights)

      with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())

        for _ in range(20):
          sess.run(assign_op)
          normed_weight, assign_op = common_layers.apply_spectral_norm(
              weights)
        normed_weight = sess.run(normed_weight).reshape(-1, 100)
        _, s, _ = np.linalg.svd(normed_weight)
        self.assertTrue(np.allclose(s[0], 1.0, rtol=0.1)) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import multiply [as 别名]
def read(self, x):
    """Read from the memory.

    An external component can use the results via a simple MLP,
    e.g., fn(x W_x + retrieved_mem W_m).

    Args:
      x: a tensor in the shape of [batch_size, length, depth].
    Returns:
      access_logits: the logits for accessing the memory in shape of
          [batch_size, length, memory_size].
      retrieved_mem: the retrieved results in the shape of
          [batch_size, length, val_depth].
    """
    access_logits = self._address_content(x)
    weights = tf.nn.softmax(access_logits)
    retrieved_mem = tf.reduce_sum(
        tf.multiply(tf.expand_dims(weights, 3),
                    tf.expand_dims(self.mem_vals, axis=1)), axis=2)
    return access_logits, retrieved_mem 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import multiply [as 别名]
def apply_batch_norm(self, wrapper, mean, variance, scale, bias, epsilon):
    # Element-wise multiplier.
    multiplier = tf.rsqrt(variance + epsilon)
    if scale is not None:
      multiplier *= scale
    w = multiplier
    # Element-wise bias.
    b = -multiplier * mean
    if bias is not None:
      b += bias
    b = tf.squeeze(b, axis=0)
    # Because the scale might be negative, we need to apply a strategy similar
    # to linear.
    c = (self.lower + self.upper) / 2.
    r = (self.upper - self.lower) / 2.
    c = tf.multiply(c, w) + b
    r = tf.multiply(r, tf.abs(w))
    return IntervalBounds(c - r, c + r) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import multiply [as 别名]
def add_heatmap_summary(feature_query, feature_map, name):
  """Plots dot produce of feature_query on feature_map.

  Args:
    feature_query: Batch x embedding size tensor of goal embeddings
    feature_map: Batch x h x w x embedding size of pregrasp scene embeddings
    name: string to name tensorflow summaries
  Returns:
     Batch x h x w x 1 heatmap
  """
  batch, dim = feature_query.shape
  reshaped_query = tf.reshape(feature_query, (int(batch), 1, 1, int(dim)))
  heatmaps = tf.reduce_sum(
      tf.multiply(feature_map, reshaped_query), axis=3, keep_dims=True)
  tf.summary.image(name, heatmaps)
  shape = tf.shape(heatmaps)
  softmaxheatmaps = tf.nn.softmax(tf.reshape(heatmaps, (int(batch), -1)))
  tf.summary.image(
      six.ensure_str(name) + 'softmax', tf.reshape(softmaxheatmaps, shape))
  return heatmaps 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import multiply [as 别名]
def _variable_with_weight_decay(name, shape, stddev, wd):
  """Helper to create an initialized Variable with weight decay.

  Note that the Variable is initialized with a truncated normal distribution.
  A weight decay is added only if one is specified.

  Args:
    name: name of the variable
    shape: list of ints
    stddev: standard deviation of a truncated Gaussian
    wd: add L2Loss weight decay multiplied by this float. If None, weight
        decay is not added for this Variable.

  Returns:
    Variable Tensor
  """
  var = _variable_on_cpu(name, shape,
                         tf.truncated_normal_initializer(stddev=stddev))
  if wd is not None:
    weight_decay = tf.multiply(tf.nn.l2_loss(var), wd, name='weight_loss')
    tf.add_to_collection('losses', weight_decay)
  return var 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import multiply [as 别名]
def _get_cost_function(self):
        """Compute the cost of the Mittens objective function.

        If self.mittens = 0, this is the same as the cost of GloVe.
        """
        self.weights = tf.placeholder(
            tf.float32, shape=[self.n_words, self.n_words])
        self.log_coincidence = tf.placeholder(
            tf.float32, shape=[self.n_words, self.n_words])
        self.diffs = tf.subtract(self.model, self.log_coincidence)
        cost = tf.reduce_sum(
            0.5 * tf.multiply(self.weights, tf.square(self.diffs)))
        if self.mittens > 0:
            self.mittens = tf.constant(self.mittens, tf.float32)
            cost += self.mittens * tf.reduce_sum(
                tf.multiply(
                    self.has_embedding,
                    self._tf_squared_euclidean(
                        tf.add(self.W, self.C),
                        self.original_embedding)))
        tf.summary.scalar("cost", cost)
        return cost 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import multiply [as 别名]
def f1_metric(precision, precision_op, recall, recall_op):
  """Computes F1 based on precision and recall.

