def __init__(self, in_channel, n_class):
super().__init__()
self.conv = nn.Sequential(
nn.Conv2d(in_channel, in_channel, kernel_size=3, padding=1, bias=False),
nn.BatchNorm2d(in_channel),
nn.ReLU(),
nn.Conv2d(in_channel, n_class, kernel_size=1),
)
for m in self.modules():
if isinstance(m, nn.Conv2d):
init_weights(m, init_type='kaiming')
elif isinstance(m, nn.BatchNorm2d):
init_weights(m, init_type='kaiming')
def __init__(self, in_channel, inter_channel, out_channel):
super().__init__()
self.conv = nn.Sequential(
nn.Conv2d(in_channel, inter_channel, 3, 2, 1, bias=False),
nn.BatchNorm2d(inter_channel),
nn.ReLU(True),
nn.Conv2d(inter_channel, inter_channel, 3, 1, 1, bias=False),
nn.BatchNorm2d(inter_channel),
nn.ReLU(True),
nn.Conv2d(inter_channel, out_channel, 3, 1, 1, bias=False),
nn.BatchNorm2d(out_channel),
)
for m in self.modules():
if isinstance(m, nn.Conv2d):
init_weights(m, init_type='kaiming')
elif isinstance(m, nn.BatchNorm2d):
init_weights(m, init_type='kaiming')
def __init__(self, in_channel, n_class):
super().__init__()
self.n_class = n_class
self.conv = _FCNHead(in_channel, n_class)
inter_channel = in_channel // 2
self.node = 64
self.st = nn.ModuleList()
for i in range(n_class):
self.st.append(
squeeze_and_expand(in_channel, self.node, inter_channel))
self.gcn = GCN(inter_channel, int(self.node * n_class))
for m in self.modules():
if isinstance(m, nn.Conv2d):
init_weights(m, init_type='kaiming')
elif isinstance(m, nn.BatchNorm2d):
init_weights(m, init_type='kaiming')