def draw_boxes(image_and_detections):
"""Draws boxes on image."""
true_shape = image_and_detections[0]
original_shape = image_and_detections[1]
if true_image_shape is not None:
image = shape_utils.pad_or_clip_nd(image_and_detections[2],
[true_shape[0], true_shape[1], 3])
if original_image_spatial_shape is not None:
image_and_detections[2] = _resize_original_image(image, original_shape)
image_with_boxes = tf.py_func(visualize_boxes_fn, image_and_detections[2:],
tf.uint8)
return image_with_boxes
def test_pad_or_clip_nd_tensor(self):
tensor_placeholder = tf.placeholder(tf.float32, [None, 5, 4, 7])
output_tensor = shape_utils.pad_or_clip_nd(
tensor_placeholder, [None, 3, 5, tf.constant(6)])
self.assertAllEqual(output_tensor.shape.as_list(), [None, 3, 5, None])
with self.test_session() as sess:
output_tensor_np = sess.run(
output_tensor,
feed_dict={
tensor_placeholder: np.random.rand(2, 5, 4, 7),
})
self.assertAllEqual(output_tensor_np.shape, [2, 3, 5, 6])
def pad_input_data_to_static_shapes(tensor_dict,
max_num_boxes,
num_classes,
spatial_image_shape=None):
"""Pads input tensors to static shapes.
Args:
tensor_dict: Tensor dictionary of input data
max_num_boxes: Max number of groundtruth boxes needed to compute shapes for
padding.
num_classes: Number of classes in the dataset needed to compute shapes for
padding.
spatial_image_shape: A list of two integers of the form [height, width]
containing expected spatial shape of the image.
Returns:
A dictionary keyed by fields.InputDataFields containing padding shapes for
tensors in the dataset.
Raises:
ValueError: If groundtruth classes is neither rank 1 nor rank 2.
"""
if not spatial_image_shape or spatial_image_shape == [-1, -1]:
height, width = None, None
else:
height, width = spatial_image_shape # pylint: disable=unpacking-non-sequence
num_additional_channels = 0
if fields.InputDataFields.image_additional_channels in tensor_dict:
num_additional_channels = tensor_dict[
fields.InputDataFields.image_additional_channels].shape[2].value
padding_shapes = {
# Additional channels are merged before batching.
fields.InputDataFields.image:
[height, width, 3 + num_additional_channels],
fields.InputDataFields.image_additional_channels:
[height, width, num_additional_channels],
fields.InputDataFields.source_id: [],
fields.InputDataFields.filename: [],
fields.InputDataFields.key: [],
fields.InputDataFields.groundtruth_difficult: [max_num_boxes],
fields.InputDataFields.groundtruth_boxes: [max_num_boxes, 4],
fields.InputDataFields.groundtruth_classes:
[max_num_boxes, num_classes],
fields.InputDataFields.groundtruth_instance_masks:
[max_num_boxes, height, width],
fields.InputDataFields.groundtruth_is_crowd: [max_num_boxes],
fields.InputDataFields.groundtruth_group_of: [max_num_boxes],
fields.InputDataFields.groundtruth_area: [max_num_boxes],
fields.InputDataFields.groundtruth_weights: [max_num_boxes],
fields.InputDataFields.num_groundtruth_boxes: [],
fields.InputDataFields.groundtruth_label_types: [max_num_boxes],
fields.InputDataFields.groundtruth_label_scores: [max_num_boxes],
fields.InputDataFields.true_image_shape: [3],
fields.InputDataFields.multiclass_scores:
[max_num_boxes, num_classes + 1 if num_classes is not None else None],
fields.InputDataFields.groundtruth_image_classes: [num_classes],
}
if fields.InputDataFields.original_image in tensor_dict:
padding_shapes[fields.InputDataFields.original_image] = [
None, None, 3 + num_additional_channels
]
if fields.InputDataFields.groundtruth_keypoints in tensor_dict:
tensor_shape = (
tensor_dict[fields.InputDataFields.groundtruth_keypoints].shape)
padding_shape = [
max_num_boxes, tensor_shape[1].value, tensor_shape[2].value
]
padding_shapes[
fields.InputDataFields.groundtruth_keypoints] = padding_shape
if fields.InputDataFields.groundtruth_keypoint_visibilities in tensor_dict:
tensor_shape = tensor_dict[
fields.InputDataFields.groundtruth_keypoint_visibilities].shape
padding_shape = [max_num_boxes, tensor_shape[1].value]
padding_shapes[fields.InputDataFields.
