def __init__(self, anno_file, anno_file_type, img_size=416):
self.img_size = img_size # For Multi-training
if cfg.TRAIN.DATA_TYPE == 'VOC':
self.classes = cfg.VOC_DATA.CLASSES
elif cfg.TRAIN.DATA_TYPE == 'COCO':
self.classes = cfg.COCO_DATA.CLASSES
else:
self.classes = cfg.DATASET.CLASSES
self.cross_offset = 0.2
self.num_classes = len(self.classes)
self.class_to_id = dict(zip(self.classes, range(self.num_classes)))
self.__annotations = self.__load_annotations(anno_file, anno_file_type)
self.hue_jitter = 0.005
self.bright_jitter = 0.25
self.sat_jitter = 0.25
self.label_smooth = dataAug.LabelSmooth()
self.bbox_minsize = 40
def __creat_label(self, bboxes):
"""
Label assignment. For a single picture all GT box bboxes are assigned anchor.
1、Select a bbox in order, convert its coordinates("xyxy") to "xywh"; and scale bbox'
xywh by the strides.
2、Calculate the iou between the each detection layer'anchors and the bbox in turn, and select the largest
anchor to predict the bbox.If the ious of all detection layers are smaller than 0.3, select the largest
of all detection layers' anchors to predict the bbox.
Note :
1、The same GT may be assigned to multiple anchors. And the anchors may be on the same or different layer.
2、The total number of bboxes may be more than it is, because the same GT may be assigned to multiple layers
of detection.
"""
anchors = np.array(cfg.MODEL["ANCHORS"])
strides = np.array(cfg.MODEL["STRIDES"])
train_output_size = self.img_size / strides
anchors_per_scale = cfg.MODEL["ANCHORS_PER_SCLAE"]
label = [
np.zeros(
(
int(train_output_size[i]),
int(train_output_size[i]),
anchors_per_scale,
6 + self.num_classes,
)
)
for i in range(3)
]
for i in range(3):
label[i][..., 5] = 1.0
bboxes_xywh = [
np.zeros((150, 4)) for _ in range(3)
] # Darknet the max_num is 30
bbox_count = np.zeros((3,))
for bbox in bboxes:
bbox_coor = bbox[:4]
bbox_class_ind = int(bbox[4])
bbox_mix = bbox[5]
# onehot
one_hot = np.zeros(self.num_classes, dtype=np.float32)
one_hot[bbox_class_ind] = 1.0
one_hot_smooth = dataAug.LabelSmooth()(one_hot, self.num_classes)
# convert "xyxy" to "xywh"
bbox_xywh = np.concatenate(
[
(bbox_coor[2:] + bbox_coor[:2]) * 0.5,
bbox_coor[2:] - bbox_coor[:2],
],
axis=-1,
)
# print("bbox_xywh: ", bbox_xywh)
bbox_xywh_scaled = (
1.0 * bbox_xywh[np.newaxis, :] / strides[:, np.newaxis]
)
iou = []
exist_positive = False
for i in range(3):
anchors_xywh = np.zeros((anchors_per_scale, 4))
anchors_xywh[:, 0:2] = (
np.floor(bbox_xywh_scaled[i, 0:2]).astype(np.int32) + 0.5
) # 0.5 for compensation
anchors_xywh[:, 2:4] = anchors[i]
iou_scale = tools.iou_xywh_numpy(
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
)
# Bug : 当多个bbox对应同一个anchor时，默认将该anchor分配给最后一个bbox
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, 5:6] = bbox_mix
label[i][yind, xind, iou_mask, 6:] = one_hot_smooth
bbox_ind = int(bbox_count[i] % 150) # BUG : 150为一个先验值,内存消耗大
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 / anchors_per_scale)
best_anchor = int(best_anchor_ind % anchors_per_scale)
xind, yind = np.floor(
bbox_xywh_scaled[best_detect, 0:2]
).astype(np.int32)
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, 5:6] = bbox_mix
label[best_detect][yind, xind, best_anchor, 6:] = one_hot_smooth
bbox_ind = int(bbox_count[best_detect] % 150)
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 creat_label(self, bboxes):
"""
Label assignment. For a single picture all GT box bboxes are assigned anchor.