  Args:
    precision: <float> [batch_size]
    precision_op: Update op for precision.
    recall: <float> [batch_size]
    recall_op: Update op for recall.

  Returns:
    tensor and update op for F1.
  """
  f1_op = tf.group(precision_op, recall_op)
  numerator = 2 * tf.multiply(precision, recall)
  denominator = tf.add(precision, recall)
  f1 = tf.divide(numerator, denominator)

  # <float> [batch_size]
  zero_vec = tf.zeros_like(f1)
  is_valid = tf.greater(denominator, zero_vec)
  f1 = tf.where(is_valid, x=f1, y=zero_vec)

  return f1, f1_op 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import multiply [as 别名]
def cosine_similarity(v1, v2):
    """Cosine similarity [-1, 1], `wiki <https://en.wikipedia.org/wiki/Cosine_similarity>`_.

    Parameters
    -----------
    v1, v2 : tensor of [batch_size, n_feature], with the same number of features.

    Returns
    -----------
    a tensor of [batch_size, ]
    """
    try: ## TF1.0
        cost = tf.reduce_sum(tf.multiply(v1, v2), 1) / (tf.sqrt(tf.reduce_sum(tf.multiply(v1, v1), 1)) * tf.sqrt(tf.reduce_sum(tf.multiply(v2, v2), 1)))
    except: ## TF0.12
        cost = tf.reduce_sum(tf.mul(v1, v2), reduction_indices=1) / (tf.sqrt(tf.reduce_sum(tf.mul(v1, v1), reduction_indices=1)) * tf.sqrt(tf.reduce_sum(tf.mul(v2, v2), reduction_indices=1)))
    return cost


## Regularization Functions 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import multiply [as 别名]
def should_distort_images(flip_left_right, random_crop, random_scale,
                          random_brightness):
  """Whether any distortions are enabled, from the input flags.

  Args:
    flip_left_right: Boolean whether to randomly mirror images horizontally.
    random_crop: Integer percentage setting the total margin used around the
    crop box.
    random_scale: Integer percentage of how much to vary the scale by.
    random_brightness: Integer range to randomly multiply the pixel values by.

  Returns:
    Boolean value indicating whether any distortions should be applied.
  """
  return (flip_left_right or (random_crop != 0) or (random_scale != 0) or
          (random_brightness != 0)) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import multiply [as 别名]
def convert_class_logits_to_softmax(multiclass_scores, temperature=1.0):
  """Converts multiclass logits to softmax scores after applying temperature.

  Args:
    multiclass_scores: float32 tensor of shape
      [num_instances, num_classes] representing the score for each box for each
      class.
    temperature: Scale factor to use prior to applying softmax. Larger
      temperatures give more uniform distruibutions after softmax.

  Returns:
    multiclass_scores: float32 tensor of shape
      [num_instances, num_classes] with scaling and softmax applied.
  """

  # Multiclass scores must be stored as logits. Apply temp and softmax.
  multiclass_scores_scaled = tf.multiply(
      multiclass_scores, 1.0 / temperature, name='scale_logits')
  multiclass_scores = tf.nn.softmax(multiclass_scores_scaled, name='softmax')

  return multiclass_scores 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import multiply [as 别名]
def testRandomHorizontalFlipWithEmptyBoxes(self):
    def graph_fn():
      preprocess_options = [(preprocessor.random_horizontal_flip, {})]
      images = self.expectedImagesAfterNormalization()
      boxes = self.createEmptyTestBoxes()
      tensor_dict = {fields.InputDataFields.image: images,
                     fields.InputDataFields.groundtruth_boxes: boxes}
      images_expected1 = self.expectedImagesAfterLeftRightFlip()
      boxes_expected = self.createEmptyTestBoxes()
      images_expected2 = images
      tensor_dict = preprocessor.preprocess(tensor_dict, preprocess_options)
      images = tensor_dict[fields.InputDataFields.image]
      boxes = tensor_dict[fields.InputDataFields.groundtruth_boxes]

