python类boolean_mask()的实例源码

def chi2(exp, obs):
    """
        Compute CHI^2 statistics of non-zero expected elements
    """
    zero = tf.constant(0, dtype=tf.float32)
    mask = tf.not_equal(exp, zero)

    def masking(tensor, mask):
        return tf.boolean_mask(tensor, mask)

    stat = tf.reduce_sum(
        tf.div(
            tf.pow(
                tf.subtract(masking(obs, mask), masking(exp, mask)),
                2),
            masking(exp, mask)),
        name="chi2_statistics")

    return stat

def sparse_boolean_mask(tensor, mask):
    """
    Creates a sparse tensor from masked elements of `tensor`

    Inputs:
      tensor: a 2-D tensor, [batch_size, T]
      mask: a 2-D mask, [batch_size, T]

    Output: a 2-D sparse tensor
    """
    mask_lens = tf.reduce_sum(tf.cast(mask, tf.int32), -1, keep_dims=True)
    mask_shape = tf.shape(mask)
    left_shifted_mask = tf.tile(
        tf.expand_dims(tf.range(mask_shape[1]), 0),
        [mask_shape[0], 1]
    ) < mask_lens
    return tf.SparseTensor(
        indices=tf.where(left_shifted_mask),
        values=tf.boolean_mask(tensor, mask),
        shape=tf.cast(tf.pack([mask_shape[0], tf.reduce_max(mask_lens)]), tf.int64)  # For 2D only
    )

def add_loss_op(self, preds):
        """Adds Ops for the loss function to the computational graph.

        TODO: Compute averaged cross entropy loss for the predictions.
        Importantly, you must ignore the loss for any masked tokens.

        Hint: You might find tf.boolean_mask useful to mask the losses on masked tokens.
        Hint: You can use tf.nn.sparse_softmax_cross_entropy_with_logits to simplify your
                    implementation. You might find tf.reduce_mean useful.
        Args:
            pred: A tensor of shape (batch_size, max_length, n_classes) containing the output of the neural
                  network before the softmax layer.
        Returns:
            loss: A 0-d tensor (scalar)
        """
        ### YOUR CODE HERE (~2-4 lines)
        loss = tf.reduce_mean(tf.boolean_mask(tf.nn.sparse_softmax_cross_entropy_with_logits(labels = self.labels_placeholder,
                                                                            logits = preds), self.mask_placeholder)) 

        ### END YOUR CODE
        return loss

def bboxes_filter_overlap(labels, bboxes,xs, ys, threshold, scope=None, assign_negative = False):
    """Filter out bounding boxes based on (relative )overlap with reference
    box [0, 0, 1, 1].  Remove completely bounding boxes, or assign negative
    labels to the one outside (useful for latter processing...).

    Return:
      labels, bboxes: Filtered (or newly assigned) elements.
    """
    with tf.name_scope(scope, 'bboxes_filter', [labels, bboxes]):
        scores = bboxes_intersection(tf.constant([0, 0, 1, 1], bboxes.dtype),bboxes)

        mask = scores > threshold
        if assign_negative:
            labels = tf.where(mask, labels, -labels)
        else:
            labels = tf.boolean_mask(labels, mask)
            bboxes = tf.boolean_mask(bboxes, mask)
            scores = bboxes_intersection(tf.constant([0, 0, 1, 1], bboxes.dtype),bboxes)
            xs = tf.boolean_mask(xs, mask);
            ys = tf.boolean_mask(ys, mask);
        return labels, bboxes, xs, ys

def bboxes_filter_center(labels, bboxes, margins=[0., 0., 0., 0.],
                         scope=None):
    """Filter out bounding boxes whose center are not in
    the rectangle [0, 0, 1, 1] + margins. The margin Tensor
    can be used to enforce or loosen this condition.

    Return:
      labels, bboxes: Filtered elements.
    """
    with tf.name_scope(scope, 'bboxes_filter', [labels, bboxes]):
        cy = (bboxes[:, 0] + bboxes[:, 2]) / 2.
        cx = (bboxes[:, 1] + bboxes[:, 3]) / 2.
        mask = tf.greater(cy, margins[0])
        mask = tf.logical_and(mask, tf.greater(cx, margins[1]))
        mask = tf.logical_and(mask, tf.less(cx, 1. + margins[2]))
        mask = tf.logical_and(mask, tf.less(cx, 1. + margins[3]))
        # Boolean masking...
        labels = tf.boolean_mask(labels, mask)
        bboxes = tf.boolean_mask(bboxes, mask)
        return labels, bboxes

def bboxes_filter_labels(labels, bboxes,
                         out_labels=[], num_classes=np.inf,
                         scope=None):
    """Filter out labels from a collection. Typically used to get
    of DontCare elements. Also remove elements based on the number of classes.

