def __init__(self,
inplanes,
planes,
dilation=1,
downsample=None,
norm_type="BN"):
"""Residual Block for DarkNet.
This module has the dowsample layer (optional),
1x1 conv layer and 3x3 conv layer.
"""
super(DarkBlock, self).__init__()
self.downsample = downsample
self.bn1 = get_norm(norm_type, inplanes, eps=1e-4, momentum=0.03)
self.bn2 = get_norm(norm_type, planes, eps=1e-4, momentum=0.03)
self.conv1 = nn.Conv2d(planes,
inplanes,
kernel_size=1,
stride=1,
padding=0,
bias=False)
self.conv2 = nn.Conv2d(inplanes,
planes,
kernel_size=3,
stride=1,
padding=dilation,
dilation=dilation,
bias=False)
self.activation = Mish()
def __init__(self, in_channels, out_channels, kernel_size, stride=1, activation=Mish()):
super(Conv, self).__init__()
self.conv = nn.Sequential(
nn.Conv2d(in_channels, out_channels, kernel_size, stride, kernel_size//2, bias=False),
nn.BatchNorm2d(out_channels),
activation,
)
def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
super(BottleneckCSP2, self).__init__()
c_ = int(c2) # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = nn.Conv2d(c_, c_, 1, 1, bias=False)
self.cv3 = Conv(2 * c_, c2, 1, 1)
self.bn = nn.BatchNorm2d(2 * c_)
self.act = Mish()
self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
def _make_stem_layer(self):
self.conv1 = nn.Conv2d(3,
self.inplanes,
kernel_size=3,
stride=1,
padding=1,
bias=False)
self.bn1 = get_norm(self.norm_type,
self.inplanes,
eps=1e-4,
momentum=0.03)
self.act1 = Mish()
def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5, k=(5, 9, 13)):
super(SPPCSP, self).__init__()
c_ = int(2 * c2 * e) # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)
self.cv3 = Conv(c_, c_, 3, 1)
self.cv4 = Conv(c_, c_, 1, 1)
self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
self.cv5 = Conv(4 * c_, c_, 1, 1)
self.cv6 = Conv(c_, c_, 3, 1)
self.bn = nn.BatchNorm2d(2 * c_)
self.act = Mish()
self.cv7 = Conv(2 * c_, c2, 1, 1)
def __init__(self,
c1,
c2,
k=1,
s=1,
p=None,
g=1,
act=True): # ch_in, ch_out, kernel, stride, padding, groups
super(ConvSqu, self).__init__()
self.conv = nn.Conv2d(c1,
c2,
k,
s,
autopad(k, p),
groups=g,
bias=False)
self.act = Mish() if act else nn.Identity()
def __init__(
self,
c1,
c2,
n=1,
shortcut=False,
g=1,
e=0.5,
activation_type='hardswish',
): # ch_in, ch_out, number, shortcut, groups, expansion
super(BottleneckCSP2, self).__init__()
Conv_ = functools.partial(Conv, activation_type=activation_type)
Bottleneck_ = functools.partial(Bottleneck,
activation_type=activation_type)
c_ = int(c2) # hidden channels
self.cv1 = Conv_(c1, c_, 1, 1)
self.cv2 = nn.Conv2d(c_, c_, 1, 1, bias=False)
self.cv3 = Conv_(2 * c_, c2, 1, 1)
self.bn = nn.BatchNorm2d(2 * c_)
self.act = Mish()
self.m = nn.Sequential(
*[Bottleneck_(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
def __init__(self,
c1,
c2,
n=1,
shortcut=False,
g=1,
e=0.5,
k=(5, 9, 13),
activation_type='hardswish'):
super(SPPCSP, self).__init__()
Conv_ = functools.partial(Conv, activation_type=activation_type)
c_ = int(2 * c2 * e) # hidden channels
self.cv1 = Conv_(c1, c_, 1, 1)
self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)
self.cv3 = Conv_(c_, c_, 3, 1)
self.cv4 = Conv_(c_, c_, 1, 1)
self.m = nn.ModuleList(
[nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
self.cv5 = Conv_(4 * c_, c_, 1, 1)
self.cv6 = Conv_(c_, c_, 3, 1)
self.bn = nn.BatchNorm2d(2 * c_)
self.act = Mish()
self.cv7 = Conv_(2 * c_, c2, 1, 1)
def ConvNormActivation(inplanes,
planes,
kernel_size=3,
stride=1,
padding=0,
dilation=1,
groups=1,
norm_type="BN"):
"""
A help function to build a 'conv-bn-activation' module
"""
layers = []
layers.append(nn.Conv2d(inplanes,
planes,
kernel_size=kernel_size,
stride=stride,
padding=padding,
dilation=dilation,
groups=groups,
bias=False))
layers.append(get_norm(norm_type, planes, eps=1e-4, momentum=0.03))
layers.append(Mish())
return nn.Sequential(*layers)