1、Select a bbox in order, convert its coordinates("xyxy") to "xywh"; and scale bbox'
xywh by the strides.
2、Calculate the iou between the each detection layer'anchors and the bbox in turn, and select the largest
anchor to predict the bbox.If the ious of all detection layers are smaller than 0.3, select the largest
of all detection layers' anchors to predict the bbox.
Note :
1、The same GT may be assigned to multiple anchors. And the anchors may be on the same or different layer. Pai : even the same cell
2、The total number of bboxes may be more than it is, because the same GT may be assigned to multiple layers
of detection.
"""
anchors = np.array(self.cfg_MODEL["ANCHORS"])
strides = np.array(self.cfg_MODEL["STRIDES"])
train_output_size = self.img_size / strides
anchors_per_scale = self.cfg_MODEL["ANCHORS_PER_SCLAE"]
label = [
np.zeros((int(train_output_size[i]), int(train_output_size[i]),
anchors_per_scale, 6 + self.num_classes))
for i in range(3)
]
# label = [np,np.np] each have size = grid,grid, anchors_per_scale, 6+self.num_classes
for i in range(3):
label[i][..., 5] = 1.0
bboxes_xywh = [np.zeros((150, 4))
for _ in range(3)] # Darknet the max_num is 30
bbox_count = np.zeros((3, ))
for bbox in bboxes: # start one by one gt box
bbox_coor = bbox[:4]
bbox_class_ind = int(bbox[4])
bbox_mix = bbox[5]
# onehot
one_hot = np.zeros(self.num_classes, dtype=np.float32)
one_hot[bbox_class_ind] = 1.0
one_hot_smooth = dataAug.LabelSmooth()(one_hot, self.num_classes)
# convert "xyxy" to "xywh"
bbox_xywh = np.concatenate([(bbox_coor[2:] + bbox_coor[:2]) * 0.5,
bbox_coor[2:] - bbox_coor[:2]],
axis=-1)
# print("bbox_xywh: ", bbox_xywh)
bbox_xywh_scaled = 1.0 * bbox_xywh[
np.
newaxis, :] / strides[:, np.
newaxis] # scale gt box to grid unit sp shape = [3,4] each row is at diferent scale. 1 grind size is 8, 16 ,32
iou = []
exist_positive = False
for i in range(3): # we have 3 scales
anchors_xywh = np.zeros((anchors_per_scale, 4))
anchors_xywh[:,
0:2] = np.floor(bbox_xywh_scaled[i, 0:2]).astype(
np.int32) + 0.5 # 0.5 for compensation
anchors_xywh[:, 2:4] = anchors[i]
iou_scale = tools.iou_xywh_numpy(
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)
# Bug : When multiple gt bboxes correspond to the same anchor, the anchor is assigned to the last bbox by default
label[i][
yind, xind, iou_mask, 0:
4] = bbox_xywh # Pai: this means the 3 anchors in that cell can be responsible to the boxes. Not choose one in this code
label[i][
yind, xind, iou_mask, 4:
5] = 1.0 # You seeeeeeeeeeee the confidence for the gt = 1 kuayyyyyyyyyyyy finally i got the answer
label[i][yind, xind, iou_mask, 5:6] = bbox_mix
label[i][yind, xind, iou_mask, 6:] = one_hot_smooth
bbox_ind = int(
bbox_count[i] % 150
) # BUG : 150 is a prior value, memory consumption is large
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 / anchors_per_scale)
best_anchor = int(best_anchor_ind % anchors_per_scale)
xind, yind = np.floor(bbox_xywh_scaled[best_detect,
0:2]).astype(np.int32)
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, 5:6] = bbox_mix
label[best_detect][yind, xind, best_anchor,
6:] = one_hot_smooth
bbox_ind = int(bbox_count[best_detect] % 150)
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