def __init__(self,
num_channels,
num_filters,
filter_size,
stride=1,
groups=1,
is_vd_mode=False,
act=None,
name=None):
super(ConvBNLayer, self).__init__()
self.is_vd_mode = is_vd_mode
self._pool2d_avg = AvgPool2D(kernel_size=2,
stride=2,
padding=0,
ceil_mode=True)
self._conv = Conv2D(in_channels=num_channels,
out_channels=num_filters,
kernel_size=filter_size,
stride=stride,
padding=(filter_size - 1) // 2,
groups=groups,
weight_attr=ParamAttr(name=name + "_weights"),
bias_attr=False)
bn_name = name + '_bn'
self._batch_norm = BatchNorm(
num_filters,
act=act,
param_attr=ParamAttr(name=bn_name + '_scale'),
bias_attr=ParamAttr(bn_name + '_offset'),
moving_mean_name=bn_name + '_mean',
moving_variance_name=bn_name + '_variance')
def __init__(self,
num_channels,
filter_size,
num_filters,
stride,
padding,
channels=None,
num_groups=1,
name=None,
use_cudnn=True):
super(ConvBNLayer, self).__init__()
self._conv = Conv2D(in_channels=num_channels,
out_channels=num_filters,
kernel_size=filter_size,
stride=stride,
padding=padding,
groups=num_groups,
weight_attr=ParamAttr(name=name + "_weights"),
bias_attr=False)
self._batch_norm = BatchNorm(
num_filters,
param_attr=ParamAttr(name=name + "_bn_scale"),
bias_attr=ParamAttr(name=name + "_bn_offset"),
moving_mean_name=name + "_bn_mean",
moving_variance_name=name + "_bn_variance")
def __init__(self,
num_channels,
num_filters,
filter_size,
stride=1,
groups=1,
padding=0,
act=None,
name=None):
super(ConvBNLayer, self).__init__()
self._conv = Conv2D(
in_channels=num_channels,
out_channels=num_filters,
kernel_size=filter_size,
stride=stride,
padding=padding,
groups=groups,
weight_attr=ParamAttr(name=name + ".conv2d.output.1.w_0"),
bias_attr=ParamAttr(name=name + ".conv2d.output.1.b_0"))
bn_name = name + "_bn"
self._batch_norm = BatchNorm(
num_filters,
act=act,
param_attr=ParamAttr(name=bn_name + ".output.1.w_0"),
bias_attr=ParamAttr(bn_name + ".output.1.b_0"),
moving_mean_name=bn_name + "_mean",
moving_variance_name=bn_name + "_variance")
def __init__(self,
in_channels,
out_channels,
kernel_size,
stride=1,
groups=1,
act="relu",
name=None):
super(ConvBNLayer, self).__init__()
self._conv = nn.Conv2D(in_channels=in_channels,
out_channels=out_channels,
kernel_size=kernel_size,
stride=stride,
padding=(kernel_size - 1) // 2,
groups=groups,
weight_attr=ParamAttr(
initializer=KaimingNormal(),
name=name + "_weights"),
bias_attr=False)
bn_name = name + "_bn"
self._batch_norm = nn.BatchNorm(
num_channels=out_channels,
act=act,
param_attr=ParamAttr(name=bn_name + "_scale",
regularizer=paddle.regularizer.L2Decay(0.0)),
bias_attr=ParamAttr(name=bn_name + "_offset",
regularizer=paddle.regularizer.L2Decay(0.0)),
moving_mean_name=bn_name + "_mean",
moving_variance_name=bn_name + "_variance")
def __init__(self,
