def __create_label(self, bboxes):
"""
(1.25, 1.625), (2.0, 3.75), (4.125, 2.875) 这三个anchor用于small_detector预测小物体
[(1.875, 3.8125), (3.875, 2.8125), (3.6875, 7.4375) 这三个anchor用于medium_detector预测中物体
[(3.625, 2.8125), (4.875, 6.1875), (11.65625, 10.1875) 这三个anchor用于big_detector预测大物体
与bbox有最大IOU的anchor，视为best anchor，best anchor所属的detector负责预测该bbox，
根据这一准则，对于一张图的所有bbox，每个detector都有自己要负责预测的bbox
small_detector负责预测的bbox放在sbboxes中，
medium_detector负责预测的bbox放在mbboxes中
big_detector负责预测的bbox放在lbboxes中
需始终记住：
small_detector对应下标索引0， medium_detector对应下标索引1，big_detector对应下标索引2
:param bboxes: 一张图对应的所有bbox和每个bbox所属的类别，bbox的坐标为(xmin, ymin, xmax, ymax, class_ind)
:return:
label_sbbox: shape为(input_size / 8, input_size / 8, anchor_per_scale, 5 + num_classes)
label_mbbox: shape为(input_size / 16, input_size / 16, anchor_per_scale, 5 + num_classes)
label_lbbox: shape为(input_size / 32, input_size / 32, anchor_per_scale, 5 + num_classes)
只有best anchor对应位置的数据才为(x, y, w, h, 1, classes), (x, y, w, h)的大小是bbox纠正后的原始大小
其他非best anchor对应位置的数据都为(0, 0, 0, 0, 0, 0...)
sbboxes：shape为(max_bbox_per_scale, 4)
mbboxes：shape为(max_bbox_per_scale, 4)
lbboxes：shape为(max_bbox_per_scale, 4)
存储的坐标为(x, y, w, h)，(x, y, w, h)的大小都是bbox纠正后的原始大小
bboxes用于计算相应detector的预测框与该detector负责预测的所有bbox的IOU
"""
label = [np.zeros((self.__train_output_sizes[i], self.__train_output_sizes[i], self.__anchor_per_scale,
5 + self.__num_classes)) for i in range(3)]
bboxes_xywh = [np.zeros((self.__max_bbox_per_scale, 4)) for _ in range(3)]
bbox_count = np.zeros((3,))
for bbox in bboxes:
bbox_coor = bbox[:4]
bbox_class_ind = bbox[4]
# label smooth
onehot = np.zeros(self.__num_classes, dtype=np.float)
onehot[bbox_class_ind] = 1.0
uniform_distribution = np.full(self.__num_classes, 1.0 / self.__num_classes)
deta = 0.01
smooth_onehot = onehot * (1 - deta) + deta * uniform_distribution
# (1)(xmin, ymin, xmax, ymax) -> (x, y, w, h)
bbox_xywh = np.concatenate([(bbox_coor[2:] + bbox_coor[:2]) * 0.5, bbox_coor[2:] - bbox_coor[:2]], axis=-1)
# (2)(x, y, w, h) / stride
# 对bbox使用三种stride，得到三个detector对应的尺度
bbox_xywh_scaled = 1.0 * bbox_xywh[np.newaxis, :] / self.__strides[:, np.newaxis]
# (3)计算所有Anchor与该bbox的IOU，并获取最大IOU对应的best anchor
iou = []
exist_positive = False
for i in range(3):
anchors_xywh = np.zeros((self.__anchor_per_scale, 4))
anchors_xywh[:, 0:2] = np.floor(bbox_xywh_scaled[i, 0:2]).astype(np.int32) + 0.5
anchors_xywh[:, 2:4] = self.__anchors[i]
iou_scale = utils.iou_calc2(bbox_xywh_scaled[i][np.newaxis, :], anchors_xywh)
iou.append(iou_scale)
iou_mask = iou_scale > 0.3
if np.any(iou_mask):
xind, yind = np.floor(bbox_xywh_scaled[i, 0:2]).astype(np.int32)
# (4)将iou大于0.3的anchor对应位置的数据标识为(x, y, w, h, 1, classes)
# 首先需要将该Anchor对应的标签清零，因为某个Anchor可能与多个bbox的IOU大于0.3
# 如果不清零，那么该Anchor可能会被标记为多类
label[i][yind, xind, iou_mask, :] = 0
label[i][yind, xind, iou_mask, 0:4] = bbox_xywh
label[i][yind, xind, iou_mask, 4:5] = 1.0
label[i][yind, xind, iou_mask, 5:] = onehot
bbox_ind = int(bbox_count[i] % self.__max_bbox_per_scale)
bboxes_xywh[i][bbox_ind, :4] = bbox_xywh
bbox_count[i] += 1
exist_positive = True
if not exist_positive:
best_anchor_ind = np.argmax(np.array(iou).reshape(-1), axis=-1)
best_detect = int(best_anchor_ind / self.__anchor_per_scale)
best_anchor = int(best_anchor_ind % self.__anchor_per_scale)
xind, yind = np.floor(bbox_xywh_scaled[best_detect, 0:2]).astype(np.int32)
# (4)将best_anchor对应位置的数据标识为(x, y, w, h, 1, classes)
# 首先需要将该Anchor对应的标签清零，因为某个Anchor可能与多个bbox有最大IOU，
# 当输入图片尺寸为416时，与多个bbox有最大IOU的Anchor总共有248个
# 如果不清零，那么该Anchor可能会被标记为多类
label[best_detect][yind, xind, best_anchor, :] = 0
