def test_autoaugment_policy(self):
# A very simple test to verify no syntax error.
image = tf.placeholder(tf.uint8, shape=[640, 640, 3])
bboxes = tf.placeholder(tf.float32, shape=[4, 4])
autoaugment.distort_image_with_autoaugment(image, bboxes, 'test')
autoaugment.distort_image_with_autoaugment(
image, bboxes, 'test', use_augmix=True)
def _common_image_process(self, image, classes, boxes, data, params):
# Training time preprocessing.
if params['skip_crowd_during_training']:
indices = tf.where(tf.logical_not(data['groundtruth_is_crowd']))
classes = tf.gather_nd(classes, indices)
boxes = tf.gather_nd(boxes, indices)
if params.get('grid_mask', None):
from aug import gridmask # pylint: disable=g-import-not-at-top
image, boxes = gridmask.gridmask(image, boxes)
if params.get('autoaugment_policy', None):
from aug import autoaugment # pylint: disable=g-import-not-at-top
if params['autoaugment_policy'] == 'randaug':
image, boxes = autoaugment.distort_image_with_randaugment(
image, boxes, num_layers=1, magnitude=15)
else:
image, boxes = autoaugment.distort_image_with_autoaugment(
image, boxes, params['autoaugment_policy'])
return image, boxes, classes
def _dataset_parser(value):
"""Parse data to a fixed dimension input image and learning targets.
Args:
value: A dictionary contains an image and groundtruth annotations.
Returns:
image: Image tensor that is preprocessed to have normalized value and
fixed dimension [image_height, image_width, 3]
cls_targets_dict: ordered dictionary with keys
[min_level, min_level+1, ..., max_level]. The values are tensor with
shape [height_l, width_l, num_anchors]. The height_l and width_l
represent the dimension of class logits at l-th level.
box_targets_dict: ordered dictionary with keys
[min_level, min_level+1, ..., max_level]. The values are tensor with
shape [height_l, width_l, num_anchors * 4]. The height_l and
width_l represent the dimension of bounding box regression output at
l-th level.
num_positives: Number of positive anchors in the image.
source_id: Source image id. Default value -1 if the source id is empty
in the groundtruth annotation.
image_scale: Scale of the processed image to the original image.
boxes: Groundtruth bounding box annotations. The box is represented in
[y1, x1, y2, x2] format. The tensor is padded with -1 to the fixed
dimension [self._max_instances_per_image, 4].
is_crowds: Groundtruth annotations to indicate if an annotation
represents a group of instances by value {0, 1}. The tensor is
padded with 0 to the fixed dimension [self._max_instances_per_image].
areas: Groundtruth areas annotations. The tensor is padded with -1
to the fixed dimension [self._max_instances_per_image].
classes: Groundtruth classes annotations. The tensor is padded with -1
to the fixed dimension [self._max_instances_per_image].
"""
with tf.name_scope('parser'):
data = example_decoder.decode(value)
source_id = data['source_id']
image = data['image']
boxes = data['groundtruth_boxes']
classes = data['groundtruth_classes']
classes = tf.reshape(tf.cast(classes, dtype=tf.float32),
[-1, 1])
areas = data['groundtruth_area']
is_crowds = data['groundtruth_is_crowd']
classes = tf.reshape(tf.cast(classes, dtype=tf.float32),
[-1, 1])
if params['skip_crowd_during_training'] and self._is_training:
indices = tf.where(
tf.logical_not(data['groundtruth_is_crowd']))
classes = tf.gather_nd(classes, indices)
boxes = tf.gather_nd(boxes, indices)
# NOTE: The autoaugment method works best when used alongside the
# standard horizontal flipping of images along with size jittering
# and normalization.
if params.get('autoaugment_policy',
None) and self._is_training:
from aug import autoaugment # pylint: disable=g-import-not-at-top
image, boxes = autoaugment.distort_image_with_autoaugment(
image, boxes, params['autoaugment_policy'],
params['use_augmix'], *params['augmix_params'])
input_processor = DetectionInputProcessor(
image, params['image_size'], boxes, classes)
input_processor.normalize_image()
if self._is_training and params['input_rand_hflip']:
input_processor.random_horizontal_flip()
if self._is_training:
input_processor.set_training_random_scale_factors(
params['train_scale_min'], params['train_scale_max'],
params.get('target_size', None))
else:
input_processor.set_scale_factors_to_output_size()
image = input_processor.resize_and_crop_image()
boxes, classes = input_processor.resize_and_crop_boxes()
# Assign anchors.
(cls_targets, box_targets,
num_positives) = anchor_labeler.label_anchors(boxes, classes)
source_id = tf.where(tf.equal(source_id, tf.constant('')),
'-1', source_id)
source_id = tf.string_to_number(source_id)
# Pad groundtruth data for evaluation.
image_scale = input_processor.image_scale_to_original
boxes *= image_scale
is_crowds = tf.cast(is_crowds, dtype=tf.float32)
boxes = pad_to_fixed_size(boxes, -1,
[self._max_instances_per_image, 4])
is_crowds = pad_to_fixed_size(
is_crowds, 0, [self._max_instances_per_image, 1])
areas = pad_to_fixed_size(areas, -1,
[self._max_instances_per_image, 1])
classes = pad_to_fixed_size(classes, -1,
[self._max_instances_per_image, 1])
return (image, cls_targets, box_targets, num_positives,
source_id, image_scale, boxes, is_crowds, areas,
classes)
def dataset_parser(self, value, example_decoder, anchor_labeler, params):
"""Parse data to a fixed dimension input image and learning targets.
