def parse_single_example(serialized_example, params):
"""Parses a singel serialized TFExample string."""
if 'retinanet_parser' in dir(params):
parser_params = params.retinanet_parser
decoder = tf_example_decoder.TfExampleDecoder()
else:
parser_params = params.maskrcnn_parser
decoder = tf_example_decoder.TfExampleDecoder(include_mask=True)
data = decoder.decode(serialized_example)
image = data['image']
source_id = data['source_id']
source_id = dataloader_utils.process_source_id(source_id)
height = data['height']
width = data['width']
boxes = data['groundtruth_boxes']
boxes = box_utils.denormalize_boxes(boxes, tf.shape(image)[:2])
classes = data['groundtruth_classes']
is_crowds = data['groundtruth_is_crowd']
areas = data['groundtruth_area']
masks = data.get('groundtruth_instance_masks_png', None)
image = input_utils.normalize_image(image)
image, image_info = input_utils.resize_and_crop_image(
image,
parser_params.output_size,
padded_size=input_utils.compute_padded_size(
parser_params.output_size,
2 ** params.architecture.max_level),
aug_scale_min=1.0,
aug_scale_max=1.0)
labels = {
'image_info': image_info,
}
groundtruths = {
'source_id': source_id,
'height': height,
'width': width,
'num_detections': tf.shape(classes),
'boxes': boxes,
'classes': classes,
'areas': areas,
'is_crowds': tf.cast(is_crowds, tf.int32),
}
if masks is not None:
groundtruths['masks'] = masks
return image, labels, groundtruths
def parse_single_example(serialized_example, params):
"""Parses a singel serialized TFExample string."""
decoder = tf_example_decoder.TfExampleDecoder()
data = decoder.decode(serialized_example)
image = data['image']
source_id = data['source_id']
source_id = dataloader_utils.process_source_id(source_id)
height = data['height']
width = data['width']
boxes = data['groundtruth_boxes']
boxes = box_utils.denormalize_boxes(boxes, tf.shape(image)[:2])
classes = data['groundtruth_classes']
is_crowds = data['groundtruth_is_crowd']
areas = data['groundtruth_area']
image = input_utils.normalize_image(image)
image, image_info = input_utils.resize_and_crop_image(
image,
params.retinanet_parser.output_size,
padded_size=input_utils.compute_padded_size(
params.retinanet_parser.output_size, 2**params.anchor.max_level),
aug_scale_min=1.0,
aug_scale_max=1.0)
anchors = anchor.Anchor(params.anchor.min_level, params.anchor.max_level,
params.anchor.num_scales,
params.anchor.aspect_ratios,
params.anchor.anchor_size,
image.get_shape().as_list()[:2])
labels = {
'anchor_boxes': anchors.multilevel_boxes,
'image_info': image_info,
}
groundtruths = {
'source_id': source_id,
'height': height,
'width': width,
'num_detections': tf.shape(classes),
'boxes': boxes,
'classes': classes,
'areas': areas,
'is_crowds': tf.cast(is_crowds, tf.int32),
}
return image, labels, groundtruths
def _parse_predict_data(self, data):
"""Parses data for prediction."""
# Gets original image and its size.
image = data['image']
image_shape = tf.shape(image)[0:2]
# Normalizes image with mean and std pixel values.
image = input_utils.normalize_image(image)
# Resizes and crops image.
image, image_info = input_utils.resize_and_crop_image(
image,
self._output_size,
padded_size=input_utils.compute_padded_size(
self._output_size, 2**self._max_level),
aug_scale_min=1.0,
aug_scale_max=1.0)
image_height, image_width, _ = image.get_shape().as_list()
# If bfloat16 is used, casts input image to tf.bfloat16.
if self._use_bfloat16:
image = tf.cast(image, dtype=tf.bfloat16)
# Compute Anchor boxes.
input_anchor = anchor.Anchor(self._min_level, self._max_level,
self._num_scales, self._aspect_ratios,
self._anchor_size,
(image_height, image_width))
labels = {
'anchor_boxes': input_anchor.multilevel_boxes,
'image_info': image_info,
}
# If mode is PREDICT_WITH_GT, returns groundtruths and training targets
# in labels.
if self._mode == ModeKeys.PREDICT_WITH_GT:
# Converts boxes from normalized coordinates to pixel coordinates.
boxes = box_utils.denormalize_boxes(data['groundtruth_boxes'],
image_shape)
groundtruths = {
'source_id': data['source_id'],
'height': data['height'],
'width': data['width'],
'num_detections': tf.shape(data['groundtruth_classes']),
'boxes': boxes,
'classes': data['groundtruth_classes'],
'areas': data['groundtruth_area'],
'is_crowds': tf.cast(data['groundtruth_is_crowd'], tf.int32),
}
groundtruths['source_id'] = dataloader_utils.process_source_id(
groundtruths['source_id'])
groundtruths = dataloader_utils.pad_groundtruths_to_fixed_size(
groundtruths, self._max_num_instances)
