def encode(self, boxes, labels):
'''Encode target bounding boxes and class labels.
We obey the Faster RCNN box coder:
tx = (x - anchor_x) / anchor_w
ty = (y - anchor_y) / anchor_h
tw = log(w / anchor_w)
th = log(h / anchor_h)
Args:
boxes: (tensor) bounding boxes of (xmin,ymin,xmax,ymax), sized [#obj, 4].
labels: (tensor) object class labels, sized [#obj,].
Returns:
loc_targets: (tensor) encoded bounding boxes, sized [#anchors,4].
cls_targets: (tensor) encoded class labels, sized [#anchors,].
'''
anchor_boxes = self.anchor_boxes
ious = box_iou(anchor_boxes, boxes)
max_ious, max_ids = ious.max(1)
boxes = boxes[max_ids]
boxes = change_box_order(boxes, 'xyxy2xywh')
anchor_boxes = change_box_order(anchor_boxes, 'xyxy2xywh')
loc_xy = (boxes[:, :2] - anchor_boxes[:, :2]) / anchor_boxes[:, 2:]
loc_wh = torch.log(boxes[:, 2:] / anchor_boxes[:, 2:])
loc_targets = torch.cat([loc_xy, loc_wh], 1)
cls_targets = 1 + labels[max_ids]
# cls_targets[max_ious<0.5] = 0
# ignore = (max_ious>0.4) & (max_ious<0.5) # ignore ious between [0.4,0.5]
# cls_targets[ignore] = -1 # mark ignored to -1
return loc_targets, cls_targets
def encode(self, boxes, labels):
'''Encode target bounding boxes and class labels.
SSD coding rules:
tx = (x - anchor_x) / (variance[0]*anchor_w)
ty = (y - anchor_y) / (variance[0]*anchor_h)
tw = log(w / anchor_w) / variance[1]
th = log(h / anchor_h) / variance[1]
Args:
boxes: (tensor) bounding boxes of (xmin,ymin,xmax,ymax), sized [#obj, 4].
labels: (tensor) object class labels, sized [#obj,].
Returns:
loc_targets: (tensor) encoded bounding boxes, sized [#anchors,4].
cls_targets: (tensor) encoded class labels, sized [#anchors,].
Reference:
https://github.com/chainer/chainercv/blob/master/chainercv/links/model/ssd/multibox_coder.py
'''
def argmax(x):
'''Find the max value index(row & col) of a 2D tensor.'''
v, i = x.max(0)
j = v.max(0)[1].item()
return (i[j], j)
default_boxes = self.default_boxes_new # xywh
default_boxes = change_box_order(default_boxes, 'xywh2xyxy')
ious = box_iou(default_boxes, boxes) # [#anchors, #obj]
index = torch.LongTensor(len(default_boxes)).fill_(-1)
masked_ious = ious.clone()
while True:
i, j = argmax(masked_ious)
if masked_ious[i, j] < 1e-6:
break
index[i] = j
masked_ious[i, :] = 0
masked_ious[:, j] = 0
mask = (index < 0) & (ious.max(1)[0] >= 0.5)
if mask.any():
index[mask] = ious[mask.nonzero().squeeze()].max(1)[1]
boxes = boxes[index.clamp(min=0)] # negative index not supported
boxes = change_box_order(boxes, 'xyxy2xywh')
default_boxes = change_box_order(default_boxes, 'xyxy2xywh')
variances = (0.1, 0.2)
loc_xy = (boxes[:, :2] -
default_boxes[:, :2]) / default_boxes[:, 2:] / variances[0]
loc_wh = torch.log(boxes[:, 2:] / default_boxes[:, 2:]) / variances[1]
loc_targets = torch.cat([loc_xy, loc_wh], 1)
cls_targets = 1 + labels[index.clamp(min=0)]
cls_targets[index < 0] = 0
return loc_targets, cls_targets
def encode(self, boxes, labels):
def argmax(x):
v, i = x.max(0)
# j = v.max(0)[1][0]
j = v.max(0)[1].item()
return (i[j], j) # 第j个obj 以及第j个obj的最大anchors坐标
default_boxes = self.default_boxes # xywh
default_boxes = change_box_order(default_boxes, 'xywh2xyxy')
ious = box_iou(default_boxes, boxes) # [#anchors, #obj]
index = torch.LongTensor(len(default_boxes)).fill_(
-1) # 与anchor匹配的boxes坐标
masked_ious = ious.clone()
while True:
i, j = argmax(masked_ious)
if masked_ious[i, j] < 1e-6:
break
index[i] = j #设置与anchor匹配度的boxes坐标
masked_ious[i, :] = 0 # 设置设置过得roi为0，表示已经搜索过次roi， 对应于while里的条件
masked_ious[:, j] = 0
mask = (index < 0) & (
ious.max(1)[0] >= 0.5
) # 没有在第一次进行匹配到的 并且 对于每一个anchor与任何boxes的roi大于0.5的
if mask.any(): # 如果存在
# index[mask] = ious[mask.nonzero().squeeze()].max(1)[1]
index[mask] = ious[mask].max(1)[1] #设置匹配 【1】表示使用坐标位置 对应于58行
boxes = boxes[index.clamp(min=0)] # negative index not supported
boxes = change_box_order(boxes, 'xyxy2xywh')
default_boxes = change_box_order(default_boxes, 'xyxy2xywh')
variances = (0.1, 0.2)
loc_xy = (boxes[:, :2] -
default_boxes[:, :2]) / default_boxes[:, 2:] / variances[0]
loc_wh = torch.log(boxes[:, 2:] / default_boxes[:, 2:]) / variances[1]
loc_targets = torch.cat([loc_xy, loc_wh], 1)
cls_targets = 1 + labels[index.clamp(min=0)]
cls_targets[index < 0] = 0
return loc_targets, cls_targets # cls>0 的是正样本 其他为0 ； loc在cls=0的地方是无效值
def encode_(self, image, boxes, labels):
'''Encode target bounding boxes and class labels.