Args:
value: a single serialized tf.Example string.
example_decoder: TF example decoder.
anchor_labeler: anchor box labeler.
params: a dict of extra parameters.
Returns:
image: Image tensor that is preprocessed to have normalized value and
fixed dimension [image_height, image_width, 3]
cls_targets_dict: ordered dictionary with keys
[min_level, min_level+1, ..., max_level]. The values are tensor with
shape [height_l, width_l, num_anchors]. The height_l and width_l
represent the dimension of class logits at l-th level.
box_targets_dict: ordered dictionary with keys
[min_level, min_level+1, ..., max_level]. The values are tensor with
shape [height_l, width_l, num_anchors * 4]. The height_l and
width_l represent the dimension of bounding box regression output at
l-th level.
num_positives: Number of positive anchors in the image.
source_id: Source image id. Default value -1 if the source id is empty
in the groundtruth annotation.
image_scale: Scale of the processed image to the original image.
boxes: Groundtruth bounding box annotations. The box is represented in
[y1, x1, y2, x2] format. The tensor is padded with -1 to the fixed
dimension [self._max_instances_per_image, 4].
is_crowds: Groundtruth annotations to indicate if an annotation
represents a group of instances by value {0, 1}. The tensor is
padded with 0 to the fixed dimension [self._max_instances_per_image].
areas: Groundtruth areas annotations. The tensor is padded with -1
to the fixed dimension [self._max_instances_per_image].
classes: Groundtruth classes annotations. The tensor is padded with -1
to the fixed dimension [self._max_instances_per_image].
"""
with tf.name_scope('parser'):
data = example_decoder.decode(value)
source_id = data['source_id']
image = data['image']
boxes = data['groundtruth_boxes']
classes = data['groundtruth_classes']
classes = tf.reshape(tf.cast(classes, dtype=tf.float32), [-1, 1])
areas = data['groundtruth_area']
is_crowds = data['groundtruth_is_crowd']
image_masks = data.get('groundtruth_instance_masks', [])
if self._is_training:
# Training time preprocessing.
if params['skip_crowd_during_training']:
indices = tf.where(
tf.logical_not(data['groundtruth_is_crowd']))
classes = tf.gather_nd(classes, indices)
boxes = tf.gather_nd(boxes, indices)
if params.get('grid_mask', None):
from aug import gridmask # pylint: disable=g-import-not-at-top
image, boxes = gridmask.gridmask(image, boxes)
if params.get('autoaugment_policy', None):
from aug import autoaugment # pylint: disable=g-import-not-at-top
if params['autoaugment_policy'] == 'randaug':
image, boxes = autoaugment.distort_image_with_randaugment(
image, boxes, num_layers=1, magnitude=15)
else:
image, boxes = autoaugment.distort_image_with_autoaugment(
image, boxes, params['autoaugment_policy'])
input_processor = DetectionInputProcessor(image,
params['image_size'],
boxes, classes)
input_processor.normalize_image()
if self._is_training:
if params['input_rand_hflip']:
input_processor.random_horizontal_flip()
input_processor.set_training_random_scale_factors(
params['jitter_min'], params['jitter_max'],
params.get('target_size', None))
else:
input_processor.set_scale_factors_to_output_size()
image = input_processor.resize_and_crop_image()
boxes, classes = input_processor.resize_and_crop_boxes()
# Assign anchors.
(cls_targets, box_targets,
num_positives) = anchor_labeler.label_anchors(boxes, classes)
source_id = tf.where(tf.equal(source_id, tf.constant('')), '-1',
source_id)
source_id = tf.strings.to_number(source_id)
# Pad groundtruth data for evaluation.
image_scale = input_processor.image_scale_to_original
boxes *= image_scale
is_crowds = tf.cast(is_crowds, dtype=tf.float32)
boxes = pad_to_fixed_size(boxes, -1,
[self._max_instances_per_image, 4])
is_crowds = pad_to_fixed_size(is_crowds, 0,
[self._max_instances_per_image, 1])
areas = pad_to_fixed_size(areas, -1,
[self._max_instances_per_image, 1])
classes = pad_to_fixed_size(classes, -1,
[self._max_instances_per_image, 1])
if params['mixed_precision']:
dtype = tf.keras.mixed_precision.global_policy().compute_dtype
image = tf.cast(image, dtype=dtype)
box_targets = tf.nest.map_structure(
lambda box_target: tf.cast(box_target, dtype=dtype),
box_targets)
return (image, cls_targets, box_targets, num_positives, source_id,
image_scale, boxes, is_crowds, areas, classes, image_masks)
