def preprocess_for_eval(image,
labels,
bboxes,
out_shape,
resize,
scope='ssd_preprocessing_train'):
"""Preprocess an image for evaluation.
Args:
image: A `Tensor` representing an image of arbitrary size.
out_shape: Output shape after pre-processing (if resize != None)
resize: Resize strategy.
Returns:
A preprocessed image.
"""
with tf.name_scope(scope):
if image.get_shape().ndims != 3:
raise ValueError('Input must be of size [height, width, C>0]')
image = tf.to_float(image)
image = tf_image_whitened(image, [_R_MEAN, _G_MEAN, _B_MEAN])
# Add image rectangle to bboxes.
bbox_img = tf.constant([[0., 0., 1., 1.]])
if bboxes is None:
bboxes = bbox_img
else:
bboxes = tf.concat(0, [bbox_img, bboxes])
# Resize strategy...
if resize == Resize.NONE:
pass
elif resize == Resize.CENTRAL_CROP:
image, bboxes = tf_image.resize_image_bboxes_with_crop_or_pad(
image, bboxes, out_shape[0], out_shape[1])
elif resize == Resize.PAD_AND_RESIZE:
# Resize image first: find the correct factor...
shape = tf.shape(image)
factor = tf.minimum(
tf.to_double(1.0),
tf.minimum(tf.to_double(out_shape[0] / shape[0]),
tf.to_double(out_shape[1] / shape[1])))
resize_shape = factor * tf.to_double(shape[0:2])
resize_shape = tf.cast(tf.floor(resize_shape), tf.int32)
image = tf_image.resize_image(
image,
resize_shape,
method=tf.image.ResizeMethod.BILINEAR,
align_corners=False)
# Pad to expected size.
image, bboxes = tf_image.resize_image_bboxes_with_crop_or_pad(
image, bboxes, out_shape[0], out_shape[1])
# Split back bounding boxes.
bbox_img = bboxes[0]
bboxes = bboxes[1:]
return image, labels, bboxes, bbox_img
def preprocess_for_eval(image, labels, bboxes, out_shape, resize,
scope='ssd_preprocessing_train'):
"""Preprocess an image for evaluation.
Args:
image: A `Tensor` representing an image of arbitrary size.
out_shape: Output shape after pre-processing (if resize != None)
resize: Resize strategy.
Returns:
A preprocessed image.
"""
with tf.name_scope(scope):
if image.get_shape().ndims != 3:
raise ValueError('Input must be of size [height, width, C>0]')
image = tf.to_float(image)
image = tf_image_whitened(image, [_R_MEAN, _G_MEAN, _B_MEAN])
# Add image rectangle to bboxes.
bbox_img = tf.constant([[0., 0., 1., 1.]])
if bboxes is None:
bboxes = bbox_img
else:
bboxes = tf.concat(0, [bbox_img, bboxes])
# Resize strategy...
if resize == Resize.NONE:
pass
elif resize == Resize.CENTRAL_CROP:
image, bboxes = tf_image.resize_image_bboxes_with_crop_or_pad(
image, bboxes, out_shape[0], out_shape[1])
elif resize == Resize.PAD_AND_RESIZE:
# Resize image first: find the correct factor...
shape = tf.shape(image)
factor = tf.minimum(tf.to_double(1.0),
tf.minimum(tf.to_double(out_shape[0] / shape[0]),
tf.to_double(out_shape[1] / shape[1])))
resize_shape = factor * tf.to_double(shape[0:2])
resize_shape = tf.cast(tf.floor(resize_shape), tf.int32)
image = tf_image.resize_image(image, resize_shape,
method=tf.image.ResizeMethod.BILINEAR,
align_corners=False)
# Pad to expected size.
image, bboxes = tf_image.resize_image_bboxes_with_crop_or_pad(
image, bboxes, out_shape[0], out_shape[1])
# Split back bounding boxes.
bbox_img = bboxes[0]
bboxes = bboxes[1:]
return image, labels, bboxes, bbox_img
def preprocess_for_eval_multi(image,
labels,
bboxes,
out_shape,
resize,
scope='ssd_preprocessing_train'):
with tf.name_scope(scope):
image = tf.to_float(image)
#image = tf_image_whitened(image, [_R_MEAN, _G_MEAN, _B_MEAN])
image = image - np.array([123.6800, 116.7790, 103.9390]).reshape(
(1, 1, 1, 3))
# Add image rectangle to bboxes.
bbox_img = tf.constant([[0., 0., 1., 1.]])
