def __init__(self,
*args,
anchor_angles=[
0.,
],
bbox_coder=dict(type='DeltaXYWHABBoxCoder',
target_means=(.0, .0, .0, .0, .0),
target_stds=(1.0, 1.0, 1.0, 1.0, 1.0)),
**kargs):
super(AnchorHeadRotated, self).__init__(*args, **kargs)
self.anchor_angles = anchor_angles
self.reg_decoded_bbox = False
self.use_vfl = True
self.bbox_coder = build_bbox_coder(bbox_coder)
self.anchor_generators = []
for anchor_base in self.anchor_base_sizes:
self.anchor_generators.append(
AnchorGeneratorRotated(anchor_base,
self.anchor_scales,
self.anchor_ratios,
angles=anchor_angles))
self.num_anchors = len(self.anchor_ratios) * \
len(self.anchor_scales) * len(self.anchor_angles)
self._init_layers()
def __init__(self,
num_classes,
in_channels,
feat_channels=256,
stacked_convs=2,
with_align=True,
anchor_scales=[4],
anchor_ratios=[1.0],
anchor_strides=[8, 16, 32, 64, 128],
anchor_base_sizes=None,
target_means=(.0, .0, .0, .0, .0),
target_stds=(1.0, 1.0, 1.0, 1.0, 1.0),
loss_cls=dict(type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss',
beta=1.0 / 9.0,
loss_weight=1.0)):
super(CascadeS2ANetHead, self).__init__()
self.num_classes = num_classes
self.in_channels = in_channels
self.feat_channels = feat_channels
self.stacked_convs = stacked_convs
self.with_align = with_align
self.anchor_scales = anchor_scales
self.anchor_ratios = anchor_ratios
self.anchor_strides = anchor_strides
self.anchor_base_sizes = list(
anchor_strides) if anchor_base_sizes is None else anchor_base_sizes
self.target_means = target_means
self.target_stds = target_stds
self.use_sigmoid_cls = loss_cls.get('use_sigmoid', False)
self.sampling = loss_cls['type'] not in ['FocalLoss', 'GHMC']
if self.use_sigmoid_cls:
self.cls_out_channels = num_classes - 1
else:
self.cls_out_channels = num_classes
if self.cls_out_channels <= 0:
raise ValueError('num_classes={} is too small'.format(num_classes))
self.loss_cls = build_loss(loss_cls)
self.loss_bbox = build_loss(loss_bbox)
self.fp16_enabled = False
self.anchor_generators = []
for anchor_base in self.anchor_base_sizes:
self.anchor_generators.append(
AnchorGeneratorRotated(anchor_base, anchor_scales,
anchor_ratios))
self._init_layers()
def __init__(self, *args, anchor_angles=[
0.,
], **kargs):
super(AnchorHeadRotated, self).__init__(*args, **kargs)
self.anchor_angles = anchor_angles
self.anchor_generators = []
for anchor_base in self.anchor_base_sizes:
self.anchor_generators.append(
AnchorGeneratorRotated(anchor_base,
self.anchor_scales,
self.anchor_ratios,
angles=anchor_angles))
self.num_anchors = len(self.anchor_ratios) * \
len(self.anchor_scales) * len(self.anchor_angles)
self._init_layers()
def __init__(self,
num_classes,
in_channels,
feat_channels=256,
stacked_convs=2,
with_orconv=True,
reg_decoded_bbox=False,
use_vfl=False,
bbox_coder=dict(type='DeltaXYWHABBoxCoder',
target_means=(0., 0., 0., 0., 0.),
target_stds=(1., 1., 1., 1., 1.),
clip_border=True),
iou_calculator=dict(type='BboxOverlaps2D_rotated'),
anchor_scales=[4],
anchor_ratios=[1.0],
anchor_strides=[8, 16, 32, 64, 128],
anchor_base_sizes=None,
target_means=(.0, .0, .0, .0, .0),
target_stds=(1.0, 1.0, 1.0, 1.0, 1.0),
loss_fam_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_fam_bbox=dict(
type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0),
loss_odm_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_odm_bbox=dict(
type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)):
super(S2ANetHead, self).__init__()
self.num_classes = num_classes
self.in_channels = in_channels
self.feat_channels = feat_channels
self.stacked_convs = stacked_convs
self.with_orconv = with_orconv
self.anchor_scales = anchor_scales
self.anchor_ratios = anchor_ratios
self.anchor_strides = anchor_strides
self.anchor_base_sizes = list(
anchor_strides) if anchor_base_sizes is None else anchor_base_sizes
self.target_means = target_means
self.target_stds = target_stds
self.use_sigmoid_cls = loss_odm_cls.get('use_sigmoid', False)
self.sampling = loss_odm_cls['type'] not in ['FocalLoss', 'GHMC', 'VarifocalLoss']
if self.use_sigmoid_cls:
self.cls_out_channels = num_classes - 1
else:
self.cls_out_channels = num_classes
if self.cls_out_channels <= 0:
raise ValueError('num_classes={} is too small'.format(num_classes))
self.loss_fam_cls = build_loss(loss_fam_cls)
self.loss_fam_bbox = build_loss(loss_fam_bbox)
self.loss_odm_cls = build_loss(loss_odm_cls)
self.loss_odm_bbox = build_loss(loss_odm_bbox)
self.fp16_enabled = False
self.reg_decoded_bbox = reg_decoded_bbox
self.use_vfl = use_vfl
self.iou_calculator = build_iou_calculator(iou_calculator)
self.bbox_coder = build_bbox_coder(bbox_coder)
self.anchor_generators = []
for anchor_base in self.anchor_base_sizes:
self.anchor_generators.append(
AnchorGeneratorRotated(anchor_base, anchor_scales, anchor_ratios))
# training mode
self.training = True
# anchor cache
self.base_anchors = dict()
self._init_layers()