groundtruth_keypoint_visibilities] = padding_shape
padded_tensor_dict = {}
for tensor_name in tensor_dict:
padded_tensor_dict[tensor_name] = shape_utils.pad_or_clip_nd(
tensor_dict[tensor_name], padding_shapes[tensor_name])
# Make sure that the number of groundtruth boxes now reflects the
# padded/clipped tensors.
if fields.InputDataFields.num_groundtruth_boxes in padded_tensor_dict:
padded_tensor_dict[fields.InputDataFields.num_groundtruth_boxes] = (
tf.minimum(
padded_tensor_dict[
fields.InputDataFields.num_groundtruth_boxes],
max_num_boxes))
return padded_tensor_dict
def pad_parts_tensor(instance_ind):
points_range_start = num_points_cumulative[instance_ind]
points_range_end = num_points_cumulative[instance_ind + 1]
part_inds = part_index[points_range_start:points_range_end]
return shape_utils.pad_or_clip_nd(part_inds,
output_shape=[max_points_per_instance])
def pad_input_data_to_static_shapes(tensor_dict, max_num_boxes, num_classes,
spatial_image_shape=None):
"""Pads input tensors to static shapes.
Args:
tensor_dict: Tensor dictionary of input data
max_num_boxes: Max number of groundtruth boxes needed to compute shapes for
padding.
num_classes: Number of classes in the dataset needed to compute shapes for
padding.
spatial_image_shape: A list of two integers of the form [height, width]
containing expected spatial shape of the image.
Returns:
A dictionary keyed by fields.InputDataFields containing padding shapes for
tensors in the dataset.
Raises:
ValueError: If groundtruth classes is neither rank 1 nor rank 2.
"""
if not spatial_image_shape or spatial_image_shape == [-1, -1]:
height, width = None, None
else:
height, width = spatial_image_shape # pylint: disable=unpacking-non-sequence
num_additional_channels = 0
if fields.InputDataFields.image_additional_channels in tensor_dict:
num_additional_channels = tensor_dict[
fields.InputDataFields.image_additional_channels].shape[2].value
padding_shapes = {
# Additional channels are merged before batching.
fields.InputDataFields.image: [
height, width, 3 + num_additional_channels
],
fields.InputDataFields.original_image_spatial_shape: [2],
fields.InputDataFields.image_additional_channels: [
height, width, num_additional_channels
],
fields.InputDataFields.source_id: [],
fields.InputDataFields.filename: [],
fields.InputDataFields.key: [],
fields.InputDataFields.groundtruth_difficult: [max_num_boxes],
fields.InputDataFields.groundtruth_boxes: [max_num_boxes, 4],
fields.InputDataFields.groundtruth_classes: [max_num_boxes, num_classes],
fields.InputDataFields.groundtruth_confidences: [
max_num_boxes, num_classes],
fields.InputDataFields.groundtruth_instance_masks: [
max_num_boxes, height, width
],
fields.InputDataFields.groundtruth_is_crowd: [max_num_boxes],
fields.InputDataFields.groundtruth_group_of: [max_num_boxes],
fields.InputDataFields.groundtruth_area: [max_num_boxes],
fields.InputDataFields.groundtruth_weights: [max_num_boxes],
fields.InputDataFields.num_groundtruth_boxes: [],
fields.InputDataFields.groundtruth_label_types: [max_num_boxes],
fields.InputDataFields.groundtruth_label_scores: [max_num_boxes],
fields.InputDataFields.true_image_shape: [3],
fields.InputDataFields.multiclass_scores: [
max_num_boxes, num_classes + 1 if num_classes is not None else None
],
fields.InputDataFields.groundtruth_image_classes: [num_classes],
fields.InputDataFields.groundtruth_image_confidences: [num_classes],
}
if fields.InputDataFields.original_image in tensor_dict:
padding_shapes[fields.InputDataFields.original_image] = [
height, width, 3 + num_additional_channels
]
if fields.InputDataFields.groundtruth_keypoints in tensor_dict:
tensor_shape = (
tensor_dict[fields.InputDataFields.groundtruth_keypoints].shape)
padding_shape = [max_num_boxes, tensor_shape[1].value,
tensor_shape[2].value]
padding_shapes[fields.InputDataFields.groundtruth_keypoints] = padding_shape
if fields.InputDataFields.groundtruth_keypoint_visibilities in tensor_dict:
tensor_shape = tensor_dict[fields.InputDataFields.
groundtruth_keypoint_visibilities].shape
padding_shape = [max_num_boxes, tensor_shape[1].value]
padding_shapes[fields.InputDataFields.
groundtruth_keypoint_visibilities] = padding_shape
padded_tensor_dict = {}
for tensor_name in tensor_dict:
padded_tensor_dict[tensor_name] = shape_utils.pad_or_clip_nd(
tensor_dict[tensor_name], padding_shapes[tensor_name])
# Make sure that the number of groundtruth boxes now reflects the
# padded/clipped tensors.
if fields.InputDataFields.num_groundtruth_boxes in padded_tensor_dict:
padded_tensor_dict[fields.InputDataFields.num_groundtruth_boxes] = (
tf.minimum(
padded_tensor_dict[fields.InputDataFields.num_groundtruth_boxes],
max_num_boxes))
return padded_tensor_dict
def pad_input_data_to_static_shapes(tensor_dict, max_num_boxes, num_classes,
spatial_image_shape=None):
"""Pads input tensors to static shapes.
In case num_additional_channels > 0, we assume that the additional channels
have already been concatenated to the base image.
Args:
tensor_dict: Tensor dictionary of input data
max_num_boxes: Max number of groundtruth boxes needed to compute shapes for
padding.
num_classes: Number of classes in the dataset needed to compute shapes for
padding.
spatial_image_shape: A list of two integers of the form [height, width]
containing expected spatial shape of the image.
Returns:
A dictionary keyed by fields.InputDataFields containing padding shapes for
tensors in the dataset.
Raises:
ValueError: If groundtruth classes is neither rank 1 nor rank 2, or if we
detect that additional channels have not been concatenated yet.
"""
if not spatial_image_shape or spatial_image_shape == [-1, -1]:
height, width = None, None
else:
height, width = spatial_image_shape # pylint: disable=unpacking-non-sequence
num_additional_channels = 0
if fields.InputDataFields.image_additional_channels in tensor_dict:
num_additional_channels = shape_utils.get_dim_as_int(tensor_dict[
fields.InputDataFields.image_additional_channels].shape[2])
# We assume that if num_additional_channels > 0, then it has already been
# concatenated to the base image (but not the ground truth).
num_channels = 3
if fields.InputDataFields.image in tensor_dict:
num_channels = shape_utils.get_dim_as_int(
tensor_dict[fields.InputDataFields.image].shape[2])
if num_additional_channels:
if num_additional_channels >= num_channels:
raise ValueError(
'Image must be already concatenated with additional channels.')
if (fields.InputDataFields.original_image in tensor_dict and
shape_utils.get_dim_as_int(
tensor_dict[fields.InputDataFields.original_image].shape[2]) ==
num_channels):
raise ValueError(
'Image must be already concatenated with additional channels.')
