def get_rpn_anchor_input(im, boxes, is_crowd):
"""
Args:
im: an image
boxes: nx4, floatbox, gt. shoudn't be changed
is_crowd: n,
Returns:
The anchor labels and target boxes for each pixel in the featuremap.
fm_labels: fHxfWxNA
fm_boxes: fHxfWxNAx4
NA will be NUM_ANCHOR_SIZES x NUM_ANCHOR_RATIOS
"""
boxes = boxes.copy()
all_anchors = np.copy(get_all_anchors())
# fHxfWxAx4 -> (-1, 4)
featuremap_anchors_flatten = all_anchors.reshape((-1, 4))
# only use anchors inside the image
inside_ind, inside_anchors = filter_boxes_inside_shape(featuremap_anchors_flatten, im.shape[:2])
# obtain anchor labels and their corresponding gt boxes
anchor_labels, anchor_gt_boxes = get_anchor_labels(inside_anchors, boxes[is_crowd == 0], boxes[is_crowd == 1])
# Fill them back to original size: fHxfWx1, fHxfWx4
anchorH, anchorW = all_anchors.shape[:2]
featuremap_labels = -np.ones((anchorH * anchorW * config.NUM_ANCHOR, ), dtype='int32')
featuremap_labels[inside_ind] = anchor_labels
featuremap_labels = featuremap_labels.reshape((anchorH, anchorW, config.NUM_ANCHOR))
featuremap_boxes = np.zeros((anchorH * anchorW * config.NUM_ANCHOR, 4), dtype='float32')
featuremap_boxes[inside_ind, :] = anchor_gt_boxes
featuremap_boxes = featuremap_boxes.reshape((anchorH, anchorW, config.NUM_ANCHOR, 4))
return featuremap_labels, featuremap_boxes
def get_rpn_anchor_input(self, im, boxes, is_crowd):
"""
Args:
im: an image
boxes: nx4, floatbox, gt. shoudn't be changed
is_crowd: n,
Returns:
The anchor labels and target boxes for each pixel in the featuremap.
fm_labels: fHxfWxNA
fm_boxes: fHxfWxNAx4
NA will be NUM_ANCHOR_SIZES x NUM_ANCHOR_RATIOS
"""
boxes = boxes.copy()
all_anchors = np.copy(
get_all_anchors(
stride=self.cfg.RPN.ANCHOR_STRIDE,
sizes=self.cfg.RPN.ANCHOR_SIZES,
ratios=self.cfg.RPN.ANCHOR_RATIOS,
max_size=self.cfg.PREPROC.MAX_SIZE,
))
# fHxfWxAx4 -> (-1, 4)
featuremap_anchors_flatten = all_anchors.reshape((-1, 4))
# only use anchors inside the image
inside_ind, inside_anchors = filter_boxes_inside_shape(
featuremap_anchors_flatten, im.shape[:2])
# obtain anchor labels and their corresponding gt boxes
anchor_labels, anchor_gt_boxes = self.get_anchor_labels(
inside_anchors, boxes[is_crowd == 0], boxes[is_crowd == 1])
# Fill them back to original size: fHxfWx1, fHxfWx4
num_anchor = self.cfg.RPN.NUM_ANCHOR
anchorH, anchorW = all_anchors.shape[:2]
featuremap_labels = -np.ones(
(anchorH * anchorW * num_anchor, ), dtype="int32")
featuremap_labels[inside_ind] = anchor_labels
featuremap_labels = featuremap_labels.reshape(
(anchorH, anchorW, num_anchor))
featuremap_boxes = np.zeros((anchorH * anchorW * num_anchor, 4),
dtype="float32")
featuremap_boxes[inside_ind, :] = anchor_gt_boxes
featuremap_boxes = featuremap_boxes.reshape(
(anchorH, anchorW, num_anchor, 4))
return featuremap_labels, featuremap_boxes
def get_multilevel_rpn_anchor_input(im, boxes, is_crowd):
"""
Args:
im: an image
boxes: nx4, floatbox, gt. shoudn't be changed
is_crowd: n,
Returns:
[(fm_labels, fm_boxes)]: Returns a tuple for each FPN level.