num_channels,
num_filters,
filter_size,
stride=1,
groups=1,
act=None,
name=None,
data_format="NCHW"):
super(ConvBNLayer, self).__init__()
self._conv = Conv2D(in_channels=num_channels,
out_channels=num_filters,
kernel_size=filter_size,
stride=stride,
padding=(filter_size - 1) // 2,
groups=groups,
weight_attr=ParamAttr(name=name + "_weights"),
bias_attr=False,
data_format=data_format)
if name == "conv1":
bn_name = "bn_" + name
else:
bn_name = "bn" + name[3:]
self._batch_norm = BatchNorm(
num_filters,
act=act,
param_attr=ParamAttr(name=bn_name + "_scale"),
bias_attr=ParamAttr(bn_name + "_offset"),
moving_mean_name=bn_name + "_mean",
moving_variance_name=bn_name + "_variance",
data_layout=data_format)
def __init__(self, channel, lr_mult, conv_decay, reduction=4, name=""):
super(SEModule, self).__init__()
self.avg_pool = nn.AdaptiveAvgPool2D(1)
mid_channels = int(channel // reduction)
self.conv1 = nn.Conv2D(
in_channels=channel,
out_channels=mid_channels,
kernel_size=1,
stride=1,
padding=0,
weight_attr=ParamAttr(
learning_rate=lr_mult,
regularizer=L2Decay(conv_decay),
name=name + "_1_weights"),
bias_attr=ParamAttr(
learning_rate=lr_mult,
regularizer=L2Decay(conv_decay),
name=name + "_1_offset"))
self.conv2 = nn.Conv2D(
in_channels=mid_channels,
out_channels=channel,
kernel_size=1,
stride=1,
padding=0,
weight_attr=ParamAttr(
learning_rate=lr_mult,
regularizer=L2Decay(conv_decay),
name=name + "_2_weights"),
bias_attr=ParamAttr(
learning_rate=lr_mult,
regularizer=L2Decay(conv_decay),
name=name + "_2_offset"))
def __init__(self,
in_channels,
out_channels,
kernel_size,
stride,
padding,
groups=1,
if_act=True,
act=None,
name=None):
super(ConvBNLayer, self).__init__()
self.if_act = if_act
self.act = act
self.conv = nn.Conv2D(
in_channels=in_channels,
out_channels=out_channels,
kernel_size=kernel_size,
stride=stride,
padding=padding,
groups=groups,
weight_attr=ParamAttr(name=name + '_weights'),
bias_attr=False)
self.bn = nn.BatchNorm(
num_channels=out_channels,
act=act,
param_attr=ParamAttr(name="bn_" + name + "_scale"),
bias_attr=ParamAttr(name="bn_" + name + "_offset"),
moving_mean_name="bn_" + name + "_mean",
moving_variance_name="bn_" + name + "_variance")
def __init__(self,
in_channels,
out_channels,
kernel_size=3,
padding=1,
conv_decay=0,
name=None):
super(SepConvLayer, self).__init__()
self.dw_conv = nn.Conv2D(in_channels=in_channels,
out_channels=in_channels,
kernel_size=kernel_size,
stride=1,
padding=padding,
groups=in_channels,
weight_attr=ParamAttr(
name=name + "_dw_weights",
regularizer=L2Decay(conv_decay)),
bias_attr=False)
self.bn = nn.BatchNorm2D(in_channels,
weight_attr=ParamAttr(
name=name + "_bn_scale",
regularizer=L2Decay(0.)),
bias_attr=ParamAttr(name=name + "_bn_offset",
regularizer=L2Decay(0.)))
