def distorted_bounding_box_crop(image,
labels,
bboxes,
min_object_covered=0.3,
aspect_ratio_range=(0.9, 1.1),
area_range=(0.1, 1.0),
max_attempts=200,
clip_bboxes=True,
scope=None):
"""Generates cropped_image using a one of the bboxes randomly distorted.
See `tf.image.sample_distorted_bounding_box` for more documentation.
Args:
image: 3-D Tensor of image (it will be converted to floats in [0, 1]).
bbox: 3-D float Tensor of bounding boxes arranged [1, num_boxes, coords]
where each coordinate is [0, 1) and the coordinates are arranged
as [ymin, xmin, ymax, xmax]. If num_boxes is 0 then it would use the whole
image.
min_object_covered: An optional `float`. Defaults to `0.1`. The cropped
area of the image must contain at least this fraction of any bounding box
supplied.
aspect_ratio_range: An optional list of `floats`. The cropped area of the
image must have an aspect ratio = width / height within this range.
area_range: An optional list of `floats`. The cropped area of the image
must contain a fraction of the supplied image within in this range.
max_attempts: An optional `int`. Number of attempts at generating a cropped
region of the image of the specified constraints. After `max_attempts`
failures, return the entire image.
scope: Optional scope for name_scope.
Returns:
A tuple, a 3-D Tensor cropped_image and the distorted bbox
"""
with tf.name_scope(scope, 'distorted_bounding_box_crop', [image, bboxes]):
# Each bounding box has shape [1, num_boxes, box coords] and
# the coordinates are ordered [ymin, xmin, ymax, xmax].
bboxes = tf.clip_by_value(bboxes, 0.0, 1.0)
bbox_begin, bbox_size, distort_bbox = tf.image.sample_distorted_bounding_box(
tf.shape(image),
bounding_boxes=tf.expand_dims(bboxes, 0),
min_object_covered=min_object_covered,
aspect_ratio_range=aspect_ratio_range,
area_range=area_range,
max_attempts=max_attempts,
use_image_if_no_bounding_boxes=True)
distort_bbox = distort_bbox[0, 0]
# Crop the image to the specified bounding box.
cropped_image = tf.slice(image, bbox_begin, bbox_size)
# Restore the shape since the dynamic slice loses 3rd dimension.
cropped_image.set_shape([None, None, 3])
# Update bounding boxes: resize and filter out.
bboxes = tfe.bboxes_resize(distort_bbox, bboxes)
labels, bboxes = tfe.bboxes_filter_overlap(labels,
bboxes,
threshold=BBOX_CROP_OVERLAP,
assign_negative=False)
return cropped_image, labels, bboxes, distort_bbox
def distorted_bounding_box_crop(image,
labels,
bboxes,
min_object_covered=0.3,
aspect_ratio_range=(0.9, 1.1),
area_range=(0.1, 1.0),
max_attempts=200,
clip_bboxes=True,
scope=None):
"""Generates cropped_image using a one of the bboxes randomly distorted.
See `tf.image.sample_distorted_bounding_box` for more documentation.
Args:
image: 3-D Tensor of image (it will be converted to floats in [0, 1]).
bbox: 3-D float Tensor of bounding boxes arranged [1, num_boxes, coords]
where each coordinate is [0, 1) and the coordinates are arranged
as [ymin, xmin, ymax, xmax]. If num_boxes is 0 then it would use the whole
image.
min_object_covered: An optional `float`. Defaults to `0.1`. The cropped
area of the image must contain at least this fraction of any bounding box
supplied.
aspect_ratio_range: An optional list of `floats`. The cropped area of the
image must have an aspect ratio = width / height within this range.
area_range: An optional list of `floats`. The cropped area of the image
must contain a fraction of the supplied image within in this range.
max_attempts: An optional `int`. Number of attempts at generating a cropped
region of the image of the specified constraints. After `max_attempts`
failures, return the entire image.
scope: Optional scope for name_scope.