We obey the Faster RCNN box coder:
tx = (x - anchor_x) / anchor_w
ty = (y - anchor_y) / anchor_h
tw = log(w / anchor_w)
th = log(h / anchor_h)
Args:
boxes: (tensor) bounding boxes of (xmin,ymin,xmax,ymax), sized [#obj, 4].
labels: (tensor) object class labels, sized [#obj,].
input_size: (tuple) model input size of (w,h).
Returns:
loc_targets: (tensor) encoded bounding boxes, sized [#anchors,4].
cls_targets: (tensor) encoded class labels, sized [#anchors,].
'''
anchor_boxes = self.default_boxes # xywh
anchor_boxes = change_box_order(anchor_boxes, 'xywh2xyxy')
default_boxes_ = anchor_boxes
ious = box_iou(anchor_boxes, boxes)
max_ious, max_ids = ious.max(1)
boxes = boxes[max_ids]
boxes = change_box_order(boxes, 'xyxy2xywh')
anchor_boxes = change_box_order(anchor_boxes, 'xyxy2xywh')
variances = (0.1, 0.2)
# variances = (1, 1)
loc_xy = (boxes[:, :2] -
anchor_boxes[:, :2]) / anchor_boxes[:, 2:] / variances[0]
loc_wh = torch.log(boxes[:, 2:] / anchor_boxes[:, 2:]) / variances[1]
loc_targets = torch.cat([loc_xy, loc_wh], 1)
cls_targets = 1 + labels[max_ids]
cls_targets[max_ious < 0.5] = 0
ignore = (max_ious > 0.4) & (max_ious < 0.5
) # ignore ious between [0.4,0.5]
cls_targets[ignore] = -1 # mark ignored to -1
# return loc_targets, cls_targets, self.default_boxes, default_boxes_
return loc_targets, cls_targets
def encode(self, boxes, labels, input_size):
"""Encode target bounding boxes and class labels.
We obey the Faster RCNN box coder:
tx = (x - anchor_x) / anchor_w
ty = (y - anchor_y) / anchor_h
tw = log(w / anchor_w)
th = log(h / anchor_h)
Args:
boxes: (tensor) bounding boxes of (xmin, ymin, xmax, ymax), sized [#obj, 4].
labels: (tensor) object class labels, sized [#obj, ].
input_size: (int/tuple) model input size of (w, h), should be the same.
Returns:
loc_trues: (tensor) encoded bounding boxes, sized [#anchors, 4].
cls_trues: (tensor) encoded class labels, sized [#anchors, ].
"""
input_size = _make_list_input_size(input_size)
boxes = tf.reshape(boxes, [-1, 4])
anchor_boxes = self._get_anchor_boxes(input_size)
boxes = change_box_order(boxes, 'xyxy2xywh')
boxes *= tf.tile(input_size, [2]) # scaled back to original size
ious = box_iou(anchor_boxes, boxes, order='xywh')
max_ids = tf.argmax(ious, axis=1)
max_ious = tf.reduce_max(ious, axis=1)
boxes = tf.gather(boxes,
max_ids) # broadcast automatically, [#anchors, 4]
loc_xy = (boxes[:, :2] - anchor_boxes[:, :2]) / anchor_boxes[:, 2:]
loc_wh = tf.log(boxes[:, 2:] / anchor_boxes[:, 2:])
loc_trues = tf.concat([loc_xy, loc_wh], 1)
cls_trues = tf.gather(labels,
max_ids) # TODO: check if needs add 1 here
cls_trues = tf.where(max_ious < 0.5, tf.zeros_like(cls_trues),
cls_trues)
ignore = (max_ious > 0.4) & (
max_ious < 0.5) # ignore ious between (0.4, 0.5), and marked as -1
cls_trues = tf.where(ignore, tf.ones_like(cls_trues) * -1, cls_trues)
cls_trues = tf.cast(cls_trues, tf.float32)
return loc_trues, cls_trues
def decode(self, loc_preds, cls_preds, score_thresh=0.6, nms_thresh=0.45):
'''Decode predicted loc/cls back to real box locations and class labels.
