1.Conv3d

class torch.nn.Conv3d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True)

Parameters：

• in_channels(int) – 輸入訊號的通道
• out_channels(int) – 卷積產生的通道
• kernel_size(intortuple) - 卷積核的尺寸
• stride(intortuple,optional) - 卷積步長
• padding(intortuple,optional
  ) - 輸入的每一條邊補充0的層數
• dilation(intortuple,optional) – 卷積核元素之間的間距
• groups(int,optional) – 從輸入通道到輸出通道的阻塞連線數
• bias(bool,optional) - 如果bias=True，新增偏置

三維卷積層, 輸入的尺度是(N, C_in,D,H,W)，輸出尺度（N,C_out,D_out,H_out,W_out）

shape:
input: (N,C_in,D_in,H_in,W_in)
output: (N,C_out,D_out,H_out,W_out)

官網案例：

>>> #
 
 With square kernels and equal stride
>>> m = nn.Conv3d(16, 33, 3, stride=2)
>>> # non-square kernels and unequal stride and with padding
>>> m = nn.Conv3d(16, 33, (3, 5, 2), stride=(2, 1, 1), padding=(4, 2, 0))
>>> input = autograd.Variable(torch.randn(20, 16, 10, 50, 100))
 
>>> output = m(input)