self.pw_conv = nn.Conv2D(in_channels=in_channels,
out_channels=out_channels,
kernel_size=1,
stride=1,
padding=0,
weight_attr=ParamAttr(
name=name + "_pw_weights",
regularizer=L2Decay(conv_decay)),
bias_attr=False)
def _convert_param_attr_to_list(param_attr, n):
if isinstance(param_attr, (list, tuple)):
assert len(param_attr) == n, (
"length of param_attr should be %d when it is a list/tuple" % n)
param_attrs = []
for attr in param_attr:
if isinstance(attr, bool):
if attr:
param_attrs.append(ParamAttr._to_attr(None))
else:
param_attrs.append(False)
else:
param_attrs.append(ParamAttr._to_attr(attr))
elif isinstance(param_attr, bool):
param_attrs = []
if param_attr:
param_attrs = [ParamAttr._to_attr(None) for i in range(n)]
else:
param_attrs = [False] * n
else:
param_attrs = []
attr = ParamAttr._to_attr(param_attr)
for i in range(n):
attr_i = copy.deepcopy(attr)
if attr.name:
attr_i.name = attr_i.name + "_" + str(i)
param_attrs.append(attr_i)
return param_attrs
def __init__(self, in_channel, mid_channel, out_channel, fuse):
super().__init__()
self.conv1 = nn.Conv2D(
in_channel,
mid_channel,
kernel_size=1,
bias_attr=False,
weight_attr=ParamAttr(initializer=KaimingNormal()))
self.conv1_bn = nn.BatchNorm2D(mid_channel)
self.conv2 = nn.Conv2D(
mid_channel,
out_channel,
kernel_size=3,
stride=1,
padding=1,
bias_attr=False,
weight_attr=ParamAttr(initializer=KaimingNormal()))
self.conv2_bn = nn.BatchNorm2D(out_channel)
if fuse:
self.att_conv = nn.Sequential(
nn.Conv2D(mid_channel * 2, 2, kernel_size=1),
nn.Sigmoid(),
)
else:
self.att_conv = None
def __init__(self,
num_channels,
num_filters,
filter_size,
stride=1,
groups=1,
act=None,
name=None):
super(ConvBNLayer, self).__init__()
self._conv = Conv2D(in_channels=num_channels,
out_channels=num_filters,
kernel_size=filter_size,
stride=stride,
padding=(filter_size - 1) // 2,
groups=groups,
weight_attr=ParamAttr(name=name + "_weights"),
bias_attr=False)
bn_name = "bn_" + name
self._batch_norm = BatchNorm(
num_filters,
act=act,
param_attr=ParamAttr(name=bn_name + "_scale"),
bias_attr=ParamAttr(name=bn_name + "_offset"),
moving_mean_name=bn_name + '_mean',
moving_variance_name=bn_name + '_variance')
def __init__(self, in_dim=256, mlp_dim=1024, resolution=7, num_stages=1):
super(TwoFCHead, self).__init__()
self.in_dim = in_dim
self.mlp_dim = mlp_dim
self.num_stages = num_stages
fan = in_dim * resolution * resolution
self.fc6_list = []
self.fc6_relu_list = []
self.fc7_list = []
self.fc7_relu_list = []
for stage in range(num_stages):
fc6_name = 'fc6_{}'.format(stage)
fc7_name = 'fc7_{}'.format(stage)
fc6 = self.add_sublayer(
fc6_name,
nn.Linear(in_dim * resolution * resolution,
mlp_dim,
weight_attr=ParamAttr(initializer=XavierUniform(
fan_out=fan)),
bias_attr=ParamAttr(learning_rate=2.,
regularizer=L2Decay(0.))))
fc6_relu = self.add_sublayer(fc6_name + 'act', ReLU())
fc7 = self.add_sublayer(
fc7_name,
nn.Linear(mlp_dim,
mlp_dim,
weight_attr=ParamAttr(initializer=XavierUniform()),
bias_attr=ParamAttr(learning_rate=2.,
regularizer=L2Decay(0.))))
fc7_relu = self.add_sublayer(fc7_name + 'act', ReLU())
self.fc6_list.append(fc6)
self.fc6_relu_list.append(fc6_relu)
self.fc7_list.append(fc7)
self.fc7_relu_list.append(fc7_relu)
def __init__(self,
num_channels,
num_filters,
filter_size,
