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 random_crop(img, boxes, labels, min_scale=0.3, max_aspect_ratio=2.):
'''Randomly crop a PIL image.
Args:
img: (PIL.Image) image.
boxes: (tensor) bounding boxes, sized [#obj, 4].
labels: (tensor) bounding box labels, sized [#obj,].
min_scale: (float) minimal image width/height scale.
max_aspect_ratio: (float) maximum width/height aspect ratio.
Returns:
img: (PIL.Image) cropped image.
boxes: (tensor) object boxes.
labels: (tensor) object labels.
'''
img = img.copy()
boxes = boxes.clone()
labels = labels.clone()
imw, imh = img.size
params = [(0, 0, imw, imh)] # crop roi (x,y,w,h) out
for min_iou in (0, 0.1, 0.3, 0.5, 0.7, 0.9):
for _ in range(100):
scale = random.uniform(min_scale, 1)
aspect_ratio = random.uniform(
max(1 / max_aspect_ratio, scale * scale),
min(max_aspect_ratio, 1 / (scale * scale)))
w = int(imw * scale * math.sqrt(aspect_ratio))
h = int(imh * scale / math.sqrt(aspect_ratio))
x = random.randrange(imw - w)
y = random.randrange(imh - h)
roi = torch.tensor([[x, y, x + w, y + h]], dtype=torch.float)
ious = box_iou(boxes, roi)
if ious.min() >= min_iou:
params.append((x, y, w, h))
break
x, y, w, h = random.choice(params)
img = img.crop((x, y, x + w, y + h))
center = (boxes[:, :2] + boxes[:, 2:]) / 2
mask = (center[:,0]>=x) & (center[:,0]<=x+w) \
& (center[:,1]>=y) & (center[:,1]<=y+h)
if mask.any():
boxes = boxes[mask] - torch.tensor([x, y, x, y], dtype=torch.float)
boxes = box_clamp(boxes, 0, 0, w, h)
labels = labels[mask]
else:
boxes = torch.tensor([[0, 0, 0, 0]], dtype=torch.float)
labels = torch.tensor([0], dtype=torch.long)
return img, boxes, labels
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