Returns:
A tuple, a 3-D Tensor cropped_image and the distorted bbox
"""
with tf.name_scope(scope, 'distorted_bounding_box_crop', [image, bboxes]):
# Each bounding box has shape [1, num_boxes, box coords] and
# the coordinates are ordered [ymin, xmin, ymax, xmax].
bbox_begin, bbox_size, distort_bbox = tf.image.sample_distorted_bounding_box(
tf.shape(image),
bounding_boxes=tf.expand_dims(bboxes, 0),
min_object_covered=min_object_covered,
aspect_ratio_range=aspect_ratio_range,
area_range=area_range,
max_attempts=max_attempts,
use_image_if_no_bounding_boxes=True)
distort_bbox = distort_bbox[0, 0]
# Crop the image to the specified bounding box.
cropped_image = tf.slice(image, bbox_begin, bbox_size)
# Restore the shape since the dynamic slice loses 3rd dimension.
cropped_image.set_shape([None, None, 3])
# Update bounding boxes: resize and filter out.
bboxes = tfe.bboxes_resize(distort_bbox, bboxes)
labels, bboxes = tfe.bboxes_filter_overlap(labels, bboxes,
threshold=BBOX_CROP_OVERLAP,
assign_negative=False)
return cropped_image, labels, bboxes, distort_bbox
def distorted_image(image, height, labels, width, bbox, thread_id, scope=None):
# Each bounding box has shape [1, num_boxes, box coords] and
# the coordinates are ordered [ymin, xmin, ymax, xmax].
# Display the bounding box in the first thread only.
with tf.name_scope(scope, 'distorted_bounding_box_crop',
[image, bbox, height, width]):
if not thread_id:
image_with_box = tf.image.draw_bounding_boxes(
tf.expand_dims(image, 0), bbox)
tf.summary.image('image_with_bounding_boxes', image_with_box)
bbox_begin, bbox_size, distort_bbox = tf.image.sample_distorted_bounding_box(
tf.shape(image),
bounding_boxes=bbox,
min_object_covered=0.1,
aspect_ratio_range=(0.9, 1.1),
area_range=(0.1, 1.0),
max_attempts=200,
use_image_if_no_bounding_boxes=True)
if not thread_id:
image_with_distorted_box = tf.image.draw_bounding_boxes(
tf.expand_dims(image, 0), distort_bbox)
tf.summary.image('images_with_distorted_bounding_box',
image_with_distorted_box)
distort_bbox = distort_bbox[0, 0]
# Crop the image to the specified bounding box.
cropped_image = tf.slice(image, bbox_begin, bbox_size)
# Restore the shape since the dynamic slice loses 3rd dimension.
distorted_image = tf.image.resize_images(
cropped_image, [height, width],
method=tf.image.ResizeMethod.BILINEAR)
distorted_image.set_shape([height, width, 3])
if not thread_id:
tf.summary.image('cropped_resized_image',
tf.expand_dims(distorted_image, 0))
distorted_image = tf.image.random_flip_left_right(distorted_image)
# Randomly distort the colors.
distorted_image = distort_color(distorted_image, thread_id)
if not thread_id:
tf.summary.image('final_distorted_image',
tf.expand_dims(distorted_image, 0))
# Update bounding boxes: resize and filter out.
bboxes = tfe.bboxes_resize(distort_bbox, bbox)
print "labels: %s " % (labels)
label, bboxes, num = tfe.bboxes_filter_overlap(labels,
bboxes,
threshold=0.4)
return distorted_image, label, bboxes, num
def distorted_bounding_box_crop(image,
labels,
bboxes,
cord,
min_object_covered=0.1,
aspect_ratio_range=(0.8, 1.2),
area_range=(0.1, 1.0),
max_attempts=200,
scope=None):
"""Generates cropped_image using a one of the bboxes randomly distorted.
