def initialize(self):
self.anchors = get_anchors_for_preset(self.preset)
self.vheight = len(self.anchors)
self.vwidth = self.num_classes + 5 # background class + location offsets
self.img_size = Size(1000, 1000)
self.anchors_arr = anchors2array(self.anchors, self.img_size)
self.initialized = True
def __call__(self, data, label, gt):
#-----------------------------------------------------------------------
# Check whether to sample or not
#-----------------------------------------------------------------------
if not self.sample:
return data, label, gt
#-----------------------------------------------------------------------
# Retry sampling a couple of times
#-----------------------------------------------------------------------
source_boxes = anchors2array(gt.boxes, gt.imgsize)
box = None
box_arr = None
for _ in range(self.max_trials):
#-------------------------------------------------------------------
# Sample a bounding box
#-------------------------------------------------------------------
scale = random.uniform(self.min_scale, self.max_scale)
aspect_ratio = random.uniform(self.min_aspect_ratio,
self.max_aspect_ratio)
# make sure width and height will not be larger than 1
aspect_ratio = max(aspect_ratio, scale**2)
aspect_ratio = min(aspect_ratio, 1 / (scale**2))
width = scale * sqrt(aspect_ratio)
height = scale / sqrt(aspect_ratio)
cx = 0.5 * width + random.uniform(0, 1 - width)
cy = 0.5 * height + random.uniform(0, 1 - height)
center = Point(cx, cy)
size = Size(width, height)
#-------------------------------------------------------------------
# Check if the box satisfies the jaccard overlap constraint
#-------------------------------------------------------------------
box_arr = np.array(prop2abs(center, size, gt.imgsize))
overlap = compute_overlap(box_arr, source_boxes, 0)
if overlap.best and overlap.best.score >= self.min_jaccard_overlap:
box = Box(None, None, center, size)
break
if box is None:
return None
#-----------------------------------------------------------------------
# Crop the box and adjust the ground truth
#-----------------------------------------------------------------------
new_size = Size(box_arr[1] - box_arr[0], box_arr[3] - box_arr[2])
w_off = -box_arr[0]
h_off = -box_arr[2]
data = data[box_arr[2]:box_arr[3], box_arr[0]:box_arr[1]]
gt = transform_gt(gt, new_size, h_off, w_off)
return data, label, gt
def __call__(self, data, label, gt):
if not self.initialized:
self.initialize()
box_cordinate = list()
gt_label = list()
for boxes in gt.boxes:
box = Anchor(Point(boxes[2][0], boxes[2][1]),
Size(boxes[3][0], boxes[3][1]))
box_cordinate.append(box)
gt_label.append(boxes[1])
box_arr = anchors2array(box_cordinate,
self.img_size) # gt h,w over 300?
vec = np.zeros((100 - len(box_arr), 4), dtype=np.double)
label = np.zeros(100 - len(box_arr), dtype=np.int64)
vec = np.r_[box_arr, vec]
label = np.r_[gt_label, label]
return data, gt.filename, label, tuple(gt.imgsize), vec #, gt[1]
def __call__(self, data, label, gt):
#-----------------------------------------------------------------------
# Check whether to sample or not
#-----------------------------------------------------------------------
if not self.sample:
return data, label, gt
#-----------------------------------------------------------------------
# Retry sampling a couple of times
#-----------------------------------------------------------------------
source_boxes = anchors2array(
gt.boxes, gt.imgsize) # get abs value(xmin,xmax,ymin,ymax)
box = None
box_arr = None
for _ in range(self.max_trials):
#-------------------------------------------------------------------
# Sample a bounding box
#-------------------------------------------------------------------
# min_scale=0.3, max_scale=1.0,
# min_aspect_ratio=0.5, max_aspect_ratio=2.0,
scale = random.uniform(self.min_scale, self.max_scale)
aspect_ratio = random.uniform(self.min_aspect_ratio,
self.max_aspect_ratio)
# make sure width and height will not be larger than 1
aspect_ratio = max(aspect_ratio, scale**2)
aspect_ratio = min(aspect_ratio, 1 / (scale**2))
width = scale * sqrt(aspect_ratio)
height = scale / sqrt(aspect_ratio)
cx = 0.5 * width + random.uniform(0, 1 - width)
cy = 0.5 * height + random.uniform(0, 1 - height)
center = Point(cx, cy)
size = Size(width, height)
#-------------------------------------------------------------------
# Check if the box satisfies the jaccard overlap constraint
#-------------------------------------------------------------------
box_arr = np.array(prop2abs(center, size, gt.imgsize))
overlap = compute_overlap(box_arr, source_boxes, 0)
if overlap.best and overlap.best.score >= self.min_jaccard_overlap:
box = Box(None, None, center, size)
break
if box is None:
return None
#-----------------------------------------------------------------------
# Crop the box and adjust the ground truth
#-----------------------------------------------------------------------
new_size = Size(box_arr[1] - box_arr[0], box_arr[3] - box_arr[2])
w_off = -box_arr[0]
h_off = -box_arr[2]
data = data.crop(
(box_arr[0], box_arr[2], box_arr[1], box_arr[3])
) # gt와 gt근처의 가상의 anchor를 잡은뒤, iou 0.1, 0.3, 0.5, 0.7, 0.9 이상이면 그 가상의 anchor부분을 crop하고 gt 좌표도 같이 변경
# 즉 일부로 gt와 iou 연관있는 그림부분을 crop함
gt = transform_gt(gt, new_size, h_off, w_off)
return data, label, gt # change gt and image_size