stride=1,
groups=1,
is_vd_mode=False,
act=None,
lr_mult=1.0,
data_format="NCHW"):
super().__init__()
self.is_vd_mode = is_vd_mode
self.act = act
self.avg_pool = AvgPool2D(
kernel_size=2, stride=2, padding=0, ceil_mode=True)
self.conv = Conv2D(
in_channels=num_channels,
out_channels=num_filters,
kernel_size=filter_size,
stride=stride,
padding=(filter_size - 1) // 2,
groups=groups,
weight_attr=ParamAttr(learning_rate=lr_mult),
bias_attr=False,
data_format=data_format)
self.bn = BatchNorm(
num_filters,
param_attr=ParamAttr(learning_rate=lr_mult),
bias_attr=ParamAttr(learning_rate=lr_mult),
data_layout=data_format)
self.relu = nn.ReLU()
def __init__(self,
num_classes=80,
width_mult=1.0,
depthwise=False,
in_channels=[256, 512, 1024],
feat_channels=256,
fpn_strides=(8, 16, 32),
l1_epoch=285,
act='silu',
assigner=SimOTAAssigner(use_vfl=False),
nms='MultiClassNMS',
loss_weight={
'cls': 1.0,
'obj': 1.0,
'iou': 5.0,
'l1': 1.0
}):
super(YOLOXHead, self).__init__()
self._dtype = paddle.framework.get_default_dtype()
self.num_classes = num_classes
assert len(in_channels) > 0, "in_channels length should > 0"
self.in_channels = in_channels
feat_channels = int(feat_channels * width_mult)
self.fpn_strides = fpn_strides
self.l1_epoch = l1_epoch
self.assigner = assigner
self.nms = nms
self.loss_weight = loss_weight
self.iou_loss = IouLoss(loss_weight=1.0) # default loss_weight 2.5
ConvBlock = DWConv if depthwise else BaseConv
self.stem_conv = nn.LayerList()
self.conv_cls = nn.LayerList()
self.conv_reg = nn.LayerList() # reg [x,y,w,h] + obj
for in_c in self.in_channels:
self.stem_conv.append(BaseConv(in_c, feat_channels, 1, 1, act=act))
self.conv_cls.append(
nn.Sequential(*[
ConvBlock(feat_channels, feat_channels, 3, 1, act=act),
ConvBlock(feat_channels, feat_channels, 3, 1, act=act),
nn.Conv2D(feat_channels,
self.num_classes,
1,
bias_attr=ParamAttr(regularizer=L2Decay(0.0)))
]))
self.conv_reg.append(
nn.Sequential(*[
ConvBlock(feat_channels, feat_channels, 3, 1, act=act),
ConvBlock(feat_channels, feat_channels, 3, 1, act=act),
nn.Conv2D(
feat_channels,
4 + 1, # reg [x,y,w,h] + obj
1,
bias_attr=ParamAttr(regularizer=L2Decay(0.0)))
]))
self._init_weights()
def basic_branch(self, num_conv_out_channels, input_ch):
# the level indexes are defined from fine to coarse,
# the branch will contain one more part than that of its previous level
# the sliding step is set to 1
pyramid_conv_list = nn.LayerList()
pyramid_fc_list = nn.LayerList()
idx_levels = 0
for idx_branches in range(self.num_branches):
if idx_branches >= sum(self.num_in_each_level[0:idx_levels + 1]):
idx_levels += 1
if self.used_levels[idx_levels] == 0:
continue
pyramid_conv_list.append(
nn.Sequential(nn.Conv2D(input_ch, num_conv_out_channels, 1),
nn.BatchNorm2D(num_conv_out_channels),
nn.ReLU()))
idx_levels = 0
for idx_branches in range(self.num_branches):
if idx_branches >= sum(self.num_in_each_level[0:idx_levels + 1]):
idx_levels += 1
if self.used_levels[idx_levels] == 0:
continue
name = "Linear_branch_id_{}".format(idx_branches)
fc = nn.Linear(in_features=num_conv_out_channels,
out_features=self.num_classes,
weight_attr=ParamAttr(name=name + "_weights",
initializer=Normal(
mean=0., std=0.001)),
bias_attr=ParamAttr(name=name + "_bias",
initializer=Constant(value=0.)))