Args:
image: A `Tensor` representing an image of arbitrary size.
labels : A Tensor inlcudes all labels
bboxes : A Tensor inlcudes cordinates of bbox in shape [N, 4]
min_object_covered: An optional `float`. Defaults to `0.1`. The cropped
area of the image must contain at least this fraction of any bounding box
supplied.
aspect_ratio_range: An optional list of `floats`. The cropped area of the
image must have an aspect ratio = width / height within this range.
area_range: An optional list of `floats`. The cropped area of the image
must contain a fraction of the supplied image within in this range.
max_attempts: An optional `int`. Number of attempts at generating a cropped
region of the image of the specified constraints. After `max_attempts`
failures, return the entire image.
scope: Optional scope for name_scope.
Returns:
A tuple, a 3-D Tensor cropped_image and the distorted bbox
"""
with tf.name_scope(scope, 'distorted_bounding_box_crop', [image, bboxes,cord]):
# Each bounding box has shape [1, num_boxes, box coords] and
# the coordinates are ordered [ymin, xmin, ymax, xmax].
bbox_begin, bbox_size, distort_bbox = tf.image.sample_distorted_bounding_box(
tf.shape(image),
bounding_boxes=tf.expand_dims(bboxes, 0),
min_object_covered=min_object_covered,
aspect_ratio_range=aspect_ratio_range,
area_range=area_range,
max_attempts=max_attempts,
use_image_if_no_bounding_boxes=False)
distort_bbox = distort_bbox[0, 0]
# Crop the image to the specified bounding box.
cropped_image = tf.slice(image, bbox_begin, bbox_size)
# Update bounding boxes: resize and filter out.
bboxes = tfe.bboxes_resize(distort_bbox, bboxes)
cord = tfe.polybox_resize(distort_bbox, cord)
labels, bboxes, cord, num = tfe.bboxes_filter_overlap(labels, bboxes,cord,
BBOX_CROP_OVERLAP)
return cropped_image, labels, bboxes, cord, distort_bbox,num
def distorted_bounding_box_crop(image,
labels,
bboxes,
xs,
ys,
min_object_covered,
aspect_ratio_range,
area_range,
max_attempts=200,
scope=None):
"""Generates cropped_image using a one of the bboxes randomly distorted.
See `tf.image.sample_distorted_bounding_box` for more documentation.
Args:
image: 3-D Tensor of image (it will be converted to floats in [0, 1]).
bbox: 2-D float Tensor of bounding boxes arranged [num_boxes, coords]
where each coordinate is [0, 1) and the coordinates are arranged
as [ymin, xmin, ymax, xmax]. If num_boxes is 0 then it would use the whole
image.
min_object_covered: An optional `float`. Defaults to `0.1`. The cropped
area of the image must contain at least this fraction of any bounding box
supplied.
aspect_ratio_range: An optional list of `floats`. The cropped area of the
image must have an aspect ratio = width / height within this range.
area_range: An optional list of `floats`. The cropped area of the image
must contain a fraction of the supplied image within in this range.
max_attempts: An optional `int`. Number of attempts at generating a cropped
region of the image of the specified constraints. After `max_attempts`
failures, return the entire image.
scope: Optional scope for name_scope.
Returns:
A tuple, a 3-D Tensor cropped_image and the distorted bbox
"""
with tf.name_scope(scope, 'distorted_bounding_box_crop',
[image, bboxes, xs, ys]):
# Each bounding box has shape [1, num_boxes, box coords] and
# the coordinates are ordered [ymin, xmin, ymax, xmax].
num_bboxes = tf.shape(bboxes)[0]
def has_bboxes():
return bboxes, labels, xs, ys
def no_bboxes():
xmin = tf.random_uniform((1, 1), minval=0, maxval=0.9)
ymin = tf.random_uniform((1, 1), minval=0, maxval=0.9)
w = tf.constant(0.1, dtype=tf.float32)
h = w
xmax = xmin + w
ymax = ymin + h
rnd_bboxes = tf.concat([ymin, xmin, ymax, xmax], axis=1)
rnd_labels = tf.constant([0], dtype=tf.int32)
rnd_xs = tf.concat([xmin, xmax, xmax, xmin], axis=1)
rnd_ys = tf.concat([ymin, ymin, ymax, ymax], axis=1)
return rnd_bboxes, rnd_labels, rnd_xs, rnd_ys
bboxes, labels, xs, ys = tf.cond(num_bboxes > 0, has_bboxes, no_bboxes)
bbox_begin, bbox_size, distort_bbox = tf.image.sample_distorted_bounding_box(
tf.shape(image),
bounding_boxes=tf.expand_dims(bboxes, 0),
min_object_covered=min_object_covered,
aspect_ratio_range=aspect_ratio_range,
area_range=area_range,
max_attempts=max_attempts,
use_image_if_no_bounding_boxes=True)
distort_bbox = distort_bbox[0, 0]