    Return:
      labels, bboxes: Filtered elements.
    """
    with tf.name_scope(scope, 'bboxes_filter_labels', [labels, bboxes]):
        mask = tf.greater_equal(labels, num_classes)
        for l in labels:
            mask = tf.logical_and(mask, tf.not_equal(labels, l))
        labels = tf.boolean_mask(labels, mask)
        bboxes = tf.boolean_mask(bboxes, mask)
        return labels, bboxes


# =========================================================================== #
# Standard boxes computation.
# =========================================================================== #

def average_precision_voc07(precision, recall, name=None):
    """Compute (interpolated) average precision from precision and recall Tensors.

    The implementation follows Pascal 2007 guidelines.
    See also: https://sanchom.wordpress.com/tag/average-precision/
    """
    with tf.name_scope(name, 'average_precision_voc07', [precision, recall]):
        # Convert to float64 to decrease error on cumulated sums.
        precision = tf.cast(precision, dtype=tf.float64)
        recall = tf.cast(recall, dtype=tf.float64)
        # Add zero-limit value to avoid any boundary problem...
        precision = tf.concat([precision, [0.]], axis=0)
        recall = tf.concat([recall, [np.inf]], axis=0)

        # Split the integral into 10 bins.
        l_aps = []
        for t in np.arange(0., 1.1, 0.1):
            mask = tf.greater_equal(recall, t)
            v = tf.reduce_max(tf.boolean_mask(precision, mask))
            l_aps.append(v / 11.)
        ap = tf.add_n(l_aps)
        return ap

def image_mirroring(img, label, seed):
    """
    Randomly mirrors the images.

    Args:
      img: Training image to mirror.
      label: Segmentation mask to mirror.
      seed: Random seed.
    """

    distort_left_right_random = tf.random_uniform([1], 0, 1.0, dtype=tf.float32, seed=seed)[0]
    mirror = tf.less(tf.stack([1.0, distort_left_right_random, 1.0]), 0.5)
    mirror = tf.boolean_mask([0, 1, 2], mirror)
    img = tf.reverse(img, mirror)
    label = tf.reverse(label, mirror)
    return img, label

def sample_k_fids_for_pid(pid, all_fids, all_pids, batch_k):
    """ Given a PID, select K FIDs of that specific PID. """
    possible_fids = tf.boolean_mask(all_fids, tf.equal(all_pids, pid))

    # The following simply uses a subset of K of the possible FIDs
    # if more than, or exactly K are available. Otherwise, we first
    # create a padded list of indices which contain a multiple of the
    # original FID count such that all of them will be sampled equally likely.
    count = tf.shape(possible_fids)[0]
    padded_count = tf.cast(tf.ceil(batch_k / count), tf.int32) * count
    full_range = tf.mod(tf.range(padded_count), count)

    # Sampling is always performed by shuffling and taking the first k.
    shuffled = tf.random_shuffle(full_range)
    selected_fids = tf.gather(possible_fids, shuffled[:batch_k])

    return selected_fids, tf.fill([batch_k], pid)

def separation_loss(tf_prediction_serial, tf_interactions_serial, **kwargs):
    """
    This loss function models the explicit positive and negative interaction predictions as normal distributions and
    returns the probability of overlap between the two distributions.
    :param tf_prediction_serial:
    :param tf_interactions_serial:
    :return:
    """

    tf_positive_mask = tf.greater(tf_interactions_serial, 0.0)
    tf_negative_mask = tf.less_equal(tf_interactions_serial, 0.0)

    tf_positive_predictions = tf.boolean_mask(tf_prediction_serial, tf_positive_mask)
    tf_negative_predictions = tf.boolean_mask(tf_prediction_serial, tf_negative_mask)

    tf_pos_mean, tf_pos_var = tf.nn.moments(tf_positive_predictions, axes=[0])
    tf_neg_mean, tf_neg_var = tf.nn.moments(tf_negative_predictions, axes=[0])

    tf_overlap_distribution = tf.contrib.distributions.Normal(loc=(tf_neg_mean - tf_pos_mean),
                                                              scale=tf.sqrt(tf_neg_var + tf_pos_var))

