def __init__(self, in_channels, out_channels):
super().__init__()
self.double_conv = nn.Sequential(
nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1),
BatchNorm2d(out_channels), nn.ReLU(inplace=True),
nn.Conv2d(out_channels, out_channels, kernel_size=3, padding=1),
BatchNorm2d(out_channels), nn.ReLU(inplace=True))
def __init__(self, in_features, kernel_size, padding):
super(ResBlock2d, self).__init__()
self.conv1 = nn.Conv2d(in_channels=in_features, out_channels=in_features, kernel_size=kernel_size,
padding=padding)
self.conv2 = nn.Conv2d(in_channels=in_features, out_channels=in_features, kernel_size=kernel_size,
padding=padding)
self.norm1 = BatchNorm2d(in_features, affine=True)
self.norm2 = BatchNorm2d(in_features, affine=True)
def __init__(self, in_dim, reduction_dim, bins):
super(PPM, self).__init__()
self.features = []
for bin in bins:
self.features.append(
nn.Sequential(
nn.AdaptiveAvgPool2d(bin),
nn.Conv2d(in_dim, reduction_dim, kernel_size=1,
bias=False), BatchNorm2d(reduction_dim),
nn.ReLU(inplace=True)))
self.features = nn.ModuleList(self.features)
self.gamma = Parameter(torch.zeros(1))
self.conv51 = nn.Sequential(
nn.Conv2d(512, 512, 3, padding=1, bias=False), BatchNorm2d(512),
nn.ReLU())
def __init__(self,
in_features,
out_features,
groups=1,
kernel_size=3,
padding=1):
super(SameBlock2d, self).__init__()
self.conv = nn.Conv2d(in_channels=in_features,
out_channels=out_features,
kernel_size=kernel_size,
padding=padding,
groups=groups)
self.norm = BatchNorm2d(out_features, affine=True)
def __init__(self, in_channels):
super(attentionHead, self).__init__()
self.conv5a = nn.Sequential(
nn.Conv2d(in_channels, in_channels, 3, padding=1, bias=False),
BatchNorm2d(in_channels), nn.ReLU())
self.sa = PAM_Module(in_channels)
