Conv3d#

class Conv3d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, conv_mode='cross_correlation')[source]#

Applies a 3D convolution over an input tensor.

For instance, given an input of the size \((N, C_{\text{in}}, T, H, W)\), this layer generates an output of the size \((N, C_{\text{out}}, T_{\text{out}}, H_{\text{out}}, W_{\text{out}})\) through the process described as below:

\[\text{out}(N_i, C_{\text{out}_j}) = \text{bias}(C_{\text{out}_j}) + \sum_{k = 0}^{C_{\text{in}} - 1} \text{weight}(C_{\text{out}_j}, k) \star \text{input}(N_i, k)\]

where \(\star\) is the valid 3D cross-correlation operator, \(N\) is batch size, \(C\) denotes number of channels.

When groups == in_channels and out_channels == K * in_channels, where K is a positive integer, this operation is also known as depthwise convolution.

In other words, for an input of size \((N, C_{in}, T_{int}, H_{in}, W_{in})\), a depthwise convolution with a depthwise multiplier K, can be constructed by arguments \((in\_channels=C_{in}, out\_channels=C_{in} \times K, ..., groups=C_{in})\).

Parameters:

  • in_channels (int) – number of input channels.

  • out_channels (int) – number of output channels.

  • kernel_size (Union[int, Tuple[int, int, int]]) – size of weight on spatial dimensions. If kernel_size is an int, the actual kernel size would be (kernel_size, kernel_size, kernel_size).

  • stride (Union[int, Tuple[int, int, int]]) – stride of the 3D convolution operation. Default: 1

  • padding (Union[int, Tuple[int, int, int]]) – size of the paddings added to the input on both sides of its spatial dimensions. Only zero-padding is supported. Default: 0

  • dilation (Union[int, Tuple[int, int, int]]) – dilation of the 3D convolution operation. Default: 1

  • groups (int) – number of groups into which the input and output channels are divided, so as to perform a grouped convolution. When groups is not 1, in_channels and out_channels must be divisible by groups, and the shape of weight should be (groups, out_channel // groups, in_channels // groups, depth, height, width). Default: 1

  • bias (bool) – whether to add a bias onto the result of convolution. Default: True

  • conv_mode (str) – Supports cross_correlation. Default: cross_correlation

Note

  • weight usually has shape (out_channels, in_channels, depth, height, width) , if groups is not 1, shape will be (groups, out_channels // groups, in_channels // groups, depth, height, width)

  • bias usually has shape (1, out_channels, *1)

Examples

>>> import numpy as np
>>> m = M.Conv3d(in_channels=3, out_channels=1, kernel_size=3)
>>> inp = mge.tensor(np.arange(0, 384).astype("float32").reshape(2, 3, 4, 4, 4))
>>> oup = m(inp)
>>> oup.numpy().shape
(2, 1, 2, 2, 2)