    loss = 1.0 - tf_overlap_distribution.cdf(0.0)
    return loss

def ctc_label_dense_to_sparse(labels, label_lengths, batch_size):
    # The second dimension of labels must be equal to the longest label length in the batch
    correct_shape_assert = tf.assert_equal(tf.shape(labels)[1], tf.reduce_max(label_lengths))
    with tf.control_dependencies([correct_shape_assert]):
        labels = tf.identity(labels)

    label_shape = tf.shape(labels)
    num_batches_tns = tf.stack([label_shape[0]])
    max_num_labels_tns = tf.stack([label_shape[1]])
    def range_less_than(previous_state, current_input):
        return tf.expand_dims(tf.range(label_shape[1]), 0) < current_input

    init = tf.cast(tf.fill(max_num_labels_tns, 0), tf.bool)
    init = tf.expand_dims(init, 0)
    dense_mask = tf.scan(range_less_than, label_lengths, initializer=init, parallel_iterations=1)
    dense_mask = dense_mask[:, 0, :]

    label_array = tf.reshape(tf.tile(tf.range(0, label_shape[1]), num_batches_tns),
          label_shape)
    label_ind = tf.boolean_mask(label_array, dense_mask)

    batch_array = tf.transpose(tf.reshape(tf.tile(tf.range(0, label_shape[0]), max_num_labels_tns), tf.reverse(label_shape, [0])))
    batch_ind = tf.boolean_mask(batch_array, dense_mask)

    indices = tf.transpose(tf.reshape(tf.concat([batch_ind, label_ind], 0), [2, -1]))
    shape = [batch_size, tf.reduce_max(label_lengths)]
    vals_sparse = gather_nd(labels, indices, shape)

    return tf.SparseTensor(tf.to_int64(indices), vals_sparse, tf.to_int64(label_shape))

# Validate and normalize transcriptions. Returns a cleaned version of the label
# or None if it's invalid.

def ctc_label_dense_to_sparse(labels, label_lengths, batch_size):
    # The second dimension of labels must be equal to the longest label length in the batch
    correct_shape_assert = tf.assert_equal(tf.shape(labels)[1], tf.reduce_max(label_lengths))
    with tf.control_dependencies([correct_shape_assert]):
        labels = tf.identity(labels)

    label_shape = tf.shape(labels)
    num_batches_tns = tf.stack([label_shape[0]])
    max_num_labels_tns = tf.stack([label_shape[1]])
    def range_less_than(previous_state, current_input):
        return tf.expand_dims(tf.range(label_shape[1]), 0) < current_input

    init = tf.cast(tf.fill(max_num_labels_tns, 0), tf.bool)
    init = tf.expand_dims(init, 0)
    dense_mask = tf.scan(range_less_than, label_lengths, initializer=init, parallel_iterations=1)
    dense_mask = dense_mask[:, 0, :]

    label_array = tf.reshape(tf.tile(tf.range(0, label_shape[1]), num_batches_tns),
          label_shape)
    label_ind = tf.boolean_mask(label_array, dense_mask)

    batch_array = tf.transpose(tf.reshape(tf.tile(tf.range(0, label_shape[0]), max_num_labels_tns), tf.reverse(label_shape, [0])))
    batch_ind = tf.boolean_mask(batch_array, dense_mask)

    indices = tf.transpose(tf.reshape(tf.concat([batch_ind, label_ind], 0), [2, -1]))
    shape = [batch_size, tf.reduce_max(label_lengths)]
    vals_sparse = gather_nd(labels, indices, shape)

    return tf.SparseTensor(tf.to_int64(indices), vals_sparse, tf.to_int64(label_shape))

# Validate and normalize transcriptions. Returns a cleaned version of the label
# or None if it's invalid.

def __init__(self, scope = 'policy_network', learning_rate = 0.001):
        self.initializer = tf.contrib.layers.xavier_initializer()
        with tf.variable_scope(scope):
            self.state = tf.placeholder(tf.float32, [None, state_dim], name = 'state')
            self.action = tf.placeholder(tf.int32, [None], name = 'action')
            self.target = tf.placeholder(tf.float32, name = 'target')
            self.action_prob = policy_nn(self.state, state_dim, action_space, self.initializer)

            action_mask = tf.cast(tf.one_hot(self.action, depth = action_space), tf.bool)
            self.picked_action_prob = tf.boolean_mask(self.action_prob, action_mask)

            self.loss = tf.reduce_sum(-tf.log(self.picked_action_prob)*self.target) + sum(tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES, scope=scope))
            self.optimizer = tf.train.AdamOptimizer(learning_rate = learning_rate)
            self.train_op = self.optimizer.minimize(self.loss)

