class torch.nn.Conv3d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, padding_mode='zeros', device=None, dtype=None)[source]

Applies a 3D convolution over an input signal composed of several input planes.

In the simplest case, the output value of the layer with input size (N,Cin,D,H,W)(N, C_{in}, D, H, W) and output (N,Cout,Dout,Hout,Wout)(N, C_{out}, D_{out}, H_{out}, W_{out}) can be precisely described as:

out(Ni,Coutj)=bias(Coutj)+k=0Cin1weight(Coutj,k)input(Ni,k)out(N_i, C_{out_j}) = bias(C_{out_j}) + \sum_{k = 0}^{C_{in} - 1} weight(C_{out_j}, k) \star input(N_i, k)

where \star is the valid 3D cross-correlation operator

This module supports TensorFloat32.

  • stride controls the stride for the cross-correlation.

  • padding controls the amount of padding applied to the input. It can be either a string {‘valid’, ‘same’} or a tuple of ints giving the amount of implicit padding applied on both sides.

  • dilation controls the spacing between the kernel points; also known as the à trous algorithm. It is harder to describe, but this link has a nice visualization of what dilation does.

  • groups controls the connections between inputs and outputs. in_channels and out_channels must both be divisible by groups. For example,

    • At groups=1, all inputs are convolved to all outputs.

    • At groups=2, the operation becomes equivalent to having two conv layers side by side, each seeing half the input channels and producing half the output channels, and both subsequently concatenated.

    • At groups= in_channels, each input channel is convolved with its own set of filters (of size out_channelsin_channels\frac{\text{out\_channels}}{\text{in\_channels}}).

The parameters kernel_size, stride, padding, dilation can either be:

  • a single int – in which case the same value is used for the depth, height and width dimension

  • a tuple of three ints – in which case, the first int is used for the depth dimension, the second int for the height dimension and the third int for the width dimension


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

In other words, for an input of size (N,Cin,Lin)(N, C_{in}, L_{in}), a depthwise convolution with a depthwise multiplier K can be performed with the arguments (Cin=Cin,Cout=Cin×K,...,groups=Cin)(C_\text{in}=C_\text{in}, C_\text{out}=C_\text{in} \times \text{K}, ..., \text{groups}=C_\text{in}).


In some circumstances when given tensors on a CUDA device and using CuDNN, this operator may select a nondeterministic algorithm to increase performance. If this is undesirable, you can try to make the operation deterministic (potentially at a performance cost) by setting torch.backends.cudnn.deterministic = True. See Reproducibility for more information.


padding='valid' is the same as no padding. padding='same' pads the input so the output has the shape as the input. However, this mode doesn’t support any stride values other than 1.

  • in_channels (int) – Number of channels in the input image

  • out_channels (int) – Number of channels produced by the convolution

  • kernel_size (int or tuple) – Size of the convolving kernel

  • stride (int or tuple, optional) – Stride of the convolution. Default: 1

  • padding (int, tuple or str, optional) – Padding added to all six sides of the input. Default: 0

  • padding_mode (string, optional) – 'zeros', 'reflect', 'replicate' or 'circular'. Default: 'zeros'

  • dilation (int or tuple, optional) – Spacing between kernel elements. Default: 1

  • groups (int, optional) – Number of blocked connections from input channels to output channels. Default: 1

  • bias (bool, optional) – If True, adds a learnable bias to the output. Default: True

  • Input: (N,Cin,Din,Hin,Win)(N, C_{in}, D_{in}, H_{in}, W_{in}) or (Cin,Din,Hin,Win)(C_{in}, D_{in}, H_{in}, W_{in})

  • Output: (N,Cout,Dout,Hout,Wout)(N, C_{out}, D_{out}, H_{out}, W_{out}) or (Cout,Dout,Hout,Wout)(C_{out}, D_{out}, H_{out}, W_{out}), where

    Dout=Din+2×padding[0]dilation[0]×(kernel_size[0]1)1stride[0]+1D_{out} = \left\lfloor\frac{D_{in} + 2 \times \text{padding}[0] - \text{dilation}[0] \times (\text{kernel\_size}[0] - 1) - 1}{\text{stride}[0]} + 1\right\rfloor
    Hout=Hin+2×padding[1]dilation[1]×(kernel_size[1]1)1stride[1]+1H_{out} = \left\lfloor\frac{H_{in} + 2 \times \text{padding}[1] - \text{dilation}[1] \times (\text{kernel\_size}[1] - 1) - 1}{\text{stride}[1]} + 1\right\rfloor
    Wout=Win+2×padding[2]dilation[2]×(kernel_size[2]1)1stride[2]+1W_{out} = \left\lfloor\frac{W_{in} + 2 \times \text{padding}[2] - \text{dilation}[2] \times (\text{kernel\_size}[2] - 1) - 1}{\text{stride}[2]} + 1\right\rfloor
  • ~Conv3d.weight (Tensor) – the learnable weights of the module of shape (out_channels,in_channelsgroups,(\text{out\_channels}, \frac{\text{in\_channels}}{\text{groups}}, kernel_size[0],kernel_size[1],kernel_size[2])\text{kernel\_size[0]}, \text{kernel\_size[1]}, \text{kernel\_size[2]}). The values of these weights are sampled from U(k,k)\mathcal{U}(-\sqrt{k}, \sqrt{k}) where k=groupsCini=02kernel_size[i]k = \frac{groups}{C_\text{in} * \prod_{i=0}^{2}\text{kernel\_size}[i]}

  • ~Conv3d.bias (Tensor) – the learnable bias of the module of shape (out_channels). If bias is True, then the values of these weights are sampled