def _parse_eval_data(self, data):
"""Parses data for training and evaluation."""
image, label = self._prepare_image_and_label(data)
# The label is first offset by +1 and then padded with 0.
label += 1
label = tf.expand_dims(label, axis=3)
if self._resize_eval:
# Resizes and crops image.
image, image_info = input_utils.resize_and_crop_image(
image, self._output_size, self._output_size)
# Resizes and crops mask.
image_scale = image_info[2, :]
offset = image_info[3, :]
label = input_utils.resize_and_crop_masks(label, image_scale,
self._output_size, offset)
else:
# Pads image and mask to output size.
image = tf.image.pad_to_bounding_box(image, 0, 0, self._output_size[0],
self._output_size[1])
label = tf.image.pad_to_bounding_box(label, 0, 0, self._output_size[0],
self._output_size[1])
label -= 1
label = tf.where(tf.equal(label, -1),
self._ignore_label * tf.ones_like(label), label)
label = tf.squeeze(label, axis=0)
valid_mask = tf.not_equal(label, self._ignore_label)
labels = {
'masks': label,
'valid_masks': valid_mask
}
# If bfloat16 is used, casts input image to tf.bfloat16.
if self._use_bfloat16:
image = tf.cast(image, dtype=tf.bfloat16)
return image, labels
def _parse_train_data(self, data):
"""Parses data for training and evaluation."""
image, label = self._prepare_image_and_label(data)
# Flips image randomly during training.
if self._aug_rand_hflip:
image, label = input_utils.random_horizontal_flip(image, masks=label)
# Resizes and crops image.
image, image_info = input_utils.resize_and_crop_image(
image,
self._output_size,
self._output_size,
aug_scale_min=self._aug_scale_min,
aug_scale_max=self._aug_scale_max)
# Resizes and crops boxes.
image_scale = image_info[2, :]
offset = image_info[3, :]
# Pad label and make sure the padded region assigned to the ignore label.
# The label is first offset by +1 and then padded with 0.
label += 1
label = tf.expand_dims(label, axis=3)
label = input_utils.resize_and_crop_masks(
label, image_scale, self._output_size, offset)
label -= 1
label = tf.where(tf.equal(label, -1),
self._ignore_label * tf.ones_like(label), label)
label = tf.squeeze(label, axis=0)
valid_mask = tf.not_equal(label, self._ignore_label)
labels = {
'masks': label,
'valid_masks': valid_mask
}
# If bfloat16 is used, casts input image to tf.bfloat16.
if self._use_bfloat16:
image = tf.cast(image, dtype=tf.bfloat16)
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,
}
def _parse_train_data(self, data):
"""Parses data for training.
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: image tensor that is preproessed to have normalized value and
dimension [output_size[0], output_size[1], 3]
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],
num_groundtrtuhs: number of objects.
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].
masks: groundtrugh masks cropped by the bounding box and
resized to a fixed size determined by mask_crop_size.
pasted_objects_mask: a binary tensor with the same size as image which
is computed as the union of all the objects masks.
"""
classes = data['groundtruth_classes']
boxes = data['groundtruth_boxes']
if self._include_mask:
masks = data['groundtruth_instance_masks']
is_crowds = data['groundtruth_is_crowd']
# Skips annotations with `is_crowd` = True.
if self._skip_crowd_during_training:
num_groundtrtuhs = tf.shape(classes)[0]
with tf.control_dependencies([num_groundtrtuhs, is_crowds]):
indices = tf.cond(
tf.greater(tf.size(is_crowds), 0),
lambda: tf.where(tf.logical_not(is_crowds))[:, 0],
lambda: tf.cast(tf.range(num_groundtrtuhs), tf.int64))
classes = tf.gather(classes, indices)
boxes = tf.gather(boxes, indices)
if self._include_mask:
masks = tf.gather(masks, indices)
# 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)
# Flips image randomly during training.
if self._aug_rand_hflip:
if self._include_mask:
image, boxes, masks = input_utils.random_horizontal_flip(
image, boxes, masks)
else:
image, boxes = input_utils.random_horizontal_flip(image, boxes)