def __init__(self, learning_rate = 0.001):
        self.initializer = tf.contrib.layers.xavier_initializer()
        with tf.variable_scope('supervised_policy'):
            self.state = tf.placeholder(tf.float32, [None, state_dim], name = 'state')
            self.action = tf.placeholder(tf.int32, [None], name = 'action')
            self.action_prob = policy_nn(self.state, state_dim, action_space, self.initializer)

            action_mask = tf.cast(tf.one_hot(self.action, depth = action_space), tf.bool)
            self.picked_action_prob = tf.boolean_mask(self.action_prob, action_mask)

            self.loss = tf.reduce_sum(-tf.log(self.picked_action_prob)) + sum(tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES, scope = 'supervised_policy'))
            self.optimizer = tf.train.AdamOptimizer(learning_rate = learning_rate)
            self.train_op = self.optimizer.minimize(self.loss)

def _cls_mining(self, scores, status, hard_neg_ratio=3.0, scope=None):
    """
    Positive classification loss and hard negative classificatin loss
    ARGS
      scores: [n, n_classes]
      status: int [n] node or link matching status
    RETURNS
      pos_loss: []
      n_pos: int []
      hard_neg_loss: []
      n_hard_neg: []
    """
    with tf.variable_scope(scope or 'cls_mining'):
      # positive classification loss
      pos_mask = tf.equal(status, MATCH_STATUS_POS)
      pos_scores = tf.boolean_mask(scores, pos_mask)
      n_pos = tf.shape(pos_scores)[0]
      pos_labels = tf.fill([n_pos], POS_LABEL)
      pos_loss = tf.reduce_sum(tf.nn.sparse_softmax_cross_entropy_with_logits(
        logits=pos_scores, labels=pos_labels))

      # hard negative classification loss
      neg_mask = tf.equal(status, MATCH_STATUS_NEG)
      neg_scores = tf.boolean_mask(scores, neg_mask)
      n_neg = tf.shape(neg_scores)[0]
      n_hard_neg = tf.cast(n_pos, tf.float32) * hard_neg_ratio
      n_hard_neg = tf.minimum(n_hard_neg, tf.cast(n_neg, tf.float32))
      n_hard_neg = tf.cast(n_hard_neg, tf.int32)
      neg_prob = tf.nn.softmax(neg_scores)[:, NEG_LABEL]
      # find the k examples with the least negative probabilities
      _, hard_neg_indices = tf.nn.top_k(-neg_prob, k=n_hard_neg)
      hard_neg_scores = tf.gather(neg_scores, hard_neg_indices)
      hard_neg_labels = tf.fill([n_hard_neg], NEG_LABEL)
      hard_neg_loss = tf.reduce_sum(tf.nn.sparse_softmax_cross_entropy_with_logits(
        logits=hard_neg_scores, labels=hard_neg_labels))

      return pos_loss, n_pos, hard_neg_loss, n_hard_neg

def ctc_label_dense_to_sparse(labels, label_lengths):
    # undocumented feature soon to be made public
    from tensorflow.python.ops import functional_ops
    label_shape = tf.shape(labels)
    num_batches_tns = tf.pack([label_shape[0]])
    max_num_labels_tns = tf.pack([label_shape[1]])

    def range_less_than(previous_state, current_input):
        return tf.expand_dims(tf.range(label_shape[1]), 0) < tf.fill(max_num_labels_tns, current_input)

    init = tf.cast(tf.fill([1, label_shape[1]], 0), tf.bool)
    dense_mask = functional_ops.scan(range_less_than, label_lengths,
                                     initializer=init, parallel_iterations=1)
    dense_mask = dense_mask[:, 0, :]

    label_array = tf.reshape(tf.tile(tf.range(0, label_shape[1]), num_batches_tns),
                             label_shape)
    label_ind = tf.boolean_mask(label_array, dense_mask)

    batch_array = tf.transpose(tf.reshape(tf.tile(tf.range(0, label_shape[0]),
                                                  max_num_labels_tns), tf.reverse(label_shape, [True])))
    batch_ind = tf.boolean_mask(batch_array, dense_mask)
    indices = tf.transpose(tf.reshape(tf.concat(0, [batch_ind, label_ind]), [2, -1]))

    vals_sparse = tf.gather_nd(labels, indices)

    return tf.SparseTensor(tf.to_int64(indices), vals_sparse, tf.to_int64(label_shape))