Each tuple contains the anchor labels and target boxes for each pixel in the featuremap.
fm_labels: fHxfWx NUM_ANCHOR_RATIOS
fm_boxes: fHxfWx NUM_ANCHOR_RATIOS x4
"""
boxes = boxes.copy()
anchors_per_level = get_all_anchors_fpn()
flatten_anchors_per_level = [k.reshape((-1, 4)) for k in anchors_per_level]
all_anchors_flatten = np.concatenate(flatten_anchors_per_level, axis=0)
inside_ind, inside_anchors = filter_boxes_inside_shape(
all_anchors_flatten, im.shape[:2])
anchor_labels, anchor_gt_boxes = get_anchor_labels(inside_anchors,
boxes[is_crowd == 0],
boxes[is_crowd == 1])
# map back to all_anchors, then split to each level
num_all_anchors = all_anchors_flatten.shape[0]
all_labels = -np.ones((num_all_anchors, ), dtype='int32')
all_labels[inside_ind] = anchor_labels
all_boxes = np.zeros((num_all_anchors, 4), dtype='float32')
all_boxes[inside_ind] = anchor_gt_boxes
start = 0
multilevel_inputs = []
for level_anchor in anchors_per_level:
assert level_anchor.shape[2] == len(config.ANCHOR_RATIOS)
anchor_shape = level_anchor.shape[:3] # fHxfWxNUM_ANCHOR_RATIOS
num_anchor_this_level = np.prod(anchor_shape)
end = start + num_anchor_this_level
multilevel_inputs.append(
(all_labels[start:end].reshape(anchor_shape),
all_boxes[start:end, :].reshape(anchor_shape + (4, ))))
start = end
assert end == num_all_anchors, "{} != {}".format(end, num_all_anchors)
return multilevel_inputs
def get_rpn_anchor_input(im, boxes, is_crowd):
cfg.RPN.NUM_ANCHOR = len(cfg.RPN.ANCHOR_SIZES) * len(cfg.RPN.ANCHOR_RATIOS)
"""
Args:
im: an image
boxes: nx4, floatbox, gt. shoudn't be changed
is_crowd: n,
Returns:
The anchor labels and target boxes for each pixel in the featuremap.
fm_labels: fHxfWxNA
fm_boxes: fHxfWxNAx4
NA will be NUM_ANCHOR_SIZES x NUM_ANCHOR_RATIOS
"""
boxes = boxes.copy()
all_anchors = np.copy(get_all_anchors())
# fHxfWxAx4 -> (-1, 4)
featuremap_anchors_flatten = all_anchors.reshape((-1, 4))
# only use anchors inside the image
inside_ind, inside_anchors = filter_boxes_inside_shape(
featuremap_anchors_flatten, im.shape[:2])
# obtain anchor labels and their corresponding gt boxes
# TODO error may occur here !!
is_crowd = np.array(is_crowd)
boxes = np.array(boxes)
anchor_labels, anchor_gt_boxes = get_anchor_labels(inside_anchors,
boxes[is_crowd == 0],
boxes[is_crowd == 1])
# Fill them back to original size: fHxfWx1, fHxfWx4
anchorH, anchorW = all_anchors.shape[:2]
cfg.RPN.NUM_ANCHOR = len(cfg.RPN.ANCHOR_SIZES) * len(cfg.RPN.ANCHOR_RATIOS)
featuremap_labels = -np.ones(
(anchorH * anchorW * cfg.RPN.NUM_ANCHOR, ), dtype='int32')
featuremap_labels[inside_ind] = anchor_labels
featuremap_labels = featuremap_labels.reshape(
(anchorH, anchorW, cfg.RPN.NUM_ANCHOR))
featuremap_boxes = np.zeros((anchorH * anchorW * cfg.RPN.NUM_ANCHOR, 4),
dtype='float32')
featuremap_boxes[inside_ind, :] = anchor_gt_boxes
featuremap_boxes = featuremap_boxes.reshape(
(anchorH, anchorW, cfg.RPN.NUM_ANCHOR, 4))
return featuremap_labels, featuremap_boxes
def get_multilevel_rpn_anchor_input(im, boxes, is_crowd):
"""
Args:
im: an image
boxes: nx4, floatbox, gt. shoudn't be changed
is_crowd: n,
Returns:
[(fm_labels, fm_boxes)]: Returns a tuple for each FPN level.