      images_diff1 = tf.squared_difference(images, images_expected1)
      images_diff2 = tf.squared_difference(images, images_expected2)
      images_diff = tf.multiply(images_diff1, images_diff2)
      images_diff_expected = tf.zeros_like(images_diff)
      return [images_diff, images_diff_expected, boxes, boxes_expected]
    (images_diff_, images_diff_expected_, boxes_,
     boxes_expected_) = self.execute_cpu(graph_fn, [])
    self.assertAllClose(boxes_, boxes_expected_)
    self.assertAllClose(images_diff_, images_diff_expected_) 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import multiply [as 别名]
def test_forward_multi_input():
    with tf.Graph().as_default():
        in1 = tf.placeholder(tf.int32, shape=[3, 3], name='in1')
        in2 = tf.placeholder(tf.int32, shape=[3, 3], name='in2')
        in3 = tf.placeholder(tf.int32, shape=[3, 3], name='in3')
        in4 = tf.placeholder(tf.int32, shape=[3, 3], name='in4')

        out1 = tf.add(in1, in2, name='out1')
        out2 = tf.subtract(in3, in4, name='out2')
        out = tf.multiply(out1, out2, name='out')
        in_data = np.arange(9, dtype='int32').reshape([3, 3])

        compare_tf_with_tvm([in_data, in_data, in_data, in_data],
                            ['in1:0', 'in2:0', 'in3:0', 'in4:0'], 'out:0')

#######################################################################
# Multi Output to Graph
# --------------------- 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import multiply [as 别名]
def calc_iou_tensor(boxes1, boxes2):
  """Calculation of IoU based on two boxes tensor.

  Reference to https://github.com/kuangliu/pytorch-ssd

  Args:
    boxes1: shape (N, 4), four coordinates of N boxes
    boxes2: shape (M, 4), four coordinates of M boxes
  Returns:
    IoU: shape (N, M), IoU of the i-th box in `boxes1` and j-th box in `boxes2`
  """
  b1_left, b1_top, b1_right, b1_bottom = tf.split(boxes1, 4, axis=1)
  b2_left, b2_top, b2_right, b2_bottom = tf.split(boxes2, 4, axis=1)

  # Shape of intersect_* (N, M)
  intersect_left = tf.maximum(b1_left, tf.transpose(b2_left))
  intersect_top = tf.maximum(b1_top, tf.transpose(b2_top))
  intersect_right = tf.minimum(b1_right, tf.transpose(b2_right))
  intersect_bottom = tf.minimum(b1_bottom, tf.transpose(b2_bottom))

  boxes1_area = (b1_right - b1_left) * (b1_bottom - b1_top)
  boxes2_area = (b2_right - b2_left) * (b2_bottom - b2_top)

  intersect = tf.multiply(tf.maximum((intersect_right - intersect_left), 0),
                          tf.maximum((intersect_bottom - intersect_top), 0))
  union = boxes1_area + tf.transpose(boxes2_area) - intersect
  iou = intersect / union

  return iou 

# 需要导入模块: from tensorflow.compat import v1 [as 别名]
# 或者: from tensorflow.compat.v1 import multiply [as 别名]
def _localization_loss(self, pred_loc, gt_loc, gt_label, num_matched_boxes):
    """Computes the localization loss.

    Computes the localization loss using smooth l1 loss.
    Args:
      pred_loc: a flatten tensor that includes all predicted locations. The
        shape is [batch_size, num_anchors, 4].
      gt_loc: a tensor representing box regression targets in
        [batch_size, num_anchors, 4].
      gt_label: a tensor that represents the classification groundtruth targets.
        The shape is [batch_size, num_anchors, 1].
      num_matched_boxes: the number of anchors that are matched to a groundtruth
        targets, used as the loss normalizater. The shape is [batch_size].
    Returns:
      box_loss: a float32 representing total box regression loss.
    """
    mask = tf.greater(tf.squeeze(gt_label), 0)
    float_mask = tf.cast(mask, tf.float32)

    smooth_l1 = tf.reduce_sum(tf.losses.huber_loss(
        gt_loc, pred_loc,
        reduction=tf.losses.Reduction.NONE
    ), axis=2)
    smooth_l1 = tf.multiply(smooth_l1, float_mask)
    box_loss = tf.reduce_sum(smooth_l1, axis=1)

    return tf.reduce_mean(box_loss / num_matched_boxes)