def nearest_neighbor_upsampling(input_tensor, scale):
"""Nearest neighbor upsampling implementation.
Nearest neighbor upsampling function that maps input tensor with shape
[batch_size, height, width, channels] to [batch_size, height * scale
, width * scale, channels]. This implementation only uses reshape and
broadcasting to make it TPU compatible.
Args:
input_tensor: A float32 tensor of size [batch, height_in, width_in,
channels].
scale: An integer multiple to scale resolution of input data.
Returns:
data_up: A float32 tensor of size
[batch, height_in*scale, width_in*scale, channels].
"""
with tf.name_scope('nearest_neighbor_upsampling'):
(batch_size, height, width, channels
) = shape_utils.combined_static_and_dynamic_shape(input_tensor)
output_tensor = tf.reshape(input_tensor, [
batch_size, height, 1, width, 1, channels
]) * tf.ones([1, 1, scale, 1, scale, 1], dtype=input_tensor.dtype)
return tf.reshape(
output_tensor,
[batch_size, height * scale, width * scale, channels])
def select_random_box(boxlist, default_box=None, seed=None, scope=None):
"""Selects a random bounding box from a `BoxList`.
Args:
boxlist: A BoxList.
default_box: A [1, 4] float32 tensor. If no boxes are present in `boxlist`,
this default box will be returned. If None, will use a default box of
[[-1., -1., -1., -1.]].
seed: Random seed.
scope: Name scope.
Returns:
bbox: A [1, 4] tensor with a random bounding box.
valid: A bool tensor indicating whether a valid bounding box is returned
(True) or whether the default box is returned (False).
"""
with tf.name_scope(scope, 'SelectRandomBox'):
bboxes = boxlist.get()
combined_shape = shape_utils.combined_static_and_dynamic_shape(bboxes)
number_of_boxes = combined_shape[0]
default_box = default_box or tf.constant([[-1., -1., -1., -1.]])
def select_box():
random_index = tf.random_uniform([],
maxval=number_of_boxes,
dtype=tf.int32,
seed=seed)
return tf.expand_dims(bboxes[random_index],
axis=0), tf.constant(True)
return tf.cond(tf.greater_equal(number_of_boxes, 1),
true_fn=select_box,
false_fn=lambda: (default_box, tf.constant(False)))
def _create_regression_targets(self, anchors, groundtruth_boxes, match):
matched_gt_boxes = match.gather_based_on_match(
groundtruth_boxes.get(),
unmatched_value=tf.zeros(4),
ignored_value=tf.zeros(4))
matched_gt_boxlist = box_list.BoxList(matched_gt_boxes)
####
if groundtruth_boxes.has_field(KEYPOINTS_FIELD_NAME):
groundtruth_keypoints = groundtruth_boxes.get_field(
KEYPOINTS_FIELD_NAME)
matched_keypoints = match.gather_based_on_match(
groundtruth_keypoints,
unmatched_value=tf.zeros(
groundtruth_keypoints.get_shape()[1:]),
ignored_value=tf.zeros(groundtruth_keypoints.get_shape()[1:]))
matched_gt_boxlist.add_field(KEYPOINTS_FIELD_NAME,
matched_keypoints)
####
matched_reg_targets = self._box_coder.encode(matched_gt_boxlist,
anchors)
match_results_shape = shape_utils.combined_static_and_dynamic_shape(
match.match_results)
unmatched_ignored_reg_targets = tf.tile(
self._default_regression_target(), [match_results_shape[0], 1])
matched_anchors_mask = match.matched_column_indicator()
reg_targets = tf.where(matched_anchors_mask, matched_reg_targets,
unmatched_ignored_reg_targets)
return reg_targets
def matmul_gather_on_zeroth_axis(params, indices, scope=None):
"""Matrix multiplication based implementation of tf.gather on zeroth axis.
TODO(rathodv, jonathanhuang): enable sparse matmul option.
Args:
params: A float32 Tensor. The tensor from which to gather values.
Must be at least rank 1.
indices: A Tensor. Must be one of the following types: int32, int64.
Must be in range [0, params.shape[0])
scope: A name for the operation (optional).
Returns:
A Tensor. Has the same type as params. Values from params gathered
from indices given by indices, with shape indices.shape + params.shape[1:].