# Crop the image to the specified bounding box.
cropped_image = tf.slice(image, bbox_begin, bbox_size)
# Restore the shape since the dynamic slice loses 3rd dimension.
cropped_image.set_shape([None, None, 3])
# Update bounding boxes: resize and filter out.
bboxes, xs, ys = tfe.bboxes_resize(distort_bbox, bboxes, xs, ys)
labels, bboxes, xs, ys = tfe.bboxes_filter_overlap(
labels,
bboxes,
xs,
ys,
threshold=BBOX_CROP_OVERLAP,
assign_value=LABEL_IGNORE)
return cropped_image, labels, bboxes, xs, ys, distort_bbox
def distorted_bounding_box_crop(image,
labels,
bboxes,
xs, ys,
min_object_covered,
aspect_ratio_range,
area_range,
max_attempts = 200,
scope=None):
"""Generates cropped_image using a one of the bboxes randomly distorted.
See `tf.image.sample_distorted_bounding_box` for more documentation.
Args:
image: 3-D Tensor of image (it will be converted to floats in [0, 1]).
bbox: 2-D float Tensor of bounding boxes arranged [num_boxes, coords]
where each coordinate is [0, 1) and the coordinates are arranged
as [ymin, xmin, ymax, xmax]. If num_boxes is 0 then it would use the whole
image.
min_object_covered: An optional `float`. Defaults to `0.1`. The cropped
area of the image must contain at least this fraction of any bounding box
supplied.
aspect_ratio_range: An optional list of `floats`. The cropped area of the
image must have an aspect ratio = width / height within this range.
area_range: An optional list of `floats`. The cropped area of the image
must contain a fraction of the supplied image within in this range.
max_attempts: An optional `int`. Number of attempts at generating a cropped
region of the image of the specified constraints. After `max_attempts`
failures, return the entire image.
scope: Optional scope for name_scope.
Returns:
A tuple, a 3-D Tensor cropped_image and the distorted bbox
"""
with tf.name_scope(scope, 'distorted_bounding_box_crop', [image, bboxes, xs, ys]):
# Each bounding box has shape [1, num_boxes, box coords] and
# the coordinates are ordered [ymin, xmin, ymax, xmax].
num_bboxes = tf.shape(bboxes)[0]
def has_bboxes():
return bboxes, labels, xs, ys
def no_bboxes():
xmin = tf.random_uniform((1,1), minval = 0, maxval = 0.9)
ymin = tf.random_uniform((1,1), minval = 0, maxval = 0.9)
w = tf.constant(0.1, dtype = tf.float32)
h = w
xmax = xmin + w
ymax = ymin + h
rnd_bboxes = tf.concat([ymin, xmin, ymax, xmax], axis = 1)
rnd_labels = tf.constant([config.background_label], dtype = tf.int64)
rnd_xs = tf.concat([xmin, xmax, xmax, xmin], axis = 1)
rnd_ys = tf.concat([ymin, ymin, ymax, ymax], axis = 1)
return rnd_bboxes, rnd_labels, rnd_xs, rnd_ys
bboxes, labels, xs, ys = tf.cond(num_bboxes > 0, has_bboxes, no_bboxes)
bbox_begin, bbox_size, distort_bbox = tf.image.sample_distorted_bounding_box(
tf.shape(image),
bounding_boxes=tf.expand_dims(bboxes, 0),
min_object_covered=min_object_covered,
aspect_ratio_range=aspect_ratio_range,
area_range=area_range,
max_attempts=max_attempts,
use_image_if_no_bounding_boxes=True)
distort_bbox = distort_bbox[0, 0]