# Converts boxes from normalized coordinates to pixel coordinates.
# Now the coordinates of boxes are w.r.t. the original image.
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,
padded_size=input_utils.compute_padded_size(
self._output_size, 2**self._max_level),
aug_scale_min=self._aug_scale_min,
aug_scale_max=self._aug_scale_max)
# Resizes and crops boxes.
# Now the coordinates of boxes are w.r.t the scaled image.
image_scale = image_info[2, :]
offset = image_info[3, :]
boxes = input_utils.resize_and_crop_boxes(boxes, image_scale,
image_info[1, :], 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)
if self._include_mask:
masks = tf.gather(masks, indices)
uncropped_masks = tf.cast(masks, tf.int8)
uncropped_masks = tf.expand_dims(uncropped_masks, axis=3)
uncropped_masks = input_utils.resize_and_crop_masks(
uncropped_masks, image_scale, self._output_size, offset)
# Transfer boxes to the original image space and do normalization.
cropped_boxes = boxes + tf.tile(tf.expand_dims(offset, axis=0),
[1, 2])
cropped_boxes /= tf.tile(tf.expand_dims(image_scale, axis=0),
[1, 2])
cropped_boxes = box_utils.normalize_boxes(cropped_boxes,
image_shape)
num_masks = tf.shape(masks)[0]
masks = tf.image.crop_and_resize(
tf.expand_dims(masks, axis=-1),
cropped_boxes,
box_indices=tf.range(num_masks, dtype=tf.int32),
crop_size=[self._mask_crop_size, self._mask_crop_size],
method='bilinear')
masks = tf.squeeze(masks, axis=-1)
indices = tf.range(start=0, limit=tf.shape(classes)[0], dtype=tf.int32)
# Samples the numbers of masks for pasting.
m = tf.random.uniform(shape=[],
maxval=tf.shape(classes)[0] + 1,
dtype=tf.int32)
m = tf.math.minimum(m, tf.shape(classes)[0])
# Shuffles the indices of objects and keep the first m objects for pasting.
shuffled_indices = tf.random.shuffle(indices)
shuffled_indices = tf.slice(shuffled_indices, [0], [m])
boxes = tf.gather(boxes, shuffled_indices)
masks = tf.gather(masks, shuffled_indices)
classes = tf.gather(classes, shuffled_indices)
uncropped_masks = tf.gather(uncropped_masks, shuffled_indices)
pasted_objects_mask = tf.reduce_max(uncropped_masks, 0)
pasted_objects_mask = tf.cast(pasted_objects_mask, tf.bool)
labels = {
'image': image,
'image_info': image_info,
'num_groundtrtuhs': tf.shape(classes)[0],
'boxes': boxes,
'masks': masks,
'classes': classes,
'pasted_objects_mask': pasted_objects_mask,
}
return labels
def _parse_train_data(self, data):
"""Parses data for training.
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.
rpn_score_targets: ordered dictionary with keys
[min_level, min_level+1, ..., max_level]. The values are tensor with
shape [height_l, width_l, anchors_per_location]. The height_l and
width_l represent the dimension of class logits at l-th level.
rpn_box_targets: ordered dictionary with keys
[min_level, min_level+1, ..., max_level]. The values are tensor with
shape [height_l, width_l, anchors_per_location * 4]. The height_l and
width_l represent the dimension of bounding box regression output at
l-th level.
gt_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].
gt_classes: Groundtruth classes annotations. The tennsor is padded
with -1 to the fixed dimension [self._max_num_instances].
gt_masks: groundtrugh masks cropped by the bounding box and
resized to a fixed size determined by mask_crop_size.
"""
classes = data['groundtruth_classes']
boxes = data['groundtruth_boxes']
if self._include_mask:
masks = data['groundtruth_instance_masks']
is_crowds = data['groundtruth_is_crowd']
# Skips annotations with `is_crowd` = True.
if self._skip_crowd_during_training and self._is_training:
num_groundtrtuhs = tf.shape(classes)[0]
with tf.control_dependencies([num_groundtrtuhs, is_crowds]):
indices = tf.cond(
tf.greater(tf.size(is_crowds), 0),
lambda: tf.where(tf.logical_not(is_crowds))[:, 0],
lambda: tf.cast(tf.range(num_groundtrtuhs), tf.int64))
classes = tf.gather(classes, indices)
boxes = tf.gather(boxes, indices)
if self._include_mask:
masks = tf.gather(masks, indices)
# 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)
# Flips image randomly during training.
if self._aug_rand_hflip:
if self._include_mask:
image, boxes, masks = input_utils.random_horizontal_flip(
image, boxes, masks)
else:
image, boxes = input_utils.random_horizontal_flip(image, boxes)
