def add_sigmoid_cross_entropy_loss_for_each_scale(scales_to_logits,
labels,
ignore_label,
loss_weight=1.0,
upsample_logits=True,
scope=None):
"""Adds sigmoid cross entropy loss for logits of each scale.
Implemented based on deeplab's add_softmax_cross_entropy_loss_for_each_scale
in deeplab/utils/train_utils.py.
Args:
scales_to_logits: A map from logits names for different scales to logits.
The logits have shape [batch, logits_height, logits_width, num_classes].
labels: Groundtruth labels with shape [batch, image_height, image_width, 1].
ignore_label: Integer, label to ignore.
loss_weight: Float, loss weight.
upsample_logits: Boolean, upsample logits or not.
scope: String, the scope for the loss.
Raises:
ValueError: Label or logits is None.
"""
if labels is None:
raise ValueError('No label for softmax cross entropy loss.')
for scale, logits in six.iteritems(scales_to_logits):
loss_scope = None
if scope:
loss_scope = '%s_%s' % (scope, scale)
if upsample_logits:
# Label is not downsampled, and instead we upsample logits.
logits = tf.image.resize_bilinear(logits,
preprocess_utils.resolve_shape(
labels, 4)[1:3],
align_corners=True)
scaled_labels = labels
else:
# Label is downsampled to the same size as logits.
scaled_labels = tf.image.resize_nearest_neighbor(
labels,
preprocess_utils.resolve_shape(logits, 4)[1:3],
align_corners=True)
logits = logits[:, :, :, 1]
scaled_labels = tf.to_float(scaled_labels)
scaled_labels = tf.squeeze(scaled_labels)
not_ignore_mask = tf.to_float(tf.not_equal(scaled_labels,
ignore_label)) * loss_weight
losses = tf.nn.weighted_cross_entropy_with_logits(
scaled_labels, logits, FLAGS.sigmoid_recall_weight)
# Loss added later in model_fn by tf.losses.get_total_loss()
tf.losses.compute_weighted_loss(losses,
weights=not_ignore_mask,
scope=loss_scope)
def add_softmax_cross_entropy_loss_for_each_scale(scales_to_logits,
labels,
num_classes,
ignore_label,
loss_weight=1.0,
upsample_logits=True,
scope=None):
"""Adds softmax cross entropy loss for logits of each scale.
Args:
scales_to_logits: A map from logits names for different scales to logits.
The logits have shape [batch, logits_height, logits_width, num_classes].
labels: Groundtruth labels with shape [batch, image_height, image_width, 1].
num_classes: Integer, number of target classes.
ignore_label: Integer, label to ignore.
loss_weight: Float, loss weight.
upsample_logits: Boolean, upsample logits or not.
scope: String, the scope for the loss.
Raises:
ValueError: Label or logits is None.
"""
if labels is None:
raise ValueError('No label for softmax cross entropy loss.')
for scale, logits in six.iteritems(scales_to_logits):
loss_scope = None
if scope:
loss_scope = '%s_%s' % (scope, scale)
if upsample_logits:
# Label is not downsampled, and instead we upsample logits.
logits = tf.image.resize_bilinear(logits,
preprocess_utils.resolve_shape(
labels, 4)[1:3],
align_corners=True)
scaled_labels = labels
else:
# Label is downsampled to the same size as logits.
scaled_labels = tf.image.resize_nearest_neighbor(
labels,
preprocess_utils.resolve_shape(logits, 4)[1:3],
align_corners=True)
scaled_labels = tf.reshape(scaled_labels, shape=[-1])
not_ignore_mask = tf.to_float(tf.not_equal(scaled_labels,
ignore_label)) * loss_weight
one_hot_labels = slim.one_hot_encoding(scaled_labels,
num_classes,
on_value=1.0,
off_value=0.0)
tf.losses.softmax_cross_entropy(one_hot_labels,
tf.reshape(logits,
shape=[-1, num_classes]),
weights=not_ignore_mask,
scope=loss_scope)
def resize_im(image, image_size, pad_val, channels, elements_boxes=None):
"""Decodes and resizes the image.
Args:
image: Image to resize.
image_size: The desired max image size.
pad_val: The value to pad with.
channels: The number of channels in the image.
elements_boxes: The boxes from elements to resize.
Returns:
Resized image with possible padded regions,
and possibly the resized elements boxes.
"""
[width, height, got_channels] = preprocess_utils.resolve_shape(image, rank=3)
new_width, new_height = get_resize_dim(width, height, image_size)
image = tf.reshape(image, [width, height, -1])
image = tf.cond(
tf.logical_and(channels == 3, tf.equal(got_channels, 1)),
true_fn=lambda: tf.image.grayscale_to_rgb(image),
false_fn=lambda: image,
)
image = tf.image.resize_images(image, [new_width, new_height])
image = preprocess_utils.pad_to_bounding_box(image, 0, 0, image_size,
image_size, pad_val)
if elements_boxes is not None:
return image, elements_boxes / tf.to_float(tf.maximum(width, height))
return image
def resize_im(image, image_size, pad_val, channels, features=None):
"""Decodes and resizes the image.
Args:
image: Image to resize.
image_size: The desired max image size.
pad_val: The value to pad with.
channels: The number of channels in the image.
features: Other features to resize.
Returns:
Resized image with possible padded regions,
and possibly the resized elements boxes.
"""
[height, width, got_channels] = preprocess_utils.resolve_shape(image,
rank=3)
new_height, new_width = get_resize_dim(height, width, image_size)
image = tf.reshape(image, [height, width, -1])
image = tf.cond(
tf.logical_and(channels == 3, tf.equal(got_channels, 1)),
true_fn=lambda: tf.image.grayscale_to_rgb(image),
false_fn=lambda: image,
)
image = tf.image.resize_images(image, [new_height, new_width])
image = preprocess_utils.pad_to_bounding_box(image, 0, 0, image_size,
image_size, pad_val)
if features is not None:
width, height = tf.to_float(width), tf.to_float(height)
max_dim = tf.to_float(tf.maximum(width, height))
features[ELEMENTS_BOX_ID] = features[ELEMENTS_BOX_ID] / max_dim
if GROUNDTRUTH_XMIN_ID in features:
features[GROUNDTRUTH_XMIN_ID] *= width / max_dim
features[GROUNDTRUTH_XMAX_ID] *= width / max_dim
features[GROUNDTRUTH_YMIN_ID] *= height / max_dim
features[GROUNDTRUTH_YMAX_ID] *= height / max_dim
return image