# Crop the image to the specified bounding box.
cropped_image = tf.slice(image, bbox_begin, bbox_size)
# Restore the shape since the dynamic slice loses 3rd dimension.
cropped_image.set_shape([None, None, 3])
# Update bounding boxes: resize and filter out.
bboxes, xs, ys = tfe.bboxes_resize(distort_bbox, bboxes, xs, ys)
labels, bboxes, xs, ys = tfe.bboxes_filter_overlap(labels, bboxes, xs, ys,
threshold=BBOX_CROP_OVERLAP, assign_value = LABEL_IGNORE)
return cropped_image, labels, bboxes, xs, ys, distort_bbox
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 = False
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]')
# Randomly flip the image horizontally.
if FLIP:
image, bboxes, xs, ys = tf_image.random_flip_left_right_bbox(
image, bboxes, xs, ys)
if ROTATE:
# random rotate the image [-10, 10]
image, bboxes, xs, ys = tf_rotate_image(image, xs, ys)
# samples = tf.multinomial(tf.log([[0.25, 0.25, 0.25, 0.25]]), 1) # note log-prob
# scale=elems[tf.cast(samples[0][0], tf.int32)]
# if SCALE:
# image,bboxes,xs,ys=tf_scale_image(image,bboxes,xs,ys,640)
image_shape = tf.cast(tf.shape(image), dtype=tf.float32)
image_h, image_w = image_shape[0], image_shape[1]
if USE_NM_CROP:
mask = tf.greater_equal(labels, 1)
valid_bboxes = tf.boolean_mask(bboxes, mask)
# FIXME bboxes may is empty
# NOTE tf_func must return value must be numpy, or you will madding!!!!!!
crop_bbox = tf.py_func(generate_sample,
[image_shape, valid_bboxes], tf.float32)
else:
scales = tf.random_shuffle([0.5, 1.])
scales = tf.Print(scales, [crop])
target_h = tf.cast(640 / scales[0], dtype=tf.float32)
target_w = tf.cast(640 / scales[0], dtype=tf.float32)
bbox_begin_h_max = tf.maximum(image_h - target_h, 0)
bbox_begin_w_max = tf.maximum(image_w - target_w, 0)
bbox_begin_h = tf.random_uniform([],
minval=0,
maxval=bbox_begin_h_max,
dtype=tf.float32)
bbox_begin_w = tf.random_uniform([],
minval=0,
maxval=bbox_begin_w_max,
dtype=tf.float32)
crop_bbox = [bbox_begin_h/image_h, bbox_begin_w/image_w, \
(bbox_begin_h+target_h)/image_h, (bbox_begin_w+target_w)/image_w]
image = tf.image.crop_and_resize(tf.expand_dims(image, 0), [crop_bbox],
[0], (640, 640),
extrapolation_value=128)
image = tf.squeeze(image, 0)
bboxes, xs, ys = tfe.bboxes_resize(crop_bbox, bboxes, xs, ys)
labels, bboxes, xs, ys = tfe.bboxes_filter_overlap(
labels,
bboxes,
xs,
ys,
threshold=BBOX_CROP_OVERLAP,
assign_value=LABEL_IGNORE)
if ROTATE_90:
rnd = tf.random_uniform((), minval=0, maxval=1)
image, bboxes, xs, ys = tf.cond(
tf.less(rnd, 0.2),
lambda: tf_image.random_rotate90(image, bboxes, xs, ys),
lambda: (image, bboxes, xs, ys))
# tf_summary_image(tf.to_float(image), bboxes, 'crop_image')
# what is the enpand's meanoing?
# 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
# use tf.image.sample_distorted_bounding_box() random crop train patch, but can't control the scale
if False:
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)
# 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 / 255.0,
lambda x, ordering: distort_color(x, ordering, fast_mode),
num_cases=4)
dst_image = dst_image * 255.
