def testNoFlipWhenProbIsZero(self):
numpy_image = np.dstack([[[5., 6.], [9., 0.]], [[4., 3.], [3., 5.]]])
image = tf.convert_to_tensor(numpy_image)
with self.test_session():
actual, is_flipped = preprocess_utils.flip_dim([image],
prob=0,
dim=0)
self.assertAllEqual(numpy_image, actual.eval())
self.assertAllEqual(False, is_flipped.eval())
actual, is_flipped = preprocess_utils.flip_dim([image],
prob=0,
dim=1)
self.assertAllEqual(numpy_image, actual.eval())
self.assertAllEqual(False, is_flipped.eval())
actual, is_flipped = preprocess_utils.flip_dim([image],
prob=0,
dim=2)
self.assertAllEqual(numpy_image, actual.eval())
self.assertAllEqual(False, is_flipped.eval())
def testFlipWhenProbIsOne(self):
numpy_image = np.dstack([[[5., 6.], [9., 0.]], [[4., 3.], [3., 5.]]])
dim0_flipped = np.dstack([[[9., 0.], [5., 6.]], [[3., 5.], [4., 3.]]])
dim1_flipped = np.dstack([[[6., 5.], [0., 9.]], [[3., 4.], [5., 3.]]])
dim2_flipped = np.dstack([[[4., 3.], [3., 5.]], [[5., 6.], [9., 0.]]])
image = tf.convert_to_tensor(numpy_image)
with self.test_session():
actual, is_flipped = preprocess_utils.flip_dim([image],
prob=1,
dim=0)
self.assertAllEqual(dim0_flipped, actual.eval())
self.assertAllEqual(True, is_flipped.eval())
actual, is_flipped = preprocess_utils.flip_dim([image],
prob=1,
dim=1)
self.assertAllEqual(dim1_flipped, actual.eval())
self.assertAllEqual(True, is_flipped.eval())
actual, is_flipped = preprocess_utils.flip_dim([image],
prob=1,
dim=2)
self.assertAllEqual(dim2_flipped, actual.eval())
self.assertAllEqual(True, is_flipped.eval())
def testReturnRandomFlipsOnMultipleEvals(self):
numpy_image = np.dstack([[[5., 6.], [9., 0.]], [[4., 3.], [3., 5.]]])
dim1_flipped = np.dstack([[[6., 5.], [0., 9.]], [[3., 4.], [5., 3.]]])
image = tf.convert_to_tensor(numpy_image)
tf.set_random_seed(53)
with self.test_session() as sess:
actual, is_flipped = preprocess_utils.flip_dim([image],
prob=0.5,
dim=1)
actual_image, actual_is_flipped = sess.run([actual, is_flipped])
self.assertAllEqual(numpy_image, actual_image)
self.assertEqual(False, actual_is_flipped)
actual_image, actual_is_flipped = sess.run([actual, is_flipped])
self.assertAllEqual(dim1_flipped, actual_image)
self.assertEqual(True, actual_is_flipped)
def testFlipMultipleImagesConsistentlyWhenProbIsOne(self):
numpy_image = np.dstack([[[5., 6.], [9., 0.]], [[4., 3.], [3., 5.]]])
numpy_label = np.dstack([[[0., 1.], [2., 3.]]])
image_dim1_flipped = np.dstack([[[6., 5.], [0., 9.]],
[[3., 4.], [5., 3.]]])
label_dim1_flipped = np.dstack([[[1., 0.], [3., 2.]]])
image = tf.convert_to_tensor(numpy_image)
label = tf.convert_to_tensor(numpy_label)
with self.test_session() as sess:
image, label, is_flipped = preprocess_utils.flip_dim(
[image, label], prob=1, dim=1)
actual_image, actual_label = sess.run([image, label])
self.assertAllEqual(image_dim1_flipped, actual_image)
self.assertAllEqual(label_dim1_flipped, actual_label)
self.assertEqual(True, is_flipped.eval())
def preprocess_image_and_label(image,
label,
crop_height,
crop_width,
min_resize_value=None,
max_resize_value=None,
resize_factor=None,
min_scale_factor=1.,
max_scale_factor=1.,
scale_factor_step_size=0,
ignore_label=255,
is_training=True,
model_variant=None):
"""Preprocesses the image and label.