labels['groundtruths'] = groundtruths
# Computes training objective for evaluation loss.
classes = data['groundtruth_classes']
image_scale = image_info[2, :]
offset = image_info[3, :]
boxes = input_utils.resize_and_crop_boxes(
boxes, image_scale, (image_height, image_width), offset)
# Filters out ground truth boxes that are all zeros.
indices = box_utils.get_non_empty_box_indices(boxes)
boxes = tf.gather(boxes, indices)
classes = tf.gather(classes, indices)
# Assigns anchors.
anchor_labeler = anchor.AnchorLabeler(input_anchor,
self._match_threshold,
self._unmatched_threshold)
(cls_targets, box_targets,
num_positives) = anchor_labeler.label_anchors(
boxes, tf.cast(tf.expand_dims(classes, axis=1), tf.float32))
labels['cls_targets'] = cls_targets
labels['box_targets'] = box_targets
labels['num_positives'] = num_positives
return {
'images': image,
'labels': labels,
}
def _parse_predict_data(self, data):
"""Parses data for prediction.
Args:
data: the decoded tensor dictionary from TfExampleDecoder.
Returns:
A dictionary of {'images': image, 'labels': labels} where
images: image tensor that is preproessed to have normalized value and
dimension [output_size[0], output_size[1], 3]
labels: a dictionary of tensors used for training. The following
describes {key: value} pairs in the dictionary.
source_ids: Source image id. Default value -1 if the source id is
empty in the groundtruth annotation.
image_info: a 2D `Tensor` that encodes the information of the image
and the applied preprocessing. It is in the format of
[[original_height, original_width], [scaled_height, scaled_width],
anchor_boxes: ordered dictionary with keys
[min_level, min_level+1, ..., max_level]. The values are tensor with
shape [height_l, width_l, 4] representing anchor boxes at each
level.
"""
# Gets original image and its size.
image = data['image']
image_shape = tf.shape(image)[0:2]
# Normalizes image with mean and std pixel values.
image = input_utils.normalize_image(image)
# Resizes and crops image.
image, image_info = input_utils.resize_and_crop_image(
image,
self._output_size,
padded_size=input_utils.compute_padded_size(
self._output_size, 2**self._max_level),
aug_scale_min=1.0,
aug_scale_max=1.0)
image_height, image_width, _ = image.get_shape().as_list()
# If bfloat16 is used, casts input image to tf.bfloat16.
if self._use_bfloat16:
image = tf.cast(image, dtype=tf.bfloat16)
# Compute Anchor boxes.
input_anchor = anchor.Anchor(self._min_level, self._max_level,
self._num_scales, self._aspect_ratios,
self._anchor_size,
(image_height, image_width))
labels = {
'source_id': dataloader_utils.process_source_id(data['source_id']),
'anchor_boxes': input_anchor.multilevel_boxes,
'image_info': image_info,
}
if self._mode == ModeKeys.PREDICT_WITH_GT:
# Converts boxes from normalized coordinates to pixel coordinates.
boxes = box_utils.denormalize_boxes(data['groundtruth_boxes'],
image_shape)
groundtruths = {
'source_id': data['source_id'],
'height': data['height'],
'width': data['width'],
'num_detections': tf.shape(data['groundtruth_classes']),
'boxes': boxes,
'classes': data['groundtruth_classes'],
'areas': data['groundtruth_area'],
'is_crowds': tf.cast(data['groundtruth_is_crowd'], tf.int32),
}
groundtruths['source_id'] = dataloader_utils.process_source_id(
groundtruths['source_id'])
groundtruths = dataloader_utils.pad_groundtruths_to_fixed_size(
groundtruths, self._max_num_instances)
labels['groundtruths'] = groundtruths
return {
'images': image,
'labels': labels,
}
def _parse_eval_data(self, data):
"""Parses data for evaluation.
Args:
data: the decoded tensor dictionary from TfExampleDecoder.
Returns:
image: image tensor that is preproessed to have normalized value and
dimension [output_size[0], output_size[1], 3]
labels: a dictionary of tensors used for training. The following describes
{key: value} pairs in the dictionary.
image_info: a 2D `Tensor` that encodes the information of the image and
the applied preprocessing. It is in the format of
[[original_height, original_width], [scaled_height, scaled_width],
anchor_boxes: ordered dictionary with keys
[min_level, min_level+1, ..., max_level]. The values are tensor with
shape [height_l, width_l, 4] representing anchor boxes at each level.
groundtruths:
source_id: Groundtruth source id.
height: Original image height.
width: Original image width.
boxes: Groundtruth bounding box annotations. The box is represented
in [y1, x1, y2, x2] format. The coordinates are w.r.t the scaled
image that is fed to the network. The tennsor is padded with -1 to
the fixed dimension [self._max_num_instances, 4].
classes: Groundtruth classes annotations. The tennsor is padded
with -1 to the fixed dimension [self._max_num_instances].
areas: Box area or mask area depend on whether mask is present.
is_crowds: Whether the ground truth label is a crowd label.
num_groundtruths: Number of ground truths in the image.