pyramid_fc_list.append(fc)
return pyramid_conv_list, pyramid_fc_list
def __init__(self,
in_channels,
out_channels,
kernel_size,
stride,
padding,
num_groups=1,
act='relu',
conv_lr=1.,
conv_decay=0.,
norm_decay=0.,
norm_type='bn',
name=None):
super(ConvBNLayer, self).__init__()
self.act = act
self._conv = nn.Conv2D(in_channels,
out_channels,
kernel_size=kernel_size,
stride=stride,
padding=padding,
groups=num_groups,
weight_attr=ParamAttr(
learning_rate=conv_lr,
initializer=KaimingNormal(),
regularizer=L2Decay(conv_decay)),
bias_attr=False)
param_attr = ParamAttr(regularizer=L2Decay(norm_decay))
bias_attr = ParamAttr(regularizer=L2Decay(norm_decay))
if norm_type in ['sync_bn', 'bn']:
self._batch_norm = nn.BatchNorm2D(out_channels,
weight_attr=param_attr,
bias_attr=bias_attr)
def __init__(self,
in_channels,
out_channels,
kernel_size,
stride=1,
groups=1,
act=None,
name=None):
super(ConvBNLayer, self).__init__()
self._conv = Conv2D(in_channels=in_channels,
out_channels=out_channels,
kernel_size=kernel_size,
stride=stride,
padding=(kernel_size - 1) // 2,
groups=groups,
weight_attr=ParamAttr(name=name + "_weights"),
bias_attr=False)
if name == "conv1":
bn_name = "bn_" + name
else:
bn_name = "bn" + name[3:]
self._act = act
self._batch_norm = BatchNorm2D(
out_channels,
weight_attr=ParamAttr(name=bn_name + "_scale"),
bias_attr=ParamAttr(bn_name + "_offset"))
def __init__(self,
num_channels: int,
filter_size: int,
num_filters: int,
stride: int,
padding: int,
channels: int = None,
num_groups: int = 1,
act: str = 'relu',
name: str = None):
super(ConvBNLayer, self).__init__()
self._conv = Conv2d(
in_channels=num_channels,
out_channels=num_filters,
kernel_size=filter_size,
stride=stride,
padding=padding,
groups=num_groups,
weight_attr=ParamAttr(initializer=MSRA(), name=name + "_weights"),
bias_attr=False)
self._batch_norm = BatchNorm(
num_filters,
act=act,
param_attr=ParamAttr(name + "_bn_scale"),
bias_attr=ParamAttr(name + "_bn_offset"),
moving_mean_name=name + "_bn_mean",
moving_variance_name=name + "_bn_variance")
def __init__(self,
input_channels,
output_channels,
filter_size,
stride=1,
padding=0,
act=None,
name=None):
super(ConvBNLayer, self).__init__()
self._conv = Conv2D(
in_channels=input_channels,
out_channels=output_channels,
kernel_size=filter_size,
stride=stride,
padding=padding,
weight_attr=ParamAttr(name=name + "/weights"),
bias_attr=False)
self._bn = BatchNorm(
num_channels=output_channels,
act=act,
epsilon=1e-3,
momentum=0.99,
param_attr=ParamAttr(name=name + "/BatchNorm/gamma"),
bias_attr=ParamAttr(name=name + "/BatchNorm/beta"),
moving_mean_name=name + "/BatchNorm/moving_mean",
moving_variance_name=name + "/BatchNorm/moving_variance")
def __init__(self,
input_channels,
output_channels,
filter_size,
stride=1,
groups=1,
act=None,
name=None):
super(ConvBNLayer, self).__init__()
if "downsample" in name:
conv_name = name + ".0"
else:
conv_name = name
self._conv = Conv2D(in_channels=input_channels,
out_channels=output_channels,
kernel_size=filter_size,
stride=stride,
padding=(filter_size - 1) // 2,
groups=groups,
weight_attr=ParamAttr(name=conv_name + ".weight"),
bias_attr=False)
if "downsample" in name:
bn_name = name[:9] + "downsample.1"
else:
if "conv1" == name:
bn_name = "bn" + name[-1]
else:
bn_name = (name[:10] if name[7:9].isdigit() else
name[:9]) + "bn" + name[-1]
self._bn = BatchNorm(num_channels=output_channels,
act=act,
param_attr=ParamAttr(name=bn_name + ".weight"),
bias_attr=ParamAttr(name=bn_name + ".bias"),
