def setup(self, bottom, top):
# parse the layer parameter string, which must be valid YAML
try:
layer_params = yaml.load(self.param_str_)
except AttributeError:
layer_params = yaml.load(self.param_str)
self._feat_stride = layer_params['feat_stride']
self._anchor_ratios = layer_params.get('ratios', (0.5, 1, 2))
anchor_scales = layer_params.get('scales', (8, 16, 32))
base_size = layer_params.get('base_size', 16)
print('feat_stride: ', self._feat_stride, 'anchor_ratio: ',
self._anchor_ratios, 'anchor_scales:', anchor_scales,
'base_size: ', base_size)
self._anchors = generate_anchors(scales=np.array(anchor_scales),
base_size=base_size,
ratios=np.array(self._anchor_ratios))
print('anchors: ', self._anchors)
self._num_anchors = self._anchors.shape[0]
print('anchors_shape: ', self._anchors.shape)
if DEBUG:
print 'feat_stride: {}'.format(self._feat_stride)
print 'anchors:'
print self._anchors
# rois blob: holds R regions of interest, each is a 5-tuple
# (n, x1, y1, x2, y2) specifying an image batch index n and a
# rectangle (x1, y1, x2, y2)
top[0].reshape(1, 5)
# scores blob: holds scores for R regions of interest
if len(top) > 1:
top[1].reshape(1, 1, 1, 1)
def setup(self, bottom, top):
# parse the layer parameter string, which must be valid YAML
try:
layer_params = yaml.load(self.param_str_)
except AttributeError:
layer_params = yaml.load(self.param_str)
self._feat_stride = layer_params['feat_stride']
self._anchor_ratios = layer_params.get('ratios',(0.5, 1, 2))
anchor_scales = layer_params.get('scales', (8, 16, 32))
base_size = layer_params.get('base_size',16)
self._anchors = generate_anchors(scales=np.array(anchor_scales), base_size=base_size,ratios=np.array(self._anchor_ratios))
self._num_anchors = self._anchors.shape[0]
if DEBUG:
print 'feat_stride: {}'.format(self._feat_stride)
print 'anchors:'
print self._anchors
# rois blob: holds R regions of interest, each is a 5-tuple
# (n, x1, y1, x2, y2) specifying an image batch index n and a
# rectangle (x1, y1, x2, y2)
top[0].reshape(1, 5)
# scores blob: holds scores for R regions of interest
if len(top) > 1:
top[1].reshape(1, 1, 1, 1)
def setup(self, bottom, top):
try:
layer_params = yaml.load(self.param_str_)
except AttributeError:
layer_params = yaml.load(self.param_str)
# Determine if hard negative mining should be performed
# based on the number of bottom blobs
self._hard_mining = False
if len(bottom) == 5:
self._hard_mining = True
anchor_scales = layer_params.get('scales', (8, 16, 32))
self._anchor_ratios = layer_params.get('ratios',(0.5, 1, 2))
base_size = layer_params.get('base_size', 16)
self._anchors = generate_anchors(scales=np.array(anchor_scales), base_size=base_size,
ratios=np.array(self._anchor_ratios))
self._num_anchors = self._anchors.shape[0]
self._feat_stride = layer_params['feat_stride']
self._positive_overlap = layer_params.get('positive_overlap',cfg.TRAIN.ANCHOR_POSITIVE_OVERLAP)
# allow boxes to sit over the edge
self._allowed_border = layer_params.get('allowed_border', 0)
height, width = bottom[0].data.shape[-2:]
A = self._num_anchors
# labels
top[0].reshape(1, 1, A * height, width)
# bbox_targets
top[1].reshape(1, A * 4, height, width)
# bbox_inside_weights
top[2].reshape(1, A * 4, height, width)
# bbox_outside_weights
top[3].reshape(1, A * 4, height, width)
def setup(self, bottom, top):
try:
layer_params = yaml.load(self.param_str_)
except AttributeError:
layer_params = yaml.load(self.param_str)
# Determine if hard negative mining should be performed
# based on the number of bottom blobs
self._hard_mining = False
if len(bottom) == 5:
self._hard_mining = True
anchor_scales = layer_params.get('scales', (8, 16, 32))
self._anchor_ratios = layer_params.get('ratios',(0.5, 1, 2))
base_size = layer_params.get('base_size', 16)
self._anchors = generate_anchors(scales=np.array(anchor_scales), base_size=base_size,
ratios=np.array(self._anchor_ratios))
self._num_anchors = self._anchors.shape[0]
self._feat_stride = layer_params['feat_stride']
self._positive_overlap = layer_params.get('positive_overlap',cfg.TRAIN.ANCHOR_POSITIVE_OVERLAP)
# allow boxes to sit over the edge
self._allowed_border = layer_params.get('allowed_border', 0)
height, width = bottom[0].data.shape[-2:]
A = self._num_anchors
# labels
top[0].reshape(1, 1, A * height, width)
# bbox_targets
top[1].reshape(1, A * 4, height, width)
# bbox_inside_weights
top[2].reshape(1, A * 4, height, width)
# bbox_outside_weights
top[3].reshape(1, A * 4, height, width)