padding_shapes = {
fields.InputDataFields.image: [
height, width, num_channels
],
fields.InputDataFields.original_image_spatial_shape: [2],
fields.InputDataFields.image_additional_channels: [
height, width, num_additional_channels
],
fields.InputDataFields.source_id: [],
fields.InputDataFields.filename: [],
fields.InputDataFields.key: [],
fields.InputDataFields.groundtruth_difficult: [max_num_boxes],
fields.InputDataFields.groundtruth_boxes: [max_num_boxes, 4],
fields.InputDataFields.groundtruth_classes: [max_num_boxes, num_classes],
fields.InputDataFields.groundtruth_instance_masks: [
max_num_boxes, height, width
],
fields.InputDataFields.groundtruth_is_crowd: [max_num_boxes],
fields.InputDataFields.groundtruth_group_of: [max_num_boxes],
fields.InputDataFields.groundtruth_area: [max_num_boxes],
fields.InputDataFields.groundtruth_weights: [max_num_boxes],
fields.InputDataFields.groundtruth_confidences: [
max_num_boxes, num_classes
],
fields.InputDataFields.num_groundtruth_boxes: [],
fields.InputDataFields.groundtruth_label_types: [max_num_boxes],
fields.InputDataFields.groundtruth_label_weights: [max_num_boxes],
fields.InputDataFields.true_image_shape: [3],
fields.InputDataFields.groundtruth_image_classes: [num_classes],
fields.InputDataFields.groundtruth_image_confidences: [num_classes],
}
if fields.InputDataFields.original_image in tensor_dict:
padding_shapes[fields.InputDataFields.original_image] = [
height, width,
shape_utils.get_dim_as_int(tensor_dict[fields.InputDataFields.
original_image].shape[2])
]
if fields.InputDataFields.groundtruth_keypoints in tensor_dict:
tensor_shape = (
tensor_dict[fields.InputDataFields.groundtruth_keypoints].shape)
padding_shape = [max_num_boxes,
shape_utils.get_dim_as_int(tensor_shape[1]),
shape_utils.get_dim_as_int(tensor_shape[2])]
padding_shapes[fields.InputDataFields.groundtruth_keypoints] = padding_shape
if fields.InputDataFields.groundtruth_keypoint_visibilities in tensor_dict:
tensor_shape = tensor_dict[fields.InputDataFields.
groundtruth_keypoint_visibilities].shape
padding_shape = [max_num_boxes, shape_utils.get_dim_as_int(tensor_shape[1])]
padding_shapes[fields.InputDataFields.
groundtruth_keypoint_visibilities] = padding_shape
padded_tensor_dict = {}
for tensor_name in tensor_dict:
padded_tensor_dict[tensor_name] = shape_utils.pad_or_clip_nd(
tensor_dict[tensor_name], padding_shapes[tensor_name])
# Make sure that the number of groundtruth boxes now reflects the
# padded/clipped tensors.
if fields.InputDataFields.num_groundtruth_boxes in padded_tensor_dict:
padded_tensor_dict[fields.InputDataFields.num_groundtruth_boxes] = (
tf.minimum(
padded_tensor_dict[fields.InputDataFields.num_groundtruth_boxes],
max_num_boxes))
return padded_tensor_dict
def graph_fn(input_tensor):
output_tensor = shape_utils.pad_or_clip_nd(
input_tensor, [None, 3, 5, tf.constant(6)])
return output_tensor
def pad_input_data_to_static_shapes(tensor_dict,
max_num_boxes,
num_classes,
spatial_image_shape=None):
if not spatial_image_shape or spatial_image_shape == [-1, -1]:
height, width = None, None
else:
height, width = spatial_image_shape # pylint: disable=unpacking-non-sequence
num_additional_channels = 0
if fields.InputDataFields.image_additional_channels in tensor_dict:
num_additional_channels = shape_utils.get_dim_as_int(tensor_dict[
fields.InputDataFields.image_additional_channels].shape[2])
# We assume that if num_additional_channels > 0, then it has already been
# concatenated to the base image (but not the ground truth).
num_channels = 3
if fields.InputDataFields.image in tensor_dict:
num_channels = shape_utils.get_dim_as_int(
tensor_dict[fields.InputDataFields.image].shape[2])
if num_additional_channels:
if num_additional_channels >= num_channels:
raise ValueError(
'Image must be already concatenated with additional channels.')