moving_mean_name=bn_name + ".running_mean",
moving_variance_name=bn_name + ".running_var")
def __init__(
self,
in_channels,
out_channels,
kernel_size,
stride=1,
groups=1,
is_vd_mode=False,
act=None,
name=None, ):
super(ConvBNLayer, self).__init__()
self.is_vd_mode = is_vd_mode
self._pool2d_avg = nn.AvgPool2D(
kernel_size=2, stride=2, padding=0, ceil_mode=True)
self._conv = nn.Conv2D(
in_channels=in_channels,
out_channels=out_channels,
kernel_size=kernel_size,
stride=stride,
padding=(kernel_size - 1) // 2,
groups=groups,
weight_attr=ParamAttr(name=name + "_weights"),
bias_attr=False)
if name == "conv1":
bn_name = "bn_" + name
else:
bn_name = "bn" + name[3:]
self._batch_norm = nn.BatchNorm(
out_channels,
act=act,
param_attr=ParamAttr(name=bn_name + '_scale'),
bias_attr=ParamAttr(bn_name + '_offset'),
moving_mean_name=bn_name + '_mean',
moving_variance_name=bn_name + '_variance')
def __init__(self,
ch_in,
ch_out,
filter_size=3,
stride=1,
groups=1,
padding=0,
act="leaky",
name=None):
super(ConvBNLayer, self).__init__()
self.conv = nn.Conv2d(in_channels=ch_in,
out_channels=ch_out,
kernel_size=filter_size,
stride=stride,
padding=padding,
groups=groups,
weight_attr=ParamAttr(name=name +
'.conv.weights'),
bias_attr=False)
bn_name = name + '.bn'
self.batch_norm = nn.BatchNorm2d(
ch_out,
weight_attr=ParamAttr(name=bn_name + '.scale',
regularizer=L2Decay(0.)),
bias_attr=ParamAttr(name=bn_name + '.offset',
regularizer=L2Decay(0.)))
self.act = act
def __init__(self,
anchors=[[10, 13], [16, 30], [33, 23], [30, 61], [62, 45],
[59, 119], [116, 90], [156, 198], [373, 326]],
anchor_masks=[[6, 7, 8], [3, 4, 5], [0, 1, 2]],
num_classes=80,
loss='YOLOv3Loss'):
super(YOLOv3Head, self).__init__()
self.num_classes = num_classes
self.loss = loss
self.parse_anchor(anchors, anchor_masks)
self.num_outputs = len(self.anchors)
self.yolo_outputs = []
for i in range(len(self.anchors)):
num_filters = self.num_outputs * (self.num_classes + 5)
name = 'yolo_output.{}'.format(i)
yolo_output = self.add_sublayer(
name,
nn.Conv2D(in_channels=1024 // (2**i),
out_channels=num_filters,
kernel_size=1,
stride=1,
padding=0,
weight_attr=ParamAttr(name=name + '.conv.weights'),
bias_attr=ParamAttr(name=name + '.conv.bias',
regularizer=L2Decay(0.))))
self.yolo_outputs.append(yolo_output)
def __init__(self, config=None):
super(Net, self).__init__(config)
if self.config['data_format'] in [
"NC", "NCL", "NCHW", "NCDHW", "NCHW"
]:
param_shape = [self.config['input_shape'][1]]
else:
param_shape = [self.config['input_shape'][-1]]
dtype = self.config['dtype']
self.mean = self.create_parameter(
dtype=dtype,
attr=ParamAttr(initializer=paddle.nn.initializer.Constant(0.0),
trainable=False,
do_model_average=True),
shape=param_shape)
self.variance = self.create_parameter(
dtype=dtype,
attr=ParamAttr(initializer=paddle.nn.initializer.Constant(1.0),
trainable=False,
do_model_average=True),
shape=param_shape)
self.weight = self.create_parameter(
shape=param_shape,
dtype=dtype,
default_initializer=paddle.nn.initializer.Constant(1.0))
self.bias = self.create_parameter(shape=param_shape,
dtype=dtype,
is_bias=True)
def __init__(self,
num_channels: int,
num_filters: int,
filter_size: int,
stride: int = 1,
groups: int = 1,
act: str = None,
name: str = None):
super(ConvBNLayer, self).__init__()
self._conv = Conv2d(in_channels=num_channels,
out_channels=num_filters,
kernel_size=filter_size,
stride=stride,
padding=(filter_size - 1) // 2,
groups=groups,