Each tuple contains the anchor labels and target boxes for each pixel in the featuremap.
fm_labels: fHxfWx NUM_ANCHOR_RATIOS
fm_boxes: fHxfWx NUM_ANCHOR_RATIOS x4
"""
boxes = boxes.copy()
anchors_per_level = get_all_anchors_fpn()
flatten_anchors_per_level = [k.reshape((-1, 4)) for k in anchors_per_level]
all_anchors_flatten = np.concatenate(flatten_anchors_per_level, axis=0)
inside_ind, inside_anchors = filter_boxes_inside_shape(all_anchors_flatten, im.shape[:2])
anchor_labels, anchor_gt_boxes = get_anchor_labels(inside_anchors, boxes[is_crowd == 0], boxes[is_crowd == 1])
# map back to all_anchors, then split to each level
num_all_anchors = all_anchors_flatten.shape[0]
all_labels = -np.ones((num_all_anchors, ), dtype='int32')
all_labels[inside_ind] = anchor_labels
all_boxes = np.zeros((num_all_anchors, 4), dtype='float32')
all_boxes[inside_ind] = anchor_gt_boxes
start = 0
multilevel_inputs = []
for level_anchor in anchors_per_level:
assert level_anchor.shape[2] == len(config.ANCHOR_RATIOS)
anchor_shape = level_anchor.shape[:3] # fHxfWxNUM_ANCHOR_RATIOS
num_anchor_this_level = np.prod(anchor_shape)
end = start + num_anchor_this_level
multilevel_inputs.append(
(all_labels[start: end].reshape(anchor_shape),
all_boxes[start: end, :].reshape(anchor_shape + (4,))
))
start = end
assert end == num_all_anchors, "{} != {}".format(end, num_all_anchors)
return multilevel_inputs
def get_rpn_anchor_input(im, boxes, is_crowd):
"""
Args:
im: an image
boxes: nx4, floatbox, gt. shoudn't be changed
is_crowd: n,
Returns:
The anchor labels and target boxes for each pixel in the featuremap.
fm_labels: fHxfWxNA
fm_boxes: fHxfWxNAx4
NA will be NUM_ANCHOR_SIZES x NUM_ANCHOR_RATIOS
"""
boxes = boxes.copy()
all_anchors = np.copy(get_all_anchors())
# fHxfWxAx4 -> (-1, 4)
featuremap_anchors_flatten = all_anchors.reshape((-1, 4))
# only use anchors inside the image
inside_ind, inside_anchors = filter_boxes_inside_shape(
featuremap_anchors_flatten, im.shape[:2])
# obtain anchor labels and their corresponding gt boxes
anchor_labels, anchor_gt_boxes = get_anchor_labels(inside_anchors,
boxes[is_crowd == 0],
boxes[is_crowd == 1])
# Fill them back to original size: fHxfWx1, fHxfWx4
anchorH, anchorW = all_anchors.shape[:2]
featuremap_labels = -np.ones(
(anchorH * anchorW * cfg.RPN.NUM_ANCHOR, ), dtype='int32')
featuremap_labels[inside_ind] = anchor_labels
featuremap_labels = featuremap_labels.reshape(
(anchorH, anchorW, cfg.RPN.NUM_ANCHOR))
featuremap_boxes = np.zeros((anchorH * anchorW * cfg.RPN.NUM_ANCHOR, 4),
dtype='float32')
# every anchor will get a set of parameterized bb vectors
# but they are only meaningful to the positive boxes
# only the regression loss from the positive boxes will be considered
featuremap_boxes[inside_ind, :] = anchor_gt_boxes
featuremap_boxes = featuremap_boxes.reshape(
(anchorH, anchorW, cfg.RPN.NUM_ANCHOR, 4))
return featuremap_labels, featuremap_boxes
