def __init__(
self,
in_channels,
out_channels,
dim,
kernel_size,
hidden_channels=None,
dilation=1,
bias=True,
**kwargs,
):
super(XConv, self).__init__()
self.in_channels = in_channels
if hidden_channels is None:
hidden_channels = in_channels // 4
assert hidden_channels > 0
self.hidden_channels = hidden_channels
self.out_channels = out_channels
self.dim = dim
self.kernel_size = kernel_size
self.dilation = dilation
self.kwargs = kwargs
C_in, C_delta, C_out = in_channels, hidden_channels, out_channels
D, K = dim, kernel_size
self.mlp1 = S(
L(dim, C_delta),
ELU(),
BN(C_delta),
L(C_delta, C_delta),
ELU(),
BN(C_delta),
Reshape(-1, K, C_delta),
)
self.mlp2 = S(
L(D * K, K**2),
ELU(),
BN(K**2),
Reshape(-1, K, K),
Conv1d(K, K**2, K, groups=K),
ELU(),
BN(K**2),
Reshape(-1, K, K),
Conv1d(K, K**2, K, groups=K),
BN(K**2),
Reshape(-1, K, K),
)
C_in = C_in + C_delta
depth_multiplier = int(ceil(C_out / C_in))
self.conv = S(
Conv1d(C_in, C_in * depth_multiplier, K, groups=C_in),
Reshape(-1, C_in * depth_multiplier),
L(C_in * depth_multiplier, C_out, bias=bias),
)
self.reset_parameters()
def __init__(self, in_channels, out_channels, dim, kernel_size,
hidden_channels=None, dilation=1, bias=True, BiLinear=BiLinear, BiConv1d=BiConv1d, ifFirst=False, **kwargs):
super(BiXConv, self).__init__()
if knn_graph is None:
raise ImportError('`XConv` requires `torch-cluster`.')
self.in_channels = in_channels
if hidden_channels is None:
hidden_channels = in_channels // 4
assert hidden_channels > 0
self.hidden_channels = hidden_channels
self.out_channels = out_channels
self.dim = dim
self.kernel_size = kernel_size
self.dilation = dilation
self.kwargs = kwargs
C_in, C_delta, C_out = in_channels, hidden_channels, out_channels
D, K = dim, kernel_size
if ifFirst:
Lin1 = Lin
else:
Lin1 = BiLinear
self.mlp1 = S(
Lin1(dim, C_delta),
Hardtanh(),
BN(C_delta),
BiLinear(C_delta, C_delta),
Hardtanh(),
BN(C_delta),
Reshape(-1, K, C_delta),
)
self.mlp2 = S(
Lin1(D * K, K**2),
Hardtanh(),
BN(K**2),
Reshape(-1, K, K),
BiConv1d(K, K**2, K, groups=K),
Hardtanh(),
BN(K**2),
Reshape(-1, K, K),
BiConv1d(K, K**2, K, groups=K),
BN(K**2),
Reshape(-1, K, K),
)
C_in = C_in + C_delta
depth_multiplier = int(ceil(C_out / C_in))
self.conv = S(
BiConv1d(C_in, C_in * depth_multiplier, K, groups=C_in),
Reshape(-1, C_in * depth_multiplier),
BiLinear(C_in * depth_multiplier, C_out, bias=bias),
)
self.reset_parameters()
def __init__(self, in_channels: int, out_channels: int, dim: int,
kernel_size: int, hidden_channels: Optional[int] = None,
dilation: int = 1, bias: bool = True, num_workers: int = 1):
super(XConv, self).__init__()
if knn_graph is None:
raise ImportError('`XConv` requires `torch-cluster`.')
self.in_channels = in_channels
if hidden_channels is None:
hidden_channels = in_channels // 4
assert hidden_channels > 0
self.hidden_channels = hidden_channels
self.out_channels = out_channels
self.dim = dim
self.kernel_size = kernel_size
self.dilation = dilation
self.num_workers = num_workers
C_in, C_delta, C_out = in_channels, hidden_channels, out_channels
D, K = dim, kernel_size
self.mlp1 = S(
L(dim, C_delta),
ELU(),
BN(C_delta),
L(C_delta, C_delta),
ELU(),
BN(C_delta),
Reshape(-1, K, C_delta),
)
self.mlp2 = S(
L(D * K, K**2),
ELU(),
BN(K**2),
Reshape(-1, K, K),
Conv1d(K, K**2, K, groups=K),
ELU(),
BN(K**2),
Reshape(-1, K, K),
Conv1d(K, K**2, K, groups=K),
BN(K**2),
Reshape(-1, K, K),
)
C_in = C_in + C_delta
depth_multiplier = int(ceil(C_out / C_in))
self.conv = S(
Conv1d(C_in, C_in * depth_multiplier, K, groups=C_in),
Reshape(-1, C_in * depth_multiplier),
L(C_in * depth_multiplier, C_out, bias=bias),
)
self.reset_parameters()
def __init__(self):
super(PointModel, self).__init__()
# self.stepWeights = GNNFixedK()
# self.dropout = torch.nn.Dropout(p=0.25)
self.k_size = 12
self.layer1 = S(L(7, 32), ReLU(), L(32, 16))
self.layerg = S(L(19, 32), ReLU(), L(32, 8))
self.layer2 = S(L(24, 32), ReLU(), L(32, 16))
self.layerg2 = S(L(16, 32), ReLU(), L(32, 8))
self.layer3 = S(L(24, 32), ReLU(), L(32, 16))
self.layerg3 = S(L(16, 32), ReLU(), L(32, 12))
self.layer4 = S(L(27, 64), ReLU(), L(64, 1))
self.layer5 = S(L(13, 64), ReLU(), L(64, 3))
self.reset_parameters()
def __init__(self):
super(GNNFixedK, self).__init__()
self.layer1 = S(L(8, 32), ReLU(), L(32, 16))
self.layerg = S(L(19, 32), ReLU(), L(32, 8))
self.layer2 = S(L(24, 32), ReLU(), L(32, 16))
self.layerg2 = S(L(16, 32), ReLU(), L(32, 8))
self.layer3 = S(L(24, 32), ReLU(), L(32, 16))
self.layerg3 = S(L(16, 32), ReLU(), L(32, 12))
self.layer4 = S(L(27, 64), ReLU(), L(64, 1))
self.reset_parameters()
def __init__(self):
super(PneumoniaFakeModel, self).__init__()
# Image size [3, 3, 256, 256]
self.conv1 = Conv2d(in_channels=3,
out_channels=12,
kernel_size=3,
stride=1,
padding=1)
self.fc2 = L(256, 50)
self.fc3 = L(50, 2)
self.pool1 = MaxPool2d(
kernel_size=2) # Reduce the image size be factor 2
self.relu2 = R()
self.sig = S()
self.bn1 = BatchNorm2d(num_features=12)
self.pool2 = MaxPool2d(
kernel_size=2) # Reduce the image size be factor 2