# tf_summary_image(dst_image, bboxes, 'image_color_distorted')
# FIXME: change the input value
# NOTE: resnet v1 use VGG data process, so we use the same way
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
def distorted_bounding_box_crop(image,
labels,
bboxes,
min_object_covered=0.3,
aspect_ratio_range=(0.9, 1.1),
area_range=(0.1, 1.0),
max_attempts=200,
clip_bboxes=True,
scope=None):
"""Generates cropped_image using a one of the bboxes randomly distorted.
See `tf.image.sample_distorted_bounding_box` for more documentation.
Args:
image: 3-D Tensor of image (it will be converted to floats in [0, 1]).
bbox: 3-D float Tensor of bounding boxes arranged [1, num_boxes, coords]
where each coordinate is [0, 1) and the coordinates are arranged
as [ymin, xmin, ymax, xmax]. If num_boxes is 0 then it would use the whole
image.
min_object_covered: An optional `float`. Defaults to `0.1`. The cropped
area of the image must contain at least this fraction of any bounding box
supplied.
aspect_ratio_range: An optional list of `floats`. The cropped area of the
image must have an aspect ratio = width / height within this range.
area_range: An optional list of `floats`. The cropped area of the image
must contain a fraction of the supplied image within in this range.
max_attempts: An optional `int`. Number of attempts at generating a cropped
region of the image of the specified constraints. After `max_attempts`
failures, return the entire image.
scope: Optional scope for name_scope.
Returns:
A tuple, a 3-D Tensor cropped_image and the distorted bbox
"""
with tf.name_scope(scope, 'distorted_bounding_box_crop', [image, bboxes]):
# 高级的随机裁剪
# The bounding box coordinates are floats in `[0.0, 1.0]` relative to the width
# and height of the underlying image.
# 1-D, 1-D, [1, 1, 4]
bbox_begin, bbox_size, distort_bbox = tf.image.sample_distorted_bounding_box(
tf.shape(image),
bounding_boxes=tf.expand_dims(bboxes, 0), # [1, n, 4]
min_object_covered=min_object_covered,
aspect_ratio_range=aspect_ratio_range,
area_range=area_range,
max_attempts=max_attempts,
use_image_if_no_bounding_boxes=True)
'''
Returns:
A tuple of `Tensor` objects (begin, size, bboxes).
begin: A `Tensor`. Has the same type as `image_size`. 1-D, containing `[offset_height, offset_width, 0]`.
Provide as input to `tf.slice`.
size: A `Tensor`. Has the same type as `image_size`. 1-D, containing `[target_height, target_width, -1]`.
Provide as input to `tf.slice`.
bboxes: A `Tensor` of type `float32`. 3-D with shape `[1, 1, 4]` containing the distorted bounding box.
Provide as input to `tf.image.draw_bounding_boxes`.
'''
# [4]
distort_bbox = distort_bbox[0, 0]
# Crop the image to the specified bounding box.
cropped_image = tf.slice(image, bbox_begin, bbox_size)
# Restore the shape since the dynamic slice loses 3rd dimension.
cropped_image.set_shape([None, None, 3]) # <-----设置了尺寸了哈
# Update bounding boxes: resize and filter out.
bboxes = tfe.bboxes_resize(distort_bbox, bboxes) # [4], [n, 4]
labels, bboxes = tfe.bboxes_filter_overlap(labels, bboxes,
threshold=BBOX_CROP_OVERLAP, # 0.5
assign_negative=False)
# 返回随机裁剪的图片，筛选调整后的labels(n,)、bboxes(n, 4)，裁剪图片对应原图坐标(4,)
return cropped_image, labels, bboxes, distort_bbox
def distorted_bounding_box_crop(image,
labels,
bboxes,
min_object_covered=0.3,
aspect_ratio_range=(0.9, 1.1),
area_range=(0.1, 1.0),
max_attempts=200,
clip_bboxes=True,
scope=None):
"""Generates cropped_image using a one of the bboxes randomly distorted.
See `tf.image.sample_distorted_bounding_box` for more documentation.