if bboxes is None:
bboxes = bbox_img
else:
bboxes = tf.concat(0, [bbox_img, bboxes])
# Resize strategy...
if resize == Resize.NONE:
pass
elif resize == Resize.CENTRAL_CROP:
image, bboxes = tf_image.resize_image_bboxes_with_crop_or_pad(
image, bboxes, out_shape[0], out_shape[1])
elif resize == Resize.PAD_AND_RESIZE:
# Resize image first: find the correct factor...
shape = tf.shape(image)
factor = tf.minimum(
tf.to_double(1.0),
tf.minimum(tf.to_double(out_shape[0] / shape[0]),
tf.to_double(out_shape[1] / shape[1])))
resize_shape = factor * tf.to_double(shape[0:2])
resize_shape = tf.cast(tf.floor(resize_shape), tf.int32)
image = tf_image.resize_image(
image,
resize_shape,
method=tf.image.ResizeMethod.BILINEAR,
align_corners=False)
# Pad to expected size.
image, bboxes = tf_image.resize_image_bboxes_with_crop_or_pad(
image, bboxes, out_shape[0], out_shape[1])
# Split back bounding boxes.
bbox_img = bboxes[0]
bboxes = bboxes[1:]
return image, labels, bboxes, bbox_img
def expand():
scale = tf.random_uniform([], minval = 1.0,
maxval = MAX_EXPAND_SCALE, dtype=tf.float32)
image_shape = tf.cast(tf.shape(image), dtype = tf.float32)
image_h, image_w = image_shape[0], image_shape[1]
target_h = tf.cast(image_h * scale, dtype = tf.int32)
target_w = tf.cast(image_w * scale, dtype = tf.int32)
tf.logging.info('expanded')
return tf_image.resize_image_bboxes_with_crop_or_pad(
image, bboxes, xs, ys, target_h, target_w)
def expand():
scale = tf.random_uniform([], minval = 1.0,
maxval = MAX_EXPAND_SCALE, dtype=tf.float32)
image_shape = tf.cast(tf.shape(image), dtype = tf.float32)
image_h, image_w = image_shape[0], image_shape[1]
target_h = tf.cast(image_h * scale, dtype = tf.int32)
target_w = tf.cast(image_w * scale, dtype = tf.int32)
tf.logging.info('expanded')
return tf_image.resize_image_bboxes_with_crop_or_pad(
image, bboxes, xs, ys, target_h, target_w)
def preprocess_for_eval(image, labels, bboxes,
out_shape=EVAL_SIZE, data_format='NHWC',
difficults=None, resize=Resize.WARP_RESIZE,
scope='ssd_preprocessing_train'):
"""Preprocess an image for evaluation.
Args:
image: A `Tensor` representing an image of arbitrary size.
out_shape: Output shape after pre-processing (if resize != None)
resize: Resize strategy.
Returns:
A preprocessed image.
"""
with tf.name_scope(scope):
if image.get_shape().ndims != 3:
raise ValueError('Input must be of size [height, width, C>0]')
image = tf.to_float(image)
image = tf_image_whitened(image, [_R_MEAN, _G_MEAN, _B_MEAN])
# Add image rectangle to bboxes.
bbox_img = tf.constant([[0., 0., 1., 1.]])
if bboxes is None:
bboxes = bbox_img
else:
bboxes = tf.concat([bbox_img, bboxes], axis=0)
if resize == Resize.NONE:
# No resizing...
pass
elif resize == Resize.CENTRAL_CROP:
# Central cropping of the image.
image, bboxes = tf_image.resize_image_bboxes_with_crop_or_pad(
image, bboxes, out_shape[0], out_shape[1])
elif resize == Resize.PAD_AND_RESIZE:
# Resize image first: find the correct factor...
shape = tf.shape(image)
factor = tf.minimum(tf.to_double(1.0),
tf.minimum(tf.to_double(out_shape[0] / shape[0]),
tf.to_double(out_shape[1] / shape[1])))
resize_shape = factor * tf.to_double(shape[0:2])
resize_shape = tf.cast(tf.floor(resize_shape), tf.int32)
image = tf_image.resize_image(image, resize_shape,
method=tf.image.ResizeMethod.BILINEAR,
align_corners=False)
# Pad to expected size.
image, bboxes = tf_image.resize_image_bboxes_with_crop_or_pad(
image, bboxes, out_shape[0], out_shape[1])
elif resize == Resize.WARP_RESIZE:
# Warp resize of the image.
image = tf_image.resize_image(image, out_shape,
method=tf.image.ResizeMethod.BILINEAR,
align_corners=False)
# Split back bounding boxes.
bbox_img = bboxes[0]
bboxes = bboxes[1:]
# Remove difficult boxes.
if difficults is not None:
mask = tf.logical_not(tf.cast(difficults, tf.bool))
labels = tf.boolean_mask(labels, mask)
bboxes = tf.boolean_mask(bboxes, mask)
# Image data format.
if data_format == 'NCHW':
image = tf.transpose(image, perm=(2, 0, 1))
return image, labels, bboxes, bbox_img
def preprocess_for_train(image,
labels,
bboxes,
xs,
ys,
out_shape,
data_format='NHWC',
scope='ssd_preprocessing_train'):
"""Preprocesses the given image for training.
