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):
v, i = x.max(0)
j = v.max(0)[1][0]
return (i[j], j)
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)
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():
t = ious[mask.nonzero().squeeze()]
if len(t.shape) == 1:
index[mask] = t[0].long()
else:
index[mask] = t.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):
'''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)
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,].
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)
anchor_boxes = self.anchor_boxes
# print (anchor_boxes.size())
ious = box_iou(anchor_boxes, boxes) # [#anchors, #obj]
index = torch.empty(anchor_boxes.size(0), dtype=torch.long).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].max(1)[1]
boxes = boxes[index.clamp(min=0)] # negative index not supported
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[index.clamp(min=0)]
# print (labels.size())
# print (cls_targets.size())
cls_targets[index < 0] = 0
return loc_targets, cls_targets
def decode(self, loc_preds, cls_preds, score_thresh=0.5, 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').cuda()
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)
# print (num_classes)
for i in range(num_classes - 1):
score = cls_preds[:, i + 1] # class i corresponds to (i+1) column
# print (score)
mask = score > score_thresh
# print (mask)
if not mask.any():
# print ("continue")
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])
# print (sizeof(boxes))
#print (np.array(boxes).shape)
boxes = torch.cat(boxes, 0)
labels = torch.cat(labels, 0)
scores = torch.cat(scores, 0)
return boxes, labels, scores
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 [8732,4] or [8732,8].
cls_preds: (tensor) predicted conf, sized [8732,21].
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,].
'''
#print("decode")
#print(loc_preds.size())
#print(cls_preds.size())
variances = (1, 0.2)
#xy = loc_preds[:,:2] * variances[0] * self.default_boxes[:,2:] + self.default_boxes[:,:2]
#wh = torch.exp(loc_preds[:,2:]*variances[1]) * self.default_boxes[:,2:]
#box_preds = torch.cat([xy-wh/2, xy+wh/2], 1)
default_boxes = change_box_order(self.default_boxes, 'xywh2xyxyxyxy')
box_preds = loc_preds * variances[
0] * self.default_boxes[:, 2:].repeat(1, 4) + default_boxes
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.nonzero().squeeze()]
score = score[mask]
keep = box_nms(box, score, nms_thresh)
boxes.append(box[keep])
labels.append(torch.LongTensor(len(box[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 nonlocal_matching(self):
anchors_boxes = change_box_order(self.anchors_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)
ious = box_iou(box_preds, boxes)
index = torch.empty(anchor_boxes.size(0), dtype=torch.long).fill_(-1)
masked_ious = ious.clone()
# pdb.set_trace()
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) # chose the activated bbox
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):
v, i = x.max(0)
j = v.max(0)[1][0]
return (i[j], j)
# True?: default boxes are also known as "anchors" in some contexts
# Or is an anchor a default position from which multiple default boxes
# are formed?
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)
masked_ious = ious.clone()
# Match ground truth boxes with default boxes based on IoU
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
# Assign ground truth boxes to unmatched default boxes if the overlap is good enough.
# Consequence: Some ground truth boxes are matched with multiple default boxes.
# Clarification: Each default box can have at most one ground truth box matched with
# it. Some default boxes will not be matched with a ground truth box.
mask = (index < 0) & (ious.max(1)[0] >= 0.5)
if mask.any():
index[mask] = ious[mask.nonzero().squeeze()].max(1)[1]
# Shape: (num_default_boxes, 4)
# Each default box index is replaced with a ground truth box that it
# was matched with. Unmatched default boxes are given the first ground
# truth box, but this won't affect the location loss since unmatched
# default boxes are tracked as "negative examples" via an index of -1.
# Later, all class labels will be incremented, leaving the class label
# of 0 free for new use. This is the class label we will assign to
# negative examples, which are those with an index of -1.
# I'm not sure why we couldn't just give negative examples a class
# label of -1 and not change the original ground truth class labels.
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)
# Add one to the label ID of each default box that was matched with a
# ground truth box. Reason: We must make room for the "unassigned"
# class. F.cross_entropy doesn't allow negative class numbers,
# so we can use -1 for this class. Not sure why we don't use the next
# available positive number, but this works.
cls_targets = 1 + labels[index.clamp(min=0)] # Positive examples
# Assign a class ID of 0 to unmatched default boxes. These will be
# considered negative examples in the location loss function.
# See SSDLoss
cls_targets[index < 0] = 0 # Negative examples
return loc_targets, cls_targets
def encode(self, boxes, labels):
#print("encode")
#print(boxes.size())
#print(labels.size())
'''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 (x1,y1,x2,y2,x3,y3,x4,y4), sized [#obj, 8].
labels: (tensor) object class labels, sized [#obj,].
Returns:
loc_targets: (tensor) encoded bounding boxes, sized [#anchors,8].
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):
v, i = x.max(0)
j = v.max(0)[1][0]
return (i[j], j)
default_boxes = self.default_boxes # xywh
default_boxes = change_box_order(default_boxes, 'xywh2xyxyxyxy')
ious = simplified_iou(change_box_order(self.default_boxes,
'xywh2xyxy'),
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 = (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)
loc_targets = (boxes -
default_boxes) / self.default_boxes[:, 2:].repeat(
1, 4) / variances[0]
cls_targets = 1 + labels[index.clamp(min=0)]
cls_targets[index < 0] = 0
return loc_targets, cls_targets