Args:
image: 3-D Tensor of image (it will be converted to floats in [0, 1]).
bbox: 3-D float Tensor of bounding boxes arranged [1, num_boxes, coords]
where each coordinate is [0, 1) and the coordinates are arranged
as [ymin, xmin, ymax, xmax]. If num_boxes is 0 then it would use the whole
image.
min_object_covered: An optional `float`. Defaults to `0.1`. The cropped
area of the image must contain at least this fraction of any bounding box
supplied.
aspect_ratio_range: An optional list of `floats`. The cropped area of the
image must have an aspect ratio = width / height within this range.
area_range: An optional list of `floats`. The cropped area of the image
must contain a fraction of the supplied image within in this range.
max_attempts: An optional `int`. Number of attempts at generating a cropped
region of the image of the specified constraints. After `max_attempts`
failures, return the entire image.
scope: Optional scope for name_scope.
Returns:
A tuple, a 3-D Tensor cropped_image and the distorted bbox
"""
with tf.name_scope(scope, 'distorted_bounding_box_crop', [image, bboxes]):
# Each bounding box has shape [1, num_boxes, box coords] and
# the coordinates are ordered [ymin, xmin, ymax, xmax].
#bbox_begin：和 image_size 具有相同的类型。包含 [offset_height, offset_width, 0] 的一维数组。作为 tf.slice 的输入。
#bbox_size：作为 tf.slice 的输入。
#distort_bbox：作为 tf.image.draw_bounding_boxes 的输入。
bbox_begin, bbox_size, distort_bbox = tf.image.sample_distorted_bounding_box(
tf.shape(image),# 是包含 [height, width, channels] 三个值的一维数组。数值类型必须是 uint8，int8，int16，int32，int64 中的一种。
bounding_boxes=tf.expand_dims(bboxes, 0),#是一个 shape 为 [batch, N, 4] 的三维数组，数据类型为float32，第一个batch是因为函数是处理一组图片的，N表示描述与图像相关联的N个边界框的形状，而标注框由4个数字 [y_min, x_min, y_max, x_max] 表示出来。例如：tf.constant([[[0.05, 0.05, 0.9, 0.7], [0.35, 0.47, 0.5, 0.56]]]) 的 shape 为 [1,2,4] 表示一张图片中的两个标注框；
min_object_covered=min_object_covered,#图像的裁剪区域必须包含所提供的任意一个边界框的至少 min_object_covered 的内容。该参数的值应为非负数，当为0时，裁剪区域不必与提供的任何边界框有重叠部分。
aspect_ratio_range=aspect_ratio_range,#图像的裁剪区域的宽高比（宽高比=宽/高） 必须在这个范围内。
area_range=area_range,#默认为 [0.05, 1] 。图像的裁剪区域必须包含这个范围内的图像的一部分。
max_attempts=max_attempts,#尝试生成图像指定约束的裁剪区域的次数。经过 max_attempts 次失败后，将返回整个图像。
use_image_if_no_bounding_boxes=True)#如果没有提供边框，则用它来控制行为。如果为True，则假设有一个覆盖整个输入的隐含边界框。如果为False，就报错。
distort_bbox = distort_bbox[0, 0]
# Crop the image to the specified bounding box.
cropped_image = tf.slice(image, bbox_begin, bbox_size)
# Restore the shape since the dynamic slice loses 3rd dimension.
cropped_image.set_shape([None, None, 3])
# Update bounding boxes: resize and filter out.
bboxes = tfe.bboxes_resize(distort_bbox, bboxes)
labels, bboxes = tfe.bboxes_filter_overlap(labels, bboxes,
threshold=BBOX_CROP_OVERLAP,
assign_negative=False)
return cropped_image, labels, bboxes, distort_bbox
def distorted_bounding_box_crop(image,
labels,
bboxes,
min_object_covered=0.3,
aspect_ratio_range=(0.9, 1.1),
area_range=(0.1, 1.0),
max_attempts=200,
clip_bboxes=True,
scope=None):
"""
#注意这个函数的解析表明的是使用其中一个随机扭曲的bbox生成cropped_image
Generates cropped_image using a one of the bboxes randomly distorted.
See `tf.image.sample_distorted_bounding_box` for more documentation.