Args:
image: Input image.
label: Ground truth annotation label.
crop_height: The height value used to crop the image and label.
crop_width: The width value used to crop the image and label.
min_resize_value: Desired size of the smaller image side.
max_resize_value: Maximum allowed size of the larger image side.
resize_factor: Resized dimensions are multiple of factor plus one.
min_scale_factor: Minimum scale factor value.
max_scale_factor: Maximum scale factor value.
scale_factor_step_size: The step size from min scale factor to max scale
factor. The input is randomly scaled based on the value of
(min_scale_factor, max_scale_factor, scale_factor_step_size).
ignore_label: The label value which will be ignored for training and
evaluation.
is_training: If the preprocessing is used for training or not.
model_variant: Model variant (string) for choosing how to mean-subtract the
images. See feature_extractor.network_map for supported model variants.
Returns:
original_image: Original image (could be resized).
processed_image: Preprocessed image.
label: Preprocessed ground truth segmentation label.
Raises:
ValueError: Ground truth label not provided during training.
"""
if is_training and label is None:
raise ValueError('During training, label must be provided.')
if model_variant is None:
tf.logging.warning(
'Default mean-subtraction is performed. Please specify '
'a model_variant. See feature_extractor.network_map for '
'supported model variants.')
# Keep reference to original image.
original_image = image
processed_image = tf.cast(image, tf.float32)
if label is not None:
label = tf.cast(label, tf.int32)
# Resize image and label to the desired range.
if min_resize_value is not None or max_resize_value is not None:
[processed_image,
label] = (preprocess_utils.resize_to_range(image=processed_image,
label=label,
min_size=min_resize_value,
max_size=max_resize_value,
factor=resize_factor,
align_corners=True))
# The `original_image` becomes the resized image.
original_image = tf.identity(processed_image)
# Data augmentation by randomly scaling the inputs.
if is_training:
scale = preprocess_utils.get_random_scale(min_scale_factor,
max_scale_factor,
scale_factor_step_size)
processed_image, label = preprocess_utils.randomly_scale_image_and_label(
processed_image, label, scale)
processed_image.set_shape([None, None, 3])
# Pad image and label to have dimensions >= [crop_height, crop_width]
image_shape = tf.shape(processed_image)
image_height = image_shape[0]
image_width = image_shape[1]
target_height = image_height + tf.maximum(crop_height - image_height, 0)
target_width = image_width + tf.maximum(crop_width - image_width, 0)
# Pad image with mean pixel value.
mean_pixel = tf.reshape(feature_extractor.mean_pixel(model_variant),
[1, 1, 3])
processed_image = preprocess_utils.pad_to_bounding_box(
processed_image, 0, 0, target_height, target_width, mean_pixel)
if label is not None:
label = preprocess_utils.pad_to_bounding_box(label, 0, 0,
target_height,
target_width,
ignore_label)
# Randomly crop the image and label.
if is_training and label is not None:
processed_image, label = preprocess_utils.random_crop(
[processed_image, label], crop_height, crop_width)
processed_image.set_shape([crop_height, crop_width, 3])
if label is not None:
label.set_shape([crop_height, crop_width, 1])
if is_training:
# Randomly left-right flip the image and label.
processed_image, label, _ = preprocess_utils.flip_dim(
[processed_image, label], _PROB_OF_FLIP, dim=1)
return original_image, processed_image, label
def preprocess_image_and_label(image,
label,
crop_height,
crop_width,
min_resize_value=None,
max_resize_value=None,
resize_factor=None,
min_scale_factor=1.,
max_scale_factor=1.,
scale_factor_step_size=0,
ignore_label=255,
is_training=True,
model_variant=None):
"""Preprocesses the image and label.
Args:
image: Input image.
label: Ground truth annotation label.
crop_height: The height value used to crop the image and label.
crop_width: The width value used to crop the image and label.
min_resize_value: Desired size of the smaller image side.
max_resize_value: Maximum allowed size of the larger image side.
resize_factor: Resized dimensions are multiple of factor plus one.
min_scale_factor: Minimum scale factor value.
max_scale_factor: Maximum scale factor value.
scale_factor_step_size: The step size from min scale factor to max scale
factor. The input is randomly scaled based on the value of
(min_scale_factor, max_scale_factor, scale_factor_step_size).
ignore_label: The label value which will be ignored for training and
evaluation.
is_training: If the preprocessing is used for training or not.
model_variant: Model variant (string) for choosing how to mean-subtract the
images. See feature_extractor.network_map for supported model variants.
Returns:
original_image: Original image (could be resized).
processed_image: Preprocessed image.
label: Preprocessed ground truth segmentation label.
