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 pad_surface_coordinates_tensor(instance_ind):
"""Pads DensePose surface coordinates for each instance."""
points_range_start = num_points_cumulative[instance_ind]
points_range_end = num_points_cumulative[instance_ind + 1]
y = dp_y[points_range_start:points_range_end]
x = dp_x[points_range_start:points_range_end]
v = dp_v[points_range_start:points_range_end]
u = dp_u[points_range_start:points_range_end]
# Create [num_points_i, 4] tensor, where num_points_i is the number of
# sampled points for instance i.
unpadded_tensor = tf.stack([y, x, v, u], axis=1)
return shape_utils.pad_or_clip_nd(
unpadded_tensor, output_shape=[max_points_per_instance, 4])
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.
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 = tensor_dict[
fields.InputDataFields.image_additional_channels].shape[2].value
# 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 = tensor_dict[fields.InputDataFields.image].shape[2].value
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
tensor_dict[fields.InputDataFields.original_image].shape[2].value ==
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, tensor_dict[fields.InputDataFields.
original_image].shape[2].value
]
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