if (fields.InputDataFields.original_image in tensor_dict
and shape_utils.get_dim_as_int(tensor_dict[
fields.InputDataFields.original_image].shape[2])
== num_channels):
raise ValueError(
'Image must be already concatenated with additional channels.')
padding_shapes = {
fields.InputDataFields.image: [height, width, num_channels],
fields.InputDataFields.original_image_spatial_shape: [2],
fields.InputDataFields.image_additional_channels:
[height, width, num_additional_channels],
fields.InputDataFields.source_id: [],
fields.InputDataFields.filename: [],
fields.InputDataFields.key: [],
fields.InputDataFields.groundtruth_difficult: [max_num_boxes],
fields.InputDataFields.groundtruth_boxes: [max_num_boxes, 4],
fields.InputDataFields.groundtruth_classes:
[max_num_boxes, num_classes],
fields.InputDataFields.groundtruth_instance_masks:
[max_num_boxes, height, width],
fields.InputDataFields.groundtruth_is_crowd: [max_num_boxes],
fields.InputDataFields.groundtruth_group_of: [max_num_boxes],
fields.InputDataFields.groundtruth_area: [max_num_boxes],
fields.InputDataFields.groundtruth_weights: [max_num_boxes],
fields.InputDataFields.groundtruth_confidences:
[max_num_boxes, num_classes],
fields.InputDataFields.num_groundtruth_boxes: [],
fields.InputDataFields.groundtruth_label_types: [max_num_boxes],
fields.InputDataFields.groundtruth_label_weights: [max_num_boxes],
fields.InputDataFields.true_image_shape: [3],
fields.InputDataFields.groundtruth_image_classes: [num_classes],
fields.InputDataFields.groundtruth_image_confidences: [num_classes],
}
if fields.InputDataFields.original_image in tensor_dict:
padding_shapes[fields.InputDataFields.original_image] = [
height, width,
shape_utils.get_dim_as_int(
tensor_dict[fields.InputDataFields.original_image].shape[2])
]
if fields.InputDataFields.groundtruth_keypoints in tensor_dict:
tensor_shape = (
tensor_dict[fields.InputDataFields.groundtruth_keypoints].shape)
padding_shape = [
max_num_boxes,
shape_utils.get_dim_as_int(tensor_shape[1]),
shape_utils.get_dim_as_int(tensor_shape[2])
]
padding_shapes[
fields.InputDataFields.groundtruth_keypoints] = padding_shape
if fields.InputDataFields.groundtruth_keypoint_visibilities in tensor_dict:
tensor_shape = tensor_dict[
fields.InputDataFields.groundtruth_keypoint_visibilities].shape
padding_shape = [
max_num_boxes,
shape_utils.get_dim_as_int(tensor_shape[1])
]
padding_shapes[fields.InputDataFields.
groundtruth_keypoint_visibilities] = padding_shape
padded_tensor_dict = {}
for tensor_name in tensor_dict:
padded_tensor_dict[tensor_name] = shape_utils.pad_or_clip_nd(
tensor_dict[tensor_name], padding_shapes[tensor_name])
# Make sure that the number of groundtruth boxes now reflects the
# padded/clipped tensors.
if fields.InputDataFields.num_groundtruth_boxes in padded_tensor_dict:
padded_tensor_dict[fields.InputDataFields.num_groundtruth_boxes] = (
tf.minimum(
padded_tensor_dict[
fields.InputDataFields.num_groundtruth_boxes],
max_num_boxes))
return padded_tensor_dict
def pad_input_data_to_static_shapes(tensor_dict,
max_num_boxes,
num_classes,
spatial_image_shape=None,
max_num_context_features=None,
context_feature_length=None,
max_dp_points=336):
"""Pads input tensors to static shapes.