label[best_detect][yind, xind, best_anchor, 0:4] = bbox_xywh
label[best_detect][yind, xind, best_anchor, 4:5] = 1.0
label[best_detect][yind, xind, best_anchor, 5:] = onehot
bbox_ind = int(bbox_count[best_detect] % self.__max_bbox_per_scale)
bboxes_xywh[best_detect][bbox_ind, :4] = bbox_xywh
bbox_count[best_detect] += 1
label_sbbox, label_mbbox, label_lbbox = label
sbboxes, mbboxes, lbboxes = bboxes_xywh
return label_sbbox, label_mbbox, label_lbbox, sbboxes, mbboxes, lbboxes
def __create_label(self, bboxes):
"""
(1.25, 1.625), (2.0, 3.75), (4.125, 2.875) 这三个anchor用于small_detector预测小物体
[(1.875, 3.8125), (3.875, 2.8125), (3.6875, 7.4375) 这三个anchor用于medium_detector预测中物体
[(3.625, 2.8125), (4.875, 6.1875), (11.65625, 10.1875) 这三个anchor用于big_detector预测大物体
与bbox有最大IOU的anchor，视为best anchor，best anchor所属的detector负责预测该bbox，
根据这一准则，对于一张图的所有bbox，每个detector都有自己要负责预测的bbox
small_detector负责预测的bbox放在sbboxes中，
medium_detector负责预测的bbox放在mbboxes中
big_detector负责预测的bbox放在lbboxes中
需始终记住：
small_detector对应下标索引0， medium_detector对应下标索引1，big_detector对应下标索引2
:param bboxes: 一张图对应的所有bbox和每个bbox所属的类别，bbox的坐标为(xmin, ymin, xmax, ymax, class_ind)
:return:
label_sbbox: shape为(input_size / 8, input_size / 8, anchor_per_scale, 5 + num_classes)
label_mbbox: shape为(input_size / 16, input_size / 16, anchor_per_scale, 5 + num_classes)
label_lbbox: shape为(input_size / 32, input_size / 32, anchor_per_scale, 5 + num_classes)
只有best anchor对应位置的数据才为(x, y, w, h, 1, classes), (x, y, w, h)的大小是bbox纠正后的原始大小
其他非best anchor对应位置的数据都为(0, 0, 0, 0, 0, 0...)
sbboxes：shape为(max_bbox_per_scale, 4)
mbboxes：shape为(max_bbox_per_scale, 4)
lbboxes：shape为(max_bbox_per_scale, 4)
存储的坐标为(x, y, w, h)，(x, y, w, h)的大小都是bbox纠正后的原始大小
bboxes用于计算相应detector的预测框与该detector负责预测的所有bbox的IOU
"""
label = [np.zeros((self.__train_output_sizes[i], self.__train_output_sizes[i], self.__anchor_per_scale,
5 + self.__num_classes)) for i in range(3)]
bboxes_xywh = [np.zeros((self.__max_bbox_per_scale, 4)) for _ in range(3)]
bbox_count = np.zeros((3,))
for bbox in bboxes:
bbox_coor = bbox[:4]
bbox_class_ind = bbox[4]
# (1)(xmin, ymin, xmax, ymax) -> (x, y, w, h)
bbox_xywh = np.concatenate([(bbox_coor[2:] + bbox_coor[:2]) * 0.5, bbox_coor[2:] - bbox_coor[:2]], axis=-1)
# (2)(x, y, w, h) / stride
# 对bbox使用三种stride，得到三个detector对应的尺度
bbox_xywh_scaled = 1.0 * bbox_xywh[np.newaxis, :] / self.__strides[:, np.newaxis]
# (3)计算所有Anchor与该bbox的IOU，并获取最大IOU对应的best anchor
iou = []
for i in range(3):
anchors_xywh = np.zeros((self.__anchor_per_scale, 4))
anchors_xywh[:, 0:2] = np.floor(bbox_xywh_scaled[i, 0:2]).astype(np.int32) + 0.5
anchors_xywh[:, 2:4] = self.__anchors[i]
iou.append(utils.iou_calc2(bbox_xywh_scaled[i][np.newaxis, :], anchors_xywh))
best_anchor_ind = np.argmax(np.array(iou).reshape(-1), axis=-1)
best_detect = int(best_anchor_ind / self.__anchor_per_scale)
best_anchor = int(best_anchor_ind % self.__anchor_per_scale)
xind, yind = np.floor(bbox_xywh_scaled[best_detect, 0:2]).astype(np.int32)
# (4)将best_anchor对应位置的数据标识为(x, y, w, h, 1, classes)
label[best_detect][yind, xind, best_anchor, 0:4] = bbox_xywh
label[best_detect][yind, xind, best_anchor, 4:5] = 1.0
label[best_detect][yind, xind, best_anchor, 5 + bbox_class_ind] = 1.0
bbox_ind = int(bbox_count[best_detect] % self.__max_bbox_per_scale)
bboxes_xywh[best_detect][bbox_ind, :4] = bbox_xywh
bbox_count[best_detect] += 1
label_sbbox, label_mbbox, label_lbbox = label
sbboxes, mbboxes, lbboxes = bboxes_xywh
return label_sbbox, label_mbbox, label_lbbox, sbboxes, mbboxes, lbboxes