# Converts boxes from normalized coordinates to pixel coordinates.
# Now the coordinates of boxes are w.r.t. the original image.
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,
padded_size=input_utils.compute_padded_size(
self._output_size, 2**self._max_level),
aug_scale_min=self._aug_scale_min,
aug_scale_max=self._aug_scale_max)
image_height, image_width, _ = image.get_shape().as_list()
# Resizes and crops boxes.
# Now the coordinates of boxes are w.r.t the scaled image.
image_scale = image_info[2, :]
offset = image_info[3, :]
boxes = input_utils.resize_and_crop_boxes(boxes, image_scale,
(image_height, image_width),
offset)
if self._include_mask:
masks = input_utils.resize_and_crop_masks(
tf.expand_dims(masks, axis=-1), image_scale,
(image_height, image_width), offset)
masks = tf.squeeze(masks, axis=-1)
# Filters out ground truth boxes that are all zeros.
indices = input_utils.get_non_empty_box_indices(boxes)
boxes = tf.gather(boxes, indices)
classes = tf.gather(classes, indices)
if self._include_mask:
masks = tf.gather(masks, indices)
num_masks = tf.shape(masks)[0]
masks = tf.image.crop_and_resize(
tf.expand_dims(masks, axis=-1),
box_utils.normalize_boxes(boxes,
tf.shape(image)[0:2]),
box_ind=tf.range(num_masks, dtype=tf.int32),
crop_size=[self._mask_crop_size, self._mask_crop_size],
method='bilinear')
masks = tf.squeeze(masks, axis=-1)
# Assigns anchor targets.
# Note that after the target assignment, box targets are absolute pixel
# offsets w.r.t. the scaled image.
input_anchor = anchor.Anchor(self._min_level, self._max_level,
self._num_scales, self._aspect_ratios,
self._anchor_size,
(image_height, image_width))
anchor_labeler = anchor.RpnAnchorLabeler(input_anchor,
self._rpn_match_threshold,
self._rpn_unmatched_threshold,
self._rpn_batch_size_per_im,
self._rpn_fg_fraction)
rpn_score_targets, rpn_box_targets = anchor_labeler.label_anchors(
boxes, tf.cast(tf.expand_dims(classes, axis=-1), dtype=tf.float32))
# If bfloat16 is used, casts input image to tf.bfloat16.
if self._use_bfloat16:
image = tf.cast(image, dtype=tf.bfloat16)
# Packs labels for model_fn outputs.
labels = {
'anchor_boxes': input_anchor.multilevel_boxes,
'image_info': image_info,
'rpn_score_targets': rpn_score_targets,
'rpn_box_targets': rpn_box_targets,
}
labels['gt_boxes'] = input_utils.pad_to_fixed_size(
boxes, self._max_num_instances, -1)
labels['gt_classes'] = input_utils.pad_to_fixed_size(
classes, self._max_num_instances, -1)
if self._include_mask:
labels['gt_masks'] = input_utils.pad_to_fixed_size(
masks, self._max_num_instances, -1)
return image, labels
def _parse_train_data(self, data):
"""Parse data for ShapeMask training."""