In case num_additional_channels > 0, we assume that the additional channels
have already been concatenated to the base image.
Args:
tensor_dict: Tensor dictionary of input data
max_num_boxes: Max number of groundtruth boxes needed to compute shapes for
padding.
num_classes: Number of classes in the dataset needed to compute shapes for
padding.
spatial_image_shape: A list of two integers of the form [height, width]
containing expected spatial shape of the image.
max_num_context_features (optional): The maximum number of context
features needed to compute shapes padding.
context_feature_length (optional): The length of the context feature.
max_dp_points (optional): The maximum number of DensePose sampled points per
instance. The default (336) is selected since the original DensePose paper
(https://arxiv.org/pdf/1802.00434.pdf) indicates that the maximum number
of samples per part is 14, and therefore 24 * 14 = 336 is the maximum
sampler per instance.
Returns:
A dictionary keyed by fields.InputDataFields containing padding shapes for
tensors in the dataset.
Raises:
ValueError: If groundtruth classes is neither rank 1 nor rank 2, or if we
detect that additional channels have not been concatenated yet, or if
max_num_context_features is not specified and context_features is in the
tensor dict.
"""
if not spatial_image_shape or spatial_image_shape == [-1, -1]:
height, width = None, None
else:
height, width = spatial_image_shape # pylint: disable=unpacking-non-sequence
num_additional_channels = 0
if fields.InputDataFields.image_additional_channels in tensor_dict:
num_additional_channels = shape_utils.get_dim_as_int(tensor_dict[
fields.InputDataFields.image_additional_channels].shape[2])
# We assume that if num_additional_channels > 0, then it has already been
# concatenated to the base image (but not the ground truth).
num_channels = 3
if fields.InputDataFields.image in tensor_dict:
num_channels = shape_utils.get_dim_as_int(
tensor_dict[fields.InputDataFields.image].shape[2])
if num_additional_channels:
if num_additional_channels >= num_channels:
raise ValueError(
'Image must be already concatenated with additional channels.')
if (fields.InputDataFields.original_image in tensor_dict and
shape_utils.get_dim_as_int(
tensor_dict[fields.InputDataFields.original_image].shape[2]) ==
num_channels):
raise ValueError(
'Image must be already concatenated with additional channels.')
if fields.InputDataFields.context_features in tensor_dict and (
max_num_context_features is None):
raise ValueError('max_num_context_features must be specified in the model '
'config if include_context is specified in the input '
'config')
padding_shapes = {
fields.InputDataFields.image: [height, width, num_channels],
fields.InputDataFields.original_image_spatial_shape: [2],
fields.InputDataFields.image_additional_channels: [
height, width, num_additional_channels
],
fields.InputDataFields.source_id: [],
fields.InputDataFields.filename: [],
fields.InputDataFields.key: [],
fields.InputDataFields.groundtruth_difficult: [max_num_boxes],
fields.InputDataFields.groundtruth_boxes: [max_num_boxes, 4],
fields.InputDataFields.groundtruth_classes: [max_num_boxes, num_classes],
fields.InputDataFields.groundtruth_instance_masks: [
max_num_boxes, height, width
],
fields.InputDataFields.groundtruth_is_crowd: [max_num_boxes],
fields.InputDataFields.groundtruth_group_of: [max_num_boxes],
fields.InputDataFields.groundtruth_area: [max_num_boxes],
fields.InputDataFields.groundtruth_weights: [max_num_boxes],
fields.InputDataFields.groundtruth_confidences: [
max_num_boxes, num_classes
],
fields.InputDataFields.num_groundtruth_boxes: [],
fields.InputDataFields.groundtruth_label_types: [max_num_boxes],
fields.InputDataFields.groundtruth_label_weights: [max_num_boxes],
fields.InputDataFields.true_image_shape: [3],
fields.InputDataFields.groundtruth_image_classes: [num_classes],
fields.InputDataFields.groundtruth_image_confidences: [num_classes],
fields.InputDataFields.groundtruth_labeled_classes: [num_classes],
}
if fields.InputDataFields.original_image in tensor_dict:
padding_shapes[fields.InputDataFields.original_image] = [
height, width,
shape_utils.get_dim_as_int(tensor_dict[fields.InputDataFields.