def filter_small_gt(gt_bboxes, gt_cats, min_size):
    mask = tf.logical_and(gt_bboxes[:, 2] >= min_size,
                          gt_bboxes[:, 3] >= min_size)
    return tf.boolean_mask(gt_bboxes, mask), tf.boolean_mask(gt_cats, mask)

def nms(self, localization, confidence, tiling):
        good_bboxes = decode_bboxes(localization, tiling)

        not_crap_mask = tf.reduce_max(confidence[:, 1:], axis=-1) >= args.conf_thresh
        good_bboxes = tf.boolean_mask(good_bboxes, not_crap_mask)
        confidence = tf.boolean_mask(confidence, not_crap_mask)

        self.detection_list = []
        self.score_list = []
        for i in range(1, self.loader.num_classes):
            class_mask = tf.greater(confidence[:, i], args.conf_thresh)
            class_scores = tf.boolean_mask(confidence[:, i], class_mask)
            class_bboxes = tf.boolean_mask(good_bboxes, class_mask)

            K = tf.minimum(tf.size(class_scores), args.top_k_nms)
            _, top_k_inds = tf.nn.top_k(class_scores, K)
            top_class_scores = tf.gather(class_scores, top_k_inds)
            top_class_bboxes = tf.gather(class_bboxes, top_k_inds)

            final_inds = tf.image.non_max_suppression(top_class_bboxes,
                                                        top_class_scores,
                                                        max_output_size=args.top_k_after_nms,
                                                        iou_threshold=args.nms_thresh)

            final_class_bboxes = tf.gather(top_class_bboxes, final_inds)
            final_scores = tf.gather(top_class_scores, final_inds)
            self.detection_list.append(final_class_bboxes)
            self.score_list.append(final_scores)

def build_detector(self):
        img_size = self.config['image_size']
        self.image_ph = tf.placeholder(shape=[None, None, 3],
                                       dtype=tf.float32, name='img_ph')
        self.seg_ph = tf.placeholder(shape=[None, None], dtype=tf.int32, name='seg_ph')

        img = tf.image.resize_bilinear(tf.expand_dims(self.image_ph, 0),
                                       (img_size, img_size))
        self.net.create_trunk(img)

        if args.detect:
            self.net.create_multibox_head(self.loader.num_classes)
            confidence = tf.nn.softmax(tf.squeeze(self.net.outputs['confidence']))
            location = tf.squeeze(self.net.outputs['location'])
            self.nms(location, confidence, self.bboxer.tiling)

        if args.segment:
            self.net.create_segmentation_head(self.loader.num_classes)
            self.segmentation = self.net.outputs['segmentation']
            seg_shape = tf.shape(self.image_ph)[:2]
            self.segmentation = tf.image.resize_bilinear(self.segmentation, seg_shape)

            self.segmentation = tf.cast(tf.argmax(tf.squeeze(self.segmentation), axis=-1), tf.int32)
            self.segmentation = tf.reshape(self.segmentation, seg_shape)
            self.segmentation.set_shape([None, None])

            if not self.no_gt:
                easy_mask = self.seg_ph <= self.loader.num_classes
                predictions = tf.boolean_mask(self.segmentation, easy_mask)
                labels = tf.boolean_mask(self.seg_ph, easy_mask)
                self.mean_iou, self.iou_update = mean_iou(predictions, labels, self.loader.num_classes)
            else:
                self.mean_iou = tf.constant(0)
                self.iou_update = tf.constant(0)

def roc_auc_score(y_pred, y_true):
    """ ROC AUC Score.

    Approximates the Area Under Curve score, using approximation based on
    the Wilcoxon-Mann-Whitney U statistic.

    Yan, L., Dodier, R., Mozer, M. C., & Wolniewicz, R. (2003).
    Optimizing Classifier Performance via an Approximation to the Wilcoxon-Mann-Whitney Statistic.

    Measures overall performance for a full range of threshold levels.

    Arguments:
        y_pred: `Tensor`. Predicted values.
        y_true: `Tensor` . Targets (labels), a probability distribution.

    """
    with tf.name_scope("RocAucScore"):

        pos = tf.boolean_mask(y_pred, tf.cast(y_true, tf.bool))
        neg = tf.boolean_mask(y_pred, ~tf.cast(y_true, tf.bool))

        pos = tf.expand_dims(pos, 0)
        neg = tf.expand_dims(neg, 1)

        # original paper suggests performance is robust to exact parameter choice
        gamma = 0.2
        p     = 3

        difference = tf.zeros_like(pos * neg) + pos - neg - gamma

        masked = tf.boolean_mask(difference, difference < 0.0)

        return tf.reduce_sum(tf.pow(-masked, p))