"""
with tf.name_scope(scope, 'MatMulGather'):
params_shape = shape_utils.combined_static_and_dynamic_shape(params)
indices_shape = shape_utils.combined_static_and_dynamic_shape(indices)
params2d = tf.reshape(params, [params_shape[0], -1])
indicator_matrix = tf.one_hot(indices, params_shape[0])
gathered_result_flattened = tf.matmul(indicator_matrix, params2d)
return tf.reshape(gathered_result_flattened,
tf.stack(indices_shape + params_shape[1:]))
def nearest_neighbor_upsampling(input_tensor,
scale=None,
height_scale=None,
width_scale=None):
"""Nearest neighbor upsampling implementation.
Nearest neighbor upsampling function that maps input tensor with shape
[batch_size, height, width, channels] to [batch_size, height * scale
, width * scale, channels]. This implementation only uses reshape and
broadcasting to make it TPU compatible.
Args:
input_tensor: A float32 tensor of size [batch, height_in, width_in,
channels].
scale: An integer multiple to scale resolution of input data in both height
and width dimensions.
height_scale: An integer multiple to scale the height of input image. This
option when provided overrides `scale` option.
width_scale: An integer multiple to scale the width of input image. This
option when provided overrides `scale` option.
Returns:
data_up: A float32 tensor of size
[batch, height_in*scale, width_in*scale, channels].
Raises:
ValueError: If both scale and height_scale or if both scale and width_scale
are None.
"""
if not scale and (height_scale is None or width_scale is None):
raise ValueError('Provide either `scale` or `height_scale` and'
' `width_scale`.')
with tf.name_scope('nearest_neighbor_upsampling'):
h_scale = scale if height_scale is None else height_scale
w_scale = scale if width_scale is None else width_scale
(batch_size, height, width, channels
) = shape_utils.combined_static_and_dynamic_shape(input_tensor)
output_tensor = tf.stack([input_tensor] * w_scale, axis=3)
output_tensor = tf.stack([output_tensor] * h_scale, axis=2)
return tf.reshape(
output_tensor,
[batch_size, height * h_scale, width * w_scale, channels])
def assign(self,
anchors,
groundtruth_boxes,
groundtruth_labels=None,
groundtruth_weights=None,
**params):
if not isinstance(anchors, box_list.BoxList):
raise ValueError('anchors must be an BoxList')
if not isinstance(groundtruth_boxes, box_list.BoxList):
raise ValueError('groundtruth_boxes must be an BoxList')
if groundtruth_labels is None:
#shape=[N,1]
groundtruth_labels = tf.ones(
tf.expand_dims(groundtruth_boxes.num_boxes(), 0))
groundtruth_labels = tf.expand_dims(groundtruth_labels, -1)
unmatched_shape_assert = shape_utils.assert_shape_equal(
shape_utils.combined_static_and_dynamic_shape(groundtruth_labels)
[1:],
shape_utils.combined_static_and_dynamic_shape(
self._unmatched_cls_target))
labels_and_box_shapes_assert = shape_utils.assert_shape_equal(
shape_utils.combined_static_and_dynamic_shape(groundtruth_labels)
[:1],
shape_utils.combined_static_and_dynamic_shape(
groundtruth_boxes.get())[:1])
if groundtruth_weights is None:
num_gt_boxes = groundtruth_boxes.num_boxes_static()
if not num_gt_boxes:
num_gt_boxes = groundtruth_boxes.num_boxes()
groundtruth_weights = tf.ones([num_gt_boxes], dtype=tf.float32)
with tf.control_dependencies(
[unmatched_shape_assert, labels_and_box_shapes_assert]):
match_quality_matrix = self._similarity_calc.compare(
groundtruth_boxes, anchors)
match = self._matcher.match(match_quality_matrix, **params)
#shape=[anchor_num,4]
reg_targets = self._create_regression_targets(
anchors, groundtruth_boxes, match)
#shape=[anchor_num,1]
cls_targets = self._create_classification_targets(
groundtruth_labels, match)
#shape=[anchor_num,]
reg_weights = self._create_regression_weights(
match, groundtruth_weights)
#shape=[anchor_num,]
cls_weights = self._create_classification_weights(
match, groundtruth_weights)
num_anchors = anchors.num_boxes_static()
if num_anchors is not None:
reg_targets = self._reset_target_shape(reg_targets, num_anchors)
cls_targets = self._reset_target_shape(cls_targets, num_anchors)
reg_weights = self._reset_target_shape(reg_weights, num_anchors)
cls_weights = self._reset_target_shape(cls_weights, num_anchors)
return cls_targets, cls_weights, reg_targets, reg_weights, match