Args:
loc_preds: (tensor) predicted loc, sized [#anchors,4].
cls_preds: (tensor) predicted conf, sized [#anchors,#classes].
score_thresh: (float) threshold for object confidence score.
nms_thresh: (float) threshold for box nms.
Returns:
boxes: (tensor) bbox locations, sized [#obj,4].
labels: (tensor) class labels, sized [#obj,].
'''
anchor_boxes = change_box_order(self.anchor_boxes, 'xyxy2xywh')
xy = loc_preds[:, :2] * anchor_boxes[:, 2:] + anchor_boxes[:, :2]
wh = loc_preds[:, 2:].exp() * anchor_boxes[:, 2:]
box_preds = torch.cat([xy - wh / 2, xy + wh / 2], 1)
boxes = []
labels = []
scores = []
num_classes = cls_preds.size(1)
for i in range(num_classes - 1):
score = cls_preds[:, i + 1] # class i corresponds to (i+1) column
mask = score > score_thresh
if not mask.any():
continue
box = box_preds[mask]
score = score[mask]
# print(box.size())
# print(score.size())
keep = box_nms(box, score, nms_thresh)
boxes.append(box[keep])
labels.append(torch.empty_like(keep).fill_(i))
scores.append(score[keep])
boxes = torch.cat(boxes, 0)
labels = torch.cat(labels, 0)
scores = torch.cat(scores, 0)
return boxes, labels, scores
def encode(self,
boxes,
labels,
input_size,
pos_iou_threshold=0.5,
neg_iou_threshold=0.4):
"""Encode target bounding boxes and class labels.
We obey the Faster RCNN box coder:
tx = (x - anchor_x) / anchor_w
ty = (y - anchor_y) / anchor_h
tw = log(w / anchor_w)
th = log(h / anchor_h)
Args:
boxes: (tensor) bounding boxes of (xmin, ymin, xmax, ymax), sized [#obj, 4].
labels: (tensor) object class labels, sized [#obj, ].
input_size: (int/tuple) model input size of (w, h), should be the same.
Returns:
loc_trues: (tensor) encoded bounding boxes, sized [#anchors, 4].
cls_trues: (tensor) encoded class labels, sized [#anchors, ].
"""
input_size = _make_list_input_size(input_size)
boxes = tf.reshape(boxes, [-1, 4])
anchor_boxes = self._get_anchor_boxes(input_size)
boxes = change_box_order(boxes, 'xyxy2xywh')
boxes *= tf.tile(input_size, [
2
]) # scaled back to original size ####exchange these two lines????
ious = box_iou(anchor_boxes, boxes,
order='xywh') #[#anchor, num_bboxes]
max_ids = tf.argmax(ious, axis=1) #[#anchor,]
max_ious = tf.reduce_max(ious, axis=1) #[#anchor,]
gboxes = tf.gather(boxes,
max_ids) # broadcast automatically, [#anchors, 4]
loc_xy = (gboxes[:, :2] - anchor_boxes[:, :2]) / anchor_boxes[:, 2:]
loc_wh = tf.log(gboxes[:, 2:] / anchor_boxes[:, 2:])
loc_trues = tf.concat([loc_xy, loc_wh], 1) #[#anchors, 4]
cls_trues = tf.gather(labels,
max_ids) # TODO: check if needs add 1 here
cls_trues = tf.where(max_ious < pos_iou_threshold,
tf.zeros_like(cls_trues), cls_trues)
ignore = (max_ious > neg_iou_threshold) & (
max_ious < pos_iou_threshold
) # ignore ious between (0.4, 0.5), and marked as -1
cls_trues = tf.where(ignore, tf.ones_like(cls_trues) * -1, cls_trues)
cls_trues = tf.cast(cls_trues, tf.float32)
###################################################################################
"""second bigger iou """
if conf.use_secondbig_loss_constrain:
mask_ious = tf.one_hot(max_ids,
tf.shape(ious, out_type=tf.int32)[1])
ious -= mask_ious
second_max_ids = tf.argmax(ious, axis=1) #[#anchor,]
sec_gboxes = tf.gather(
boxes,
second_max_ids) # broadcast automatically, [#anchors, 4]
se_loc_xy = (sec_gboxes[:, :2] -
anchor_boxes[:, :2]) / anchor_boxes[:, 2:]
se_loc_wh = tf.log(sec_gboxes[:, 2:] / anchor_boxes[:, 2:])
sec_loc_trues = tf.concat([se_loc_xy, se_loc_wh], 1)
loc_trues = tf.concat([loc_trues, sec_loc_trues], 1)
###################################################################################
return loc_trues, cls_trues