original_image].shape[2])
]
if fields.InputDataFields.groundtruth_keypoints in tensor_dict:
tensor_shape = (
tensor_dict[fields.InputDataFields.groundtruth_keypoints].shape)
padding_shape = [max_num_boxes,
shape_utils.get_dim_as_int(tensor_shape[1]),
shape_utils.get_dim_as_int(tensor_shape[2])]
padding_shapes[fields.InputDataFields.groundtruth_keypoints] = padding_shape
if fields.InputDataFields.groundtruth_keypoint_visibilities in tensor_dict:
tensor_shape = tensor_dict[fields.InputDataFields.
groundtruth_keypoint_visibilities].shape
padding_shape = [max_num_boxes, shape_utils.get_dim_as_int(tensor_shape[1])]
padding_shapes[fields.InputDataFields.
groundtruth_keypoint_visibilities] = padding_shape
if fields.InputDataFields.groundtruth_keypoint_weights in tensor_dict:
tensor_shape = (
tensor_dict[fields.InputDataFields.groundtruth_keypoint_weights].shape)
padding_shape = [max_num_boxes, shape_utils.get_dim_as_int(tensor_shape[1])]
padding_shapes[fields.InputDataFields.
groundtruth_keypoint_weights] = padding_shape
if fields.InputDataFields.groundtruth_dp_num_points in tensor_dict:
padding_shapes[
fields.InputDataFields.groundtruth_dp_num_points] = [max_num_boxes]
padding_shapes[
fields.InputDataFields.groundtruth_dp_part_ids] = [
max_num_boxes, max_dp_points]
padding_shapes[
fields.InputDataFields.groundtruth_dp_surface_coords] = [
max_num_boxes, max_dp_points, 4]
# Prepare for ContextRCNN related fields.
if fields.InputDataFields.context_features in tensor_dict:
padding_shape = [max_num_context_features, context_feature_length]
padding_shapes[fields.InputDataFields.context_features] = padding_shape
tensor_shape = tf.shape(
tensor_dict[fields.InputDataFields.context_features])
tensor_dict[fields.InputDataFields.valid_context_size] = tensor_shape[0]
padding_shapes[fields.InputDataFields.valid_context_size] = []
if fields.InputDataFields.context_feature_length in tensor_dict:
padding_shapes[fields.InputDataFields.context_feature_length] = []
if fields.InputDataFields.is_annotated in tensor_dict:
padding_shapes[fields.InputDataFields.is_annotated] = []
padded_tensor_dict = {}
for tensor_name in tensor_dict:
padded_tensor_dict[tensor_name] = shape_utils.pad_or_clip_nd(
tensor_dict[tensor_name], padding_shapes[tensor_name])
# Make sure that the number of groundtruth boxes now reflects the
# padded/clipped tensors.
if fields.InputDataFields.num_groundtruth_boxes in padded_tensor_dict:
padded_tensor_dict[fields.InputDataFields.num_groundtruth_boxes] = (
tf.minimum(
padded_tensor_dict[fields.InputDataFields.num_groundtruth_boxes],
max_num_boxes))
return padded_tensor_dict