classes = data['groundtruth_classes']
boxes = data['groundtruth_boxes']
masks = data['groundtruth_instance_masks']
is_crowds = data['groundtruth_is_crowd']
# Skips annotations with `is_crowd` = True.
if self._skip_crowd_during_training and self._is_training:
num_groundtrtuhs = tf.shape(classes)[0]
with tf.control_dependencies([num_groundtrtuhs, is_crowds]):
indices = tf.cond(
tf.greater(tf.size(is_crowds), 0),
lambda: tf.where(tf.logical_not(is_crowds))[:, 0],
lambda: tf.cast(tf.range(num_groundtrtuhs), tf.int64))
classes = tf.gather(classes, indices)
boxes = tf.gather(boxes, indices)
masks = tf.gather(masks, indices)
# Gets original image and its size.
image = data['image']
image_shape = tf.shape(image)[0:2]
# 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)
# Normalizes image with mean and std pixel values.
image = input_utils.normalize_image(image)
# Flips image randomly during training.
if self._aug_rand_hflip:
image, boxes, masks = input_utils.random_horizontal_flip(
image, boxes, masks)
# Converts boxes from normalized coordinates to pixel coordinates.
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=self._aug_scale_min,
aug_scale_max=self._aug_scale_max)
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, self._output_size, offset)
masks = input_utils.resize_and_crop_masks(
tf.expand_dims(masks, axis=-1), image_scale, self._output_size, offset)
masks = tf.squeeze(masks, axis=-1)
# Filters out ground truth boxes that are all zeros.
indices = input_utils.get_non_empty_box_indices(boxes)
boxes = tf.gather(boxes, indices)
classes = tf.gather(classes, indices)
masks = tf.gather(masks, 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)
(cls_targets,
box_targets,
num_positives) = anchor_labeler.label_anchors(
boxes,
tf.cast(tf.expand_dims(classes, axis=1), tf.float32))
# Sample groundtruth masks/boxes/classes for mask branch.
num_masks = tf.shape(masks)[0]
mask_shape = tf.shape(masks)[1:3]
# Pad sampled boxes/masks/classes to a constant batch size.
padded_boxes = input_utils.pad_to_fixed_size(boxes, self._num_sampled_masks)
padded_classes = input_utils.pad_to_fixed_size(
classes, self._num_sampled_masks)
padded_masks = input_utils.pad_to_fixed_size(masks, self._num_sampled_masks)
# Randomly sample groundtruth masks for mask branch training. For the image
# without groundtruth masks, it will sample the dummy padded tensors.
rand_indices = tf.random.uniform(
[self._num_sampled_masks],
minval=0,
maxval=tf.maximum(num_masks, 1),
dtype=tf.dtypes.int32)
sampled_boxes = tf.gather(padded_boxes, rand_indices)
sampled_classes = tf.gather(padded_classes, rand_indices)
sampled_masks = tf.gather(padded_masks, rand_indices)
# Jitter the sampled boxes to mimic the noisy detections.
sampled_boxes = box_utils.jitter_boxes(
sampled_boxes, noise_scale=self._box_jitter_scale)
# Compute mask targets in feature crop. A feature crop fully contains a
# sampled box.
mask_outer_boxes = box_utils.compute_outer_boxes(
sampled_boxes, mask_shape, scale=self._outer_box_scale)
norm_mask_outer_boxes = box_utils.normalize_boxes(
mask_outer_boxes, mask_shape)
# Set sampled_masks shape to [batch_size, height, width, 1].
sampled_masks = tf.expand_dims(sampled_masks, axis=-1)
mask_targets = tf.image.crop_and_resize(
sampled_masks,
norm_mask_outer_boxes,
box_ind=tf.range(self._num_sampled_masks),
crop_size=[self._mask_crop_size, self._mask_crop_size],
method='bilinear',
extrapolation_value=0,
name='train_mask_targets')
mask_targets = tf.where(tf.greater_equal(mask_targets, 0.5),
tf.ones_like(mask_targets),
tf.zeros_like(mask_targets))
mask_targets = tf.squeeze(mask_targets, axis=-1)
# If bfloat16 is used, casts input image to tf.bfloat16.
if self._use_bfloat16:
image = tf.cast(image, dtype=tf.bfloat16)
# Packs labels for model_fn outputs.
labels = {
'cls_targets': cls_targets,
'box_targets': box_targets,
'anchor_boxes': input_anchor.multilevel_boxes,
'num_positives': num_positives,
'image_info': image_info,
# For ShapeMask.
'mask_boxes': sampled_boxes,
'mask_outer_boxes': mask_outer_boxes,
'mask_targets': mask_targets,
'mask_classes': sampled_classes,
'mask_is_valid': tf.cast(tf.not_equal(num_masks, 0), tf.int32)
}
return image, labels