weight_attr=ParamAttr(name=name + "_weights"),
bias_attr=False)
if name == "conv1":
bn_name = "bn_" + name
else:
bn_name = "bn" + name[3:]
self._batch_norm = BatchNorm(
num_filters,
act=act,
param_attr=ParamAttr(name=bn_name + '_scale'),
bias_attr=ParamAttr(bn_name + '_offset'),
moving_mean_name=bn_name + '_mean',
moving_variance_name=bn_name + '_variance')
def initial_type(name: str, use_bias: bool = False):
param_attr = ParamAttr(name=name + "_weights")
if use_bias:
bias_attr = ParamAttr(name=name + "_offset")
else:
bias_attr = False
return param_attr, bias_attr
def __init__(self,
in_c,
out_c,
filter_size,
stride,
padding,
num_groups=1,
if_act=True,
act=None,
use_cudnn=True,
name=""):
super(ConvBNLayer, self).__init__()
self.if_act = if_act
self.act = act
self.conv = Conv2D(in_channels=in_c,
out_channels=out_c,
kernel_size=filter_size,
stride=stride,
padding=padding,
groups=num_groups,
weight_attr=ParamAttr(name=name + "_weights"),
bias_attr=False)
self.bn = BatchNorm(num_channels=out_c,
act=None,
param_attr=ParamAttr(name=name + "_bn_scale",
regularizer=L2Decay(0.0)),
bias_attr=ParamAttr(name=name + "_bn_offset",
regularizer=L2Decay(0.0)),
moving_mean_name=name + "_bn_mean",
moving_variance_name=name + "_bn_variance")
def __init__(self, ch_in, ch_out=128, num_classes=80, conv_num=2):
super(HMHead, self).__init__()
head_conv = nn.Sequential()
for i in range(conv_num):
name = 'conv.{}'.format(i)
head_conv.add_sublayer(
name,
nn.Conv2D(in_channels=ch_in if i == 0 else ch_out,
out_channels=ch_out,
kernel_size=3,
padding=1,
weight_attr=ParamAttr(initializer=Normal(0, 0.01)),
bias_attr=ParamAttr(learning_rate=2.,
regularizer=L2Decay(0.))))
head_conv.add_sublayer(name + '.act', nn.ReLU())
self.feat = self.add_sublayer('hm_feat', head_conv)
bias_init = float(-np.log((1 - 0.01) / 0.01))
self.head = self.add_sublayer(
'hm_head',
nn.Conv2D(in_channels=ch_out,
out_channels=num_classes,
kernel_size=1,
weight_attr=ParamAttr(initializer=Normal(0, 0.01)),
bias_attr=ParamAttr(learning_rate=2.,
regularizer=L2Decay(0.),
initializer=Constant(bias_init))))
def __init__(self,
num_channels,
num_filters,
filter_size,
stride=1,
pad=0,
groups=1,
act="relu",
name=None):
super(BNACConvLayer, self).__init__()
self._batch_norm = BatchNorm(
num_channels,
act=act,
param_attr=ParamAttr(name=name + '_bn_scale'),
bias_attr=ParamAttr(name + '_bn_offset'),
moving_mean_name=name + '_bn_mean',
moving_variance_name=name + '_bn_variance')
self._conv = Conv2D(in_channels=num_channels,
out_channels=num_filters,
kernel_size=filter_size,
stride=stride,
padding=pad,
groups=groups,
weight_attr=ParamAttr(name=name + "_weights"),
bias_attr=False)
def __init__(self,
num_channels: int,
filter_size: int,
num_filters: int,
stride: int,
padding: int,
channels: int = None,
num_groups: int = 1,
if_act: bool = True,
act: str = 'relu',
name: str = None):
super(ConvBNLayer, self).__init__()
self._if_act = if_act
assert act in ['relu', 'swish'], \
"supported act are {} but your act is {}".format(
['relu', 'swish'], act)
self._act = act
self._conv = Conv2d(in_channels=num_channels,
out_channels=num_filters,
kernel_size=filter_size,
stride=stride,
padding=padding,
groups=num_groups,
weight_attr=ParamAttr(initializer=MSRA(),
name=name + "_weights"),
bias_attr=False)
self._batch_norm = BatchNorm(
num_filters,
param_attr=ParamAttr(name=name + "_bn_scale"),
bias_attr=ParamAttr(name=name + "_bn_offset"),
moving_mean_name=name + "_bn_mean",
moving_variance_name=name + "_bn_variance")