Args:
#观察这些参数可以发现，这个函数实际是对一张图片的多个gt bbox中随机选择一个（暂时理解为ground truth bbox）进行随机扭曲，返回cropped_image和bbox等等
image: 3-D Tensor of image (it will be converted to floats in [0, 1]).
bbox: 3-D float Tensor of bounding boxes arranged [1, num_boxes, coords]
where each coordinate is [0, 1) and the coordinates are arranged
as [ymin, xmin, ymax, xmax]. If num_boxes is 0 then it would use the whole
image.
min_object_covered: An optional `float`. Defaults to `0.1`. The cropped
area of the image must contain at least this fraction of any bounding box
supplied.
aspect_ratio_range: An optional list of `floats`. The cropped area of the
image must have an aspect ratio = width / height within this range.
area_range: An optional list of `floats`. The cropped area of the image
must contain a fraction of the supplied image within in this range.
max_attempts: An optional `int`. Number of attempts at generating a cropped
region of the image of the specified constraints. After `max_attempts`
failures, return the entire image.
scope: Optional scope for name_scope.
#注意返回值是一个tuple，分别是cropped_image和distorted bbox，这个我们主要参考tf.image.sample_distorted_bounding_box的实现
Returns:
A tuple, a 3-D Tensor cropped_image and the distorted bbox
"""
with tf.name_scope(scope, 'distorted_bounding_box_crop', [image, bboxes]):
# Each bounding box has shape [1, num_boxes, box coords] and
# the coordinates are ordered [ymin, xmin, ymax, xmax].
# 为什么要用sample_distorted_bounding_box的原因在于可以随机的截取图片中一个块，减小需要关注的物体大小对图像识别算法的影响
# tf.image.sample_distorted_bounding_box的讲解主要参考：https://blog.csdn.net/tz_zs/article/details/77920116
# 需要注意的是，返回值的类型为：
# begin： 和 image_size 具有相同的类型。包含 [offset_height, offset_width, 0] 的一维数组。作为 tf.slice 的输入。
# size： 和 image_size 具有相同的类型。包含 [target_height, target_width, -1] 的一维数组。作为 tf.slice 的输入。
# 根据begin，size两个参数我们可以tf.slice出来我们所需要的裁剪出来的小图，而bboxes主要用于在图像上面的显示bbox工作！！！
# 那么为什么bboxes的shape为[1,1,4]呢？是不是因为tf.image.sample_distorted_bounding_box函数仅裁出来了一个bbox呢？
# bboxes：shape为 [1, 1, 4] 的三维矩阵，数据类型为float32，表示随机变形后的边界框。作为 tf.image.draw_bounding_boxes 的输入。
bbox_begin, bbox_size, distort_bbox = tf.image.sample_distorted_bounding_box(
tf.shape(image),
bounding_boxes=tf.expand_dims(bboxes, 0),
min_object_covered=min_object_covered,
aspect_ratio_range=aspect_ratio_range,
area_range=area_range,
max_attempts=max_attempts,
use_image_if_no_bounding_boxes=True)
distort_bbox = distort_bbox[0, 0]
# Crop the image to the specified bounding box.
# 注意tf.slice中的begin参数和size参数，begin.shape[-1]=0，size.shape[-1]=-1，可以由tf.image.sample_distorted_bouning_box中确定，
# 然后我们就可以从图像中裁剪我们所期望的小图！
cropped_image = tf.slice(image, bbox_begin, bbox_size)
# Restore the shape since the dynamic slice loses 3rd dimension.
cropped_image.set_shape([None, None, 3])
# Update bounding boxes: resize and filter out.
bboxes = tfe.bboxes_resize(distort_bbox, bboxes)
labels, bboxes = tfe.bboxes_filter_overlap(labels,
bboxes,
threshold=BBOX_CROP_OVERLAP,
assign_negative=False)
#注意我们的返回值cropped_image的shape为[None,None,３],不用担心，在后面preprocess_for_train中我们会怎样呢，对了没错，
#resize到ｓｓｄ所需要的大小，所以不用担心哈！
return cropped_image, labels, bboxes, distort_bbox