Note that the actual resizing scale is sampled from
[`resize_size_min`, `resize_size_max`].
Args:
image: A `Tensor` representing an image of arbitrary size.
output_height: The height of the image after preprocessing.
output_width: The width of the image after preprocessing.
resize_side_min: The lower bound for the smallest side of the image for
aspect-preserving resizing.
resize_side_max: The upper bound for the smallest side of the image for
aspect-preserving resizing.
Returns:
A preprocessed image.
"""
fast_mode = True
with tf.name_scope(scope, 'ssd_preprocessing_train',
[image, labels, bboxes]):
if image.get_shape().ndims != 3:
raise ValueError('Input must be of size [height, width, C>0]')
# rotate image by 0, 0.5 * pi, pi, 1.5 * pi randomly
# if USE_ROTATION:
# image, bboxes, xs, ys = tf_image.random_rotate90(image, bboxes, xs, ys)
# rotate image by 0, 0.5 * pi, pi, 1.5 * pi randomly
if USE_ROTATION:
rnd = tf.random_uniform((), minval=0, maxval=1)
def rotate():
return tf_image.random_rotate90(image, bboxes, xs, ys)
def no_rotate():
return image, bboxes, xs, ys
image, bboxes, xs, ys = tf.cond(tf.less(rnd, config.rotation_prob),
rotate, no_rotate)
#
image_shape = tf.cast(tf.shape(image), dtype=tf.float32)
image_h, image_w = image_shape[0], image_shape[1]
target = tf.cast(tf.maximum(image_h, image_w), dtype=tf.int32)
image, bboxes, xs, ys = tf_image.resize_image_bboxes_with_crop_or_pad(
image, bboxes, xs, ys, target, target)
# expand image
if MAX_EXPAND_SCALE > 1:
rnd2 = tf.random_uniform((), minval=0, maxval=1)
def expand():
scale = tf.random_uniform([],
minval=1.0,
maxval=MAX_EXPAND_SCALE,
dtype=tf.float32)
image_shape = tf.cast(tf.shape(image), dtype=tf.float32)
image_h, image_w = image_shape[0], image_shape[1]
target_h = tf.cast(image_h * scale, dtype=tf.int32)
target_w = tf.cast(image_w * scale, dtype=tf.int32)
tf.logging.info('expanded')
return tf_image.resize_image_bboxes_with_crop_or_pad(
image, bboxes, xs, ys, target_h, target_w)
def no_expand():
return image, bboxes, xs, ys
image, bboxes, xs, ys = tf.cond(tf.less(rnd2, config.expand_prob),
expand, no_expand)
# Convert to float scaled [0, 1].
if image.dtype != tf.float32:
image = tf.image.convert_image_dtype(image, dtype=tf.float32)
# tf_summary_image(image, bboxes, 'image_with_bboxes')
# Distort image and bounding boxes.
dst_image = image
# dst_image, labels, bboxes, xs, ys, distort_bbox = \
# distorted_bounding_box_crop(image, labels, bboxes, xs, ys,
# min_object_covered = MIN_OBJECT_COVERED,
# aspect_ratio_range = CROP_ASPECT_RATIO_RANGE,
# area_range = AREA_RANGE)
# Resize image to output size.
dst_image = tf_image.resize_image(
dst_image,
out_shape,
method=tf.image.ResizeMethod.BILINEAR,
align_corners=False)
tf_summary_image(dst_image, bboxes, 'image_shape_distorted')
# Filter bboxes using the length of shorter sides
if USING_SHORTER_SIDE_FILTERING:
xs = xs * out_shape[1]
ys = ys * out_shape[0]
labels, bboxes, xs, ys = tfe.bboxes_filter_by_shorter_side(
labels,
bboxes,
xs,
ys,
min_height=MIN_SHORTER_SIDE,
max_height=MAX_SHORTER_SIDE,
assign_value=LABEL_IGNORE)
xs = xs / out_shape[1]
ys = ys / out_shape[0]
# Randomly distort the colors. There are 4 ways to do it.
dst_image = apply_with_random_selector(
dst_image,
lambda x, ordering: distort_color(x, ordering, fast_mode),
num_cases=4)
tf_summary_image(dst_image, bboxes, 'image_color_distorted')
# Rescale to VGG input scale.
image = dst_image * 255.
image = tf_image_whitened(image, [_R_MEAN, _G_MEAN, _B_MEAN])
# Image data format.
if data_format == 'NCHW':
image = tf.transpose(image, perm=(2, 0, 1))
return image, labels, bboxes, xs, ys
