def prepare_data(roidb, aug, aug_type="default", is_unlabled=False):
fname, boxes, klass, is_crowd, img_id = roidb["file_name"], roidb[
"boxes"], roidb["class"], roidb["is_crowd"], roidb["image_id"]
assert boxes.ndim == 2 and boxes.shape[1] == 4, boxes.shape
boxes = np.copy(boxes)
im = cv2.imread(fname, cv2.IMREAD_COLOR)
assert im is not None, fname
im = im.astype("float32")
height, width = im.shape[:2]
# assume floatbox as input
assert boxes.dtype == np.float32, "Loader has to return float32 boxes!"
if not self.cfg.DATA.ABSOLUTE_COORD:
boxes[:, 0::2] *= width
boxes[:, 1::2] *= height
ret = {}
if not is_unlabled and aug_type == "default":
tfms = aug.get_transform(im)
im = tfms.apply_image(im)
points = box_to_point8(boxes)
points = tfms.apply_coords(points)
boxes = point8_to_box(points)
else:
# It is strong augmentation
# Load box informaiton from disk
if is_unlabled:
pseudo_target = self.get_pseudo_gt(img_id)
# has no pseudo target found
assert pseudo_target is not None
boxes = pseudo_target["boxes"]
klass = pseudo_target["labels"].astype(np.int32)
assert len(
boxes) > 0, "boxes after thresholding becomes to zero"
is_crowd = np.array(
[0] * len(klass)) # do not ahve crowd annotations
else:
# it is labeled data, use boxes loaded from roidb, klass, is_crowd
pass
if aug_type == "default":
# use default augmentations, only happend for unlabeled data
tfms = self.aug.get_transform(im)
im = tfms.apply_image(im)
points = box_to_point8(boxes)
points = tfms.apply_coords(points)
boxes = point8_to_box(points)
# is_crowd = np.array([0]*len(klass)) # do not ahve crowd annotations
else:
# use strong augmentation with extra packages
# resize first
tfms = self.resize.get_transform(im)
im = tfms.apply_image(im)
points = box_to_point8(boxes)
points = tfms.apply_coords(points)
boxes = point8_to_box(points)
boxes_backup = boxes.copy()
h, w = im.shape[:2]
# strong augmentation
try:
assert len(
boxes) > 0, "boxes after resizing becomes to zero"
assert np.sum(
np_area(boxes)) > 0, "boxes are all zero area!"
bbs = array_to_bb(boxes)
images_aug, bbs_aug, _ = aug(images=[im],
bounding_boxes=[bbs],
n_real_box=len(bbs))
# # convert to gt boxes array
boxes = bb_to_array(bbs_aug[0])
boxes[:, 0] = np.clip(boxes[:, 0], 0, w)
boxes[:, 1] = np.clip(boxes[:, 1], 0, h)
boxes[:, 2] = np.clip(boxes[:, 2], 0, w)
boxes[:, 3] = np.clip(boxes[:, 3], 0, h)
# after affine, some boxes can be zero area. Let's remove them and their corresponding info
boxes, mask = remove_empty_boxes(boxes)
klass = klass[mask]
is_crowd = is_crowd[mask]
assert len(
klass
) > 0, "Empty boxes and kclass after removing empty ones"
assert klass.max() <= self.cfg.DATA.NUM_CATEGORY, \
"Invalid category {}!".format(klass.max())
assert np.min(
np_area(boxes)) > 0, "Some boxes have zero area!"
im = images_aug[0]
except Exception as e:
# if augmentation makes the boxes become empty, we switch to
# non-augmented one
# logger.warn("Error catched " + str(e) +
# "\n Use non-augmented data.")
boxes = boxes_backup
ret["image"] = im
# Add rpn data to dataflow:
if self.cfg.MODE_FPN:
multilevel_anchor_inputs = self.get_multilevel_rpn_anchor_input(
im, boxes, is_crowd)
for i, (anchor_labels,
anchor_boxes) in enumerate(multilevel_anchor_inputs):
ret["anchor_labels_lvl{}".format(i + 2)] = anchor_labels
ret["anchor_boxes_lvl{}".format(i + 2)] = anchor_boxes
else:
ret["anchor_labels"], ret[
"anchor_boxes"] = self.get_rpn_anchor_input(
im, boxes, is_crowd)
boxes = boxes[is_crowd == 0] # skip crowd boxes in training target
klass = klass[is_crowd == 0]
ret["gt_boxes"] = boxes
ret["gt_labels"] = klass
if is_unlabled:
ret["proposals_boxes"] = pseudo_target["proposals_boxes"]
# ret["proposals_scores"] = pseudo_target['proposals_scores']
return ret
def remove_empty_boxes(boxes):
areas = np_area(boxes)
mask = areas > 0
return boxes[mask], mask
def __call__(self, roidb): #
fname, boxes, klass, is_crowd = roidb["file_name"], roidb[
"boxes"], roidb["class"], roidb["is_crowd"]
assert boxes.ndim == 2 and boxes.shape[1] == 4, boxes.shape
boxes = np.copy(boxes)
im = cv2.imread(fname, cv2.IMREAD_COLOR)
assert im is not None, fname
im = im.astype("float32")
height, width = im.shape[:2]
# assume floatbox as input
assert boxes.dtype == np.float32, "Loader has to return float32 boxes!"
if not self.cfg.DATA.ABSOLUTE_COORD:
boxes[:, 0::2] *= width
boxes[:, 1::2] *= height
ret = {}
tfms = self.aug_weak.get_transform(im)
im = tfms.apply_image(im)
points = box_to_point8(boxes)
points = tfms.apply_coords(points)
boxes = point8_to_box(points)
h, w = im.shape[:2]
if self.aug_type != "default":
boxes_backup = boxes.copy()
try:
assert len(boxes) > 0, "boxes after resizing becomes to zero"
assert np.sum(np_area(boxes)) > 0, "boxes are all zero area!"
bbs = array_to_bb(boxes)
images_aug, bbs_aug, _ = self.aug_strong(images=[im],
bounding_boxes=[bbs],
n_real_box=len(bbs))
# convert to gt boxes array
boxes = bb_to_array(bbs_aug[0])
boxes[:, 0] = np.clip(boxes[:, 0], 0, w)
boxes[:, 1] = np.clip(boxes[:, 1], 0, h)
boxes[:, 2] = np.clip(boxes[:, 2], 0, w)
boxes[:, 3] = np.clip(boxes[:, 3], 0, h)
# after affine, some boxes can be zero area. Let's remove them and their corresponding info
boxes, mask = remove_empty_boxes(boxes)
klass = klass[mask]
assert len(
klass
) > 0, "Empty boxes and kclass after removing empty ones"
is_crowd = np.array(
[0] * len(klass)) # do not ahve crowd annotations
assert klass.max() <= self.cfg.DATA.NUM_CATEGORY, \
"Invalid category {}!".format(klass.max())
assert np.min(np_area(boxes)) > 0, "Some boxes have zero area!"
im = images_aug[0]
except Exception as e:
logger.warn("Error catched " + str(e) +
"\n Use non-augmented data.")
boxes = boxes_backup
ret["image"] = im
try:
# Add rpn data to dataflow:
if self.cfg.MODE_FPN:
multilevel_anchor_inputs = self.get_multilevel_rpn_anchor_input(
im, boxes, is_crowd)
for i, (anchor_labels,
anchor_boxes) in enumerate(multilevel_anchor_inputs):
ret["anchor_labels_lvl{}".format(i + 2)] = anchor_labels
ret["anchor_boxes_lvl{}".format(i + 2)] = anchor_boxes
else:
ret["anchor_labels"], ret[
"anchor_boxes"] = self.get_rpn_anchor_input(
im, boxes, is_crowd)
boxes = boxes[is_crowd == 0] # skip crowd boxes in training target
klass = klass[is_crowd == 0]
ret["gt_boxes"] = boxes
ret["gt_labels"] = klass
except Exception as e:
log_once(
"Input {} is filtered for training: {}".format(fname, str(e)),
"warn")
return None
return ret