def __init__(self,
in_channels,
out_channels,
kernel_size,
A,
stride=1,
residual=True):
super().__init__()
self.A = nn.Parameter(A + 0.0001 * torch.ones(A.size()))
self.gcn = ConvTemporalGraphical(in_channels, out_channels,
kernel_size)
self.bn = nn.BatchNorm2d(out_channels)
if not residual:
self.residual = lambda x: 0
elif (in_channels == out_channels) and (stride == 1):
self.residual = lambda x: x
else:
self.residual = nn.Sequential(
nn.Conv2d(in_channels,
out_channels,
kernel_size=1,
stride=(stride, 1)),
nn.BatchNorm2d(out_channels),
)
self.relu = nn.ReLU(inplace=True)
def __init__(
self,
in_channels,
out_channels,
kernel_size,
stride=1,
dropout=0,
isStgcn=False,
residual=True,
):
super().__init__()
assert len(kernel_size) == 2
assert kernel_size[0] % 2 == 1
padding = ((kernel_size[0] - 1) // 2, 0)
if isStgcn:
self.gcn = ConvTemporalGraphical(in_channels, out_channels,
kernel_size[1])
else:
self.gcn = ConvTemporalGraphicalBatchA(in_channels, out_channels,
kernel_size[1])
self.tcn = nn.Sequential(
nn.BatchNorm2d(out_channels),
nn.ReLU(inplace=True),
nn.Conv2d(
out_channels,
out_channels,
(kernel_size[0], 1),
(stride, 1),
padding,
),
nn.BatchNorm2d(out_channels),
nn.Dropout(dropout, inplace=True),
)
if not residual:
self.residual = zero
elif (in_channels == out_channels) and (stride == 1):
self.residual = iden
else:
self.residual = nn.Sequential(
nn.Conv2d(in_channels,
out_channels,
kernel_size=1,
stride=(stride, 1)),
nn.BatchNorm2d(out_channels),
)
self.relu = nn.ReLU(inplace=True)