Raises:
ValueError: Ground truth label not provided during training.
"""
if is_training and label is None:
raise ValueError('During training, label must be provided.')
if model_variant is None:
tf.logging.warning('Default mean-subtraction is performed. Please specify '
'a model_variant. See feature_extractor.network_map for '
'supported model variants.')
# Keep reference to original image.
original_image = image
processed_image = tf.cast(image, tf.float32)
if label is not None:
label = tf.cast(label, tf.int32)
# Resize image and label to the desired range.
if min_resize_value is not None or max_resize_value is not None:
[processed_image, label] = (
preprocess_utils.resize_to_range(
image=processed_image,
label=label,
min_size=min_resize_value,
max_size=max_resize_value,
factor=resize_factor,
align_corners=True))
# The `original_image` becomes the resized image.
original_image = tf.identity(processed_image)
# Data augmentation by randomly scaling the inputs.
scale = preprocess_utils.get_random_scale(
min_scale_factor, max_scale_factor, scale_factor_step_size)
processed_image, label = preprocess_utils.randomly_scale_image_and_label(
processed_image, label, scale)
processed_image.set_shape([None, None, 3])
# Pad image and label to have dimensions >= [crop_height, crop_width]
image_shape = tf.shape(processed_image)
image_height = image_shape[0]
image_width = image_shape[1]
target_height = image_height + tf.maximum(crop_height - image_height, 0)
target_width = image_width + tf.maximum(crop_width - image_width, 0)
# Pad image with mean pixel value.
mean_pixel = tf.reshape(
feature_extractor.mean_pixel(model_variant), [1, 1, 3])
processed_image = preprocess_utils.pad_to_bounding_box(
processed_image, 0, 0, target_height, target_width, mean_pixel)
if label is not None:
label = preprocess_utils.pad_to_bounding_box(
label, 0, 0, target_height, target_width, ignore_label)
# Randomly crop the image and label.
if is_training and label is not None:
processed_image, label = preprocess_utils.random_crop(
[processed_image, label], crop_height, crop_width)
processed_image.set_shape([crop_height, crop_width, 3])
if label is not None:
label.set_shape([crop_height, crop_width, 1])
if is_training:
# Randomly left-right flip the image and label.
processed_image, label, _ = preprocess_utils.flip_dim(
[processed_image, label], _PROB_OF_FLIP, dim=1)
return original_image, processed_image, label
def preprocess_image_and_label_test(image,
label,
crop_height,
crop_width,
min_resize_value=None,
max_resize_value=None,
resize_factor=None,
min_scale_factor=1.,
max_scale_factor=1.,
scale_factor_step_size=0,
ignore_label=255,
is_training=True,
model_variant=None):
if is_training and label is None:
raise ValueError('During training, label must be provided.')
if model_variant is None:
tf.logging.warning(
'Default mean-subtraction is performed. Please specify '
'a model_variant. See feature_extractor.network_map for '
'supported model variants.')
# Keep reference to original image.
original_image = image
processed_image = tf.cast(image, tf.float32)
if label is not None:
label = tf.cast(label, tf.int32)
# The `original_image` becomes the resized image.
original_image = tf.identity(processed_image)
processed_image = tf.expand_dims(processed_image, 0)
#if label is not None:
# label.set_shape([crop_height, crop_width, 1])
print('processed_image:', processed_image)
processed_image = tf.image.resize_bilinear(processed_image,
[crop_height, crop_width],
align_corners=True)
if is_training:
processed_image = color_augmentation(processed_image)
#processed_image.set_shape([crop_height, crop_width, 3])
label = tf.expand_dims(label, 0)
label = tf.image.resize_bilinear(label, [crop_height, crop_width],
align_corners=True)
if is_training:
# Randomly left-right flip the image and label.
processed_image, label, _ = preprocess_utils.flip_dim(
[processed_image, label], _PROB_OF_FLIP, dim=1)
#t_xy = tf.random_normal([2], mean=0, stddev=10, seed = tf.set_random_seed(1234))
#t_xy_out = tf.cast(t_xy, dtype=tf.int32)
t_x = tf.random_normal([1],
mean=0,
stddev=20,
seed=tf.set_random_seed(1234))
t_y = tf.random_normal([1],
mean=0,
stddev=5,
seed=tf.set_random_seed(1234))
t_x = tf.cast(t_x, dtype=tf.int32)
t_y = tf.cast(t_y, dtype=tf.int32)
t_y = tf.abs(t_y)
#image_aug = tf_image_translate(image_aug, tx=t_x[0], ty=t_y[0])
processed_image = tf_image_translate(processed_image,
tx=t_x[0],
ty=t_y[0])
label = tf_image_translate(label, tx=t_x[0], ty=t_y[0])
processed_image = gaussian_noise_layer(processed_image, std=0.1)
processed_image = negative_layer(processed_image)
#processed_image = tf.image.rgb_to_grayscale(processed_image)
#processed_image = tf.image.grayscale_to_rgb(processed_image)
processed_image = tf.squeeze(processed_image, squeeze_dims=0, name=None)
label = tf.squeeze(label, squeeze_dims=0, name=None)
return original_image, processed_image, label
def preprocess_image_and_label_seq(
image,
label,
prior_segs,
crop_height,
crop_width,
channel,
seq_length,
label_for_each_frame,
pre_crop_height=None,
pre_crop_width=None,
num_class=None,
HU_window=None,
min_resize_value=None,
max_resize_value=None,
resize_factor=None,
min_scale_factor=1.,
max_scale_factor=1.,
scale_factor_step_size=0,
ignore_label=255,
rotate_angle=None,
is_training=True,
model_variant=None,
):
"""Preprocesses the image and label.
Args:
image: Input image.
label: Ground truth annotation label.
crop_height: The height value used to crop the image and label.
crop_width: The width value used to crop the image and label.
min_resize_value: Desired size of the smaller image side.
max_resize_value: Maximum allowed size of the larger image side.
resize_factor: Resized dimensions are multiple of factor plus one.
min_scale_factor: Minimum scale factor value.
max_scale_factor: Maximum scale factor value.
scale_factor_step_size: The step size from min scale factor to max scale
factor. The input is randomly scaled based on the value of
(min_scale_factor, max_scale_factor, scale_factor_step_size).
ignore_label: The label value which will be ignored for training and
evaluation.
is_training: If the preprocessing is used for training or not.
model_variant: Model variant (string) for choosing how to mean-subtract the
images. See feature_extractor.network_map for supported model variants.
Returns:
original_image: Original image (could be resized).
processed_image: Preprocessed image.
label: Preprocessed ground truth segmentation label.
Raises:
ValueError: Ground truth label not provided during training.
"""
if is_training and label is None:
raise ValueError('During training, label must be provided.')
# if (prior_num_slice is not None) != (prior_imgs is not None or prior_segs is not None):
# raise ValueError('prior_num_slice should exist when import prior and vice versa')
if model_variant is None:
tf.logging.warning(
'Default mean-subtraction is performed. Please specify '
'a model_variant. See feature_extractor.network_map for '
'supported model variants.')
# Keep reference to original image.
original_image = image
original_label = label
# sample prior if exist
# TODO: sample problem (consider z gt)
# data type and value convert
if HU_window is not None:
image = preprocess_utils.HU_to_pixelvalue(image, HU_window)
processed_image = tf.cast(image, tf.float32)
if label is not None:
label = tf.cast(label, tf.int32)
if pre_crop_height is not None and pre_crop_width is not None:
if is_training and label is not None:
if prior_segs is not None:
processed_image, label, prior_segs = preprocess_utils.random_crop(
[processed_image, label, prior_segs], pre_crop_height,
pre_crop_width)
else:
processed_image, label = preprocess_utils.random_crop(
[processed_image, label], pre_crop_height, pre_crop_width)
# Resize image and label to the desired range.
# TODO: interface for this func.
if min_resize_value or max_resize_value:
[processed_image,
label] = (preprocess_utils.resize_to_range(image=processed_image,
label=label,
min_size=min_resize_value,
max_size=max_resize_value,
factor=resize_factor,
align_corners=True))
# The `original_image` becomes the resized image.
original_image = tf.identity(processed_image)
if prior_segs is not None:
# prior_segs = tf.cast(prior_segs, tf.int32)
prior_segs, _ = (preprocess_utils.resize_to_range(
image=prior_segs,
min_size=min_resize_value,
max_size=max_resize_value,
factor=resize_factor,
align_corners=True))
# Data augmentation by randomly scaling the inputs.
if is_training:
scale = preprocess_utils.get_random_scale(min_scale_factor,
max_scale_factor,
scale_factor_step_size)
processed_image, label = preprocess_utils.randomly_scale_image_and_label(
processed_image, label, scale)
processed_image.set_shape([None, None, seq_length * channel])
if prior_segs is not None:
prior_segs = preprocess_utils.scale_image_data(prior_segs, scale)
# Pad image and label to have dimensions >= [crop_height, crop_width]
image_shape = tf.shape(processed_image)
# image_shape = processed_image.get_shape().as_list()
image_height = image_shape[0]
image_width = image_shape[1]
target_height = image_height + tf.maximum(crop_height - image_height, 0)
target_width = image_width + tf.maximum(crop_width - image_width, 0)
# Pad image with mean pixel value.
# TODO: check padding value
# mean_pixel = tf.reshape(
# features_extractor.mean_pixel(model_variant), [1, 1, 3])
mean_pixel = 0.0
processed_image = preprocess_utils.pad_to_bounding_box(
processed_image, 0, 0, target_height, target_width, mean_pixel)
if label is not None:
label = preprocess_utils.pad_to_bounding_box(label, 0, 0,
target_height,
target_width, 0)
if prior_segs is not None:
prior_segs = preprocess_utils.pad_to_bounding_box(
prior_segs, 0, 0, target_height, target_width, 0)
# Randomly crop the image and label.
# TODO: Do it in the right way
# TODO: offset_height, offset_width for input
# processed_image, label = preprocess_utils.random_crop(
# [processed_image, label], crop_height, crop_width)
if is_training and label is not None:
if prior_segs is not None:
processed_image, label, prior_segs = preprocess_utils.random_crop(
[processed_image, label, prior_segs], crop_height, crop_width)
else:
processed_image, label = preprocess_utils.random_crop(
[processed_image, label], crop_height, crop_width)
processed_image.set_shape([crop_height, crop_width, seq_length * channel])
if label is not None:
label.set_shape([crop_height, crop_width, seq_length * channel])
# if label_for_each_frame:
# label.set_shape([crop_height, crop_width, seq_length*channel])
# else:
# label.set_shape([crop_height, crop_width, 1])
if prior_segs is not None:
prior_segs = tf.squeeze(tf.image.resize_bilinear(
tf.expand_dims(prior_segs, axis=0), [crop_height, crop_width]),
axis=0)
# prior_segs.set_shape([crop_height,crop_width,num_class])
if is_training:
# Randomly left-right flip the image and label.
if prior_segs is not None:
processed_image, label, prior_segs, _ = preprocess_utils.flip_dim(
[processed_image, label, prior_segs], _PROB_OF_FLIP, dim=1)
else:
processed_image, label, _ = preprocess_utils.flip_dim(
[processed_image, label], _PROB_OF_FLIP, dim=1)
# TODO: coplete random rotate method
# Randomly rotate the image and label.
if rotate_angle is not None:
pass
# processed_image, label, _ = preprocess_utils.random_rotate([processed_image, label], _PROB_OF_ROT, rotate_angle)
return original_image, processed_image, label, original_label, prior_segs
def preprocess_image_and_label(image,
label,
crop_height,
crop_width,
min_resize_value=None,
max_resize_value=None,
resize_factor=None,
min_scale_factor=1.,
max_scale_factor=1.,
scale_factor_step_size=0,
ignore_label=255,
is_training=True,
model_variant=None,
strong_weak=False,
output_valid=False):
"""Preprocesses the image and label.
Args:
image: Input image.
label: Ground truth annotation label.
crop_height: The height value used to crop the image and label.
crop_width: The width value used to crop the image and label.
min_resize_value: Desired size of the smaller image side.
max_resize_value: Maximum allowed size of the larger image side.
resize_factor: Resized dimensions are multiple of factor plus one.
min_scale_factor: Minimum scale factor value.
max_scale_factor: Maximum scale factor value.
scale_factor_step_size: The step size from min scale factor to max scale
factor. The input is randomly scaled based on the value of
(min_scale_factor, max_scale_factor, scale_factor_step_size).
ignore_label: The label value which will be ignored for training and
evaluation.
is_training: If the preprocessing is used for training or not.
model_variant: Model variant (string) for choosing how to mean-subtract the
images. See feature_extractor.network_map for supported model variants.
strong_weak: Generate a pair of (strong, weak) augmented images for
consistency. Also, need to get the valid region exluding padding.
output_valid: Output valid region excluding padding or not.
Returns:
original_image: Original image (could be resized).
processed_image: Preprocessed image.
label: Preprocessed ground truth segmentation label.
Raises:
ValueError: Ground truth label not provided during training.
"""
if is_training and label is None:
raise ValueError('During training, label must be provided.')
if model_variant is None:
tf.logging.warning(
'Default mean-subtraction is performed. Please specify '
'a model_variant. See feature_extractor.network_map for '
'supported model variants.')
# Keep reference to original image.
original_image = image
processed_image = tf.cast(image, tf.float32)
if label is not None:
label = tf.cast(label, tf.int32)
# Resize image and label to the desired range.
if min_resize_value or max_resize_value:
[processed_image,
label] = (preprocess_utils.resize_to_range(image=processed_image,
label=label,
min_size=min_resize_value,
max_size=max_resize_value,
factor=resize_factor,
align_corners=True))
# The `original_image` becomes the resized image.
original_image = tf.identity(processed_image)
# Data augmentation by randomly scaling the inputs.
if is_training:
scale = preprocess_utils.get_random_scale(min_scale_factor,
max_scale_factor,
scale_factor_step_size)
processed_image, label = preprocess_utils.randomly_scale_image_and_label(
processed_image, label, scale)
processed_image.set_shape([None, None, 3])
# Pad image and label to have dimensions >= [crop_height, crop_width]
image_shape = tf.shape(processed_image)
image_height = image_shape[0]
image_width = image_shape[1]
target_height = image_height + tf.maximum(crop_height - image_height, 0)
target_width = image_width + tf.maximum(crop_width - image_width, 0)
if strong_weak:
# # Color distortion (operates in [0, 1])
strong = processed_image / 255.
strong = preprocess_utils.random_color_jitter(strong, _PROB_OF_JITTER)
strong = strong * 255.
# Pad image with mean pixel value.
mean_pixel = tf.reshape(feature_extractor.mean_pixel(model_variant),
[1, 1, 3])
processed_image = preprocess_utils.pad_to_bounding_box(
processed_image, 0, 0, target_height, target_width, mean_pixel)
if strong_weak:
strong = preprocess_utils.pad_to_bounding_box(strong, 0, 0,
target_height,
target_width, mean_pixel)
if label is not None:
label = preprocess_utils.pad_to_bounding_box(label, 0, 0,
target_height,
target_width,
ignore_label)
# Randomly crop the image and label.
if is_training and label is not None:
if not strong_weak:
processed_image, label = preprocess_utils.random_crop(
[processed_image, label], crop_height, crop_width)
else:
processed_image, label, strong = preprocess_utils.random_crop(
[processed_image, label, strong], crop_height, crop_width)
processed_image.set_shape([crop_height, crop_width, 3])
if label is not None:
label.set_shape([crop_height, crop_width, 1])
if not is_training and output_valid:
# Construct the valid mask excluding the boundary padding
xs, ys = tf.meshgrid(tf.range(0, crop_width), tf.range(0, crop_height))
valid_x = tf.cast(tf.less(xs, image_width), tf.int32)
valid_y = tf.cast(tf.less(ys, image_height), tf.int32)
valid = tf.reshape(valid_x * valid_y, [crop_height, crop_width, 1])
if is_training:
if strong_weak or output_valid:
# Construct the valid mask excluding the boundary padding
xs, ys = tf.meshgrid(tf.range(0, crop_width),
tf.range(0, crop_height))
valid_x = tf.cast(tf.less(xs, image_width), tf.int32)
valid_y = tf.cast(tf.less(ys, image_height), tf.int32)
valid = tf.reshape(valid_x * valid_y, [crop_height, crop_width, 1])
if strong_weak:
# Ignore CutOut region
strong, label, valid = preprocess_utils.cutout_with_mask(
strong,
label,
pad_size=50,
mean_pixel=mean_pixel,
ignore_label=ignore_label,
valid=valid)
# Randomly left-right flip the image and label.
processed_image, strong, valid, label, _ = preprocess_utils.flip_dim(
[processed_image, strong, valid, label], _PROB_OF_FLIP, dim=1)
return original_image, processed_image, label, strong, valid
# Randomly left-right flip the image and label.
if not output_valid:
processed_image, label, _ = preprocess_utils.flip_dim(
[processed_image, label], _PROB_OF_FLIP, dim=1)
else:
processed_image, valid, label, _ = preprocess_utils.flip_dim(
[processed_image, valid, label], _PROB_OF_FLIP, dim=1)
if not output_valid:
return original_image, processed_image, label
else:
return original_image, processed_image, label, valid