"""
# Gets original image and its size.
image = data['image']
image_shape = tf.shape(image)[0:2]
# Normalizes image with mean and std pixel values.
image = input_utils.normalize_image(image)
# Resizes and crops image.
image, image_info = input_utils.resize_and_crop_image(
image,
self._output_size,
padded_size=input_utils.compute_padded_size(
self._output_size, 2**self._max_level),
aug_scale_min=1.0,
aug_scale_max=1.0)
image_height, image_width, _ = image.get_shape().as_list()
# Assigns anchor targets.
input_anchor = anchor.Anchor(self._min_level, self._max_level,
self._num_scales, self._aspect_ratios,
self._anchor_size,
(image_height, image_width))
# If bfloat16 is used, casts input image to tf.bfloat16.
if self._use_bfloat16:
image = tf.cast(image, dtype=tf.bfloat16)
# Sets up groundtruth data for evaluation.
groundtruths = {
'source_id':
data['source_id'],
'height':
data['height'],
'width':
data['width'],
'num_groundtruths':
tf.shape(data['groundtruth_classes']),
'boxes':
box_utils.denormalize_boxes(data['groundtruth_boxes'],
image_shape),
'classes':
data['groundtruth_classes'],
'areas':
data['groundtruth_area'],
'is_crowds':
tf.cast(data['groundtruth_is_crowd'], tf.int32),
}
# TODO(b/143766089): Add ground truth masks for segmentation metrics.
groundtruths['source_id'] = dataloader_utils.process_source_id(
groundtruths['source_id'])
groundtruths = dataloader_utils.pad_groundtruths_to_fixed_size(
groundtruths, self._max_num_instances)
# Packs labels for model_fn outputs.
labels = {
'anchor_boxes': input_anchor.multilevel_boxes,
'image_info': image_info,
'groundtruths': groundtruths,
}
return image, labels
def parse_predict_data(self, data):
"""Parse data for ShapeMask training."""
classes = data['groundtruth_classes']
boxes = data['groundtruth_boxes']
masks = data['groundtruth_instance_masks']
# If not using category, makes all categories with id = 0.
if not self._use_category:
classes = tf.cast(tf.greater(classes, 0), dtype=tf.float32)
image = self.get_normalized_image(data)
# Converts boxes from normalized coordinates to pixel coordinates.
image_shape = tf.shape(image)[0:2]
boxes = box_utils.denormalize_boxes(boxes, image_shape)
# Resizes and crops image.
image, image_info = input_utils.resize_and_crop_image(
image,
self._output_size,
self._output_size,
aug_scale_min=1.0,
aug_scale_max=1.0)
image_scale = image_info[2, :]
offset = image_info[3, :]
# Resizes and crops boxes and masks.
boxes = input_utils.resize_and_crop_boxes(boxes, image_scale,
image_info[1, :], offset)
masks = input_utils.resize_and_crop_masks(
tf.expand_dims(masks, axis=-1), image_scale, self._output_size,
offset)
# Filters out ground truth boxes that are all zeros.
indices = box_utils.get_non_empty_box_indices(boxes)
boxes = tf.gather(boxes, indices)
classes = tf.gather(classes, indices)
# Assigns anchors.
input_anchor = anchor.Anchor(self._min_level, self._max_level,
self._num_scales, self._aspect_ratios,
self._anchor_size, self._output_size)
anchor_labeler = anchor.AnchorLabeler(input_anchor,
self._match_threshold,
self._unmatched_threshold)
# If bfloat16 is used, casts input image to tf.bfloat16.
if self._use_bfloat16:
image = tf.cast(image, dtype=tf.bfloat16)
labels = {
'anchor_boxes': input_anchor.multilevel_boxes,
'image_info': image_info,
}
if self._mode == ModeKeys.PREDICT_WITH_GT:
# Converts boxes from normalized coordinates to pixel coordinates.
groundtruths = {
'source_id':
data['source_id'],
'height':
data['height'],
'width':
data['width'],
'num_detections':
tf.shape(data['groundtruth_classes']),
'boxes':
box_utils.denormalize_boxes(data['groundtruth_boxes'],
image_shape),
'classes':
data['groundtruth_classes'],
# 'masks': tf.squeeze(masks, axis=-1),
'areas':
data['groundtruth_area'],
'is_crowds':
tf.cast(data['groundtruth_is_crowd'], tf.int32),
}
groundtruths['source_id'] = dataloader_utils.process_source_id(
groundtruths['source_id'])
groundtruths = dataloader_utils.pad_groundtruths_to_fixed_size(
groundtruths, self._max_num_instances)
# Computes training labels.
(cls_targets, box_targets,
num_positives) = anchor_labeler.label_anchors(
boxes, tf.cast(tf.expand_dims(classes, axis=1), tf.float32))
# Packs labels for model_fn outputs.
labels.update({
'cls_targets': cls_targets,
'box_targets': box_targets,
'num_positives': num_positives,
'groundtruths': groundtruths,
})
return {
'images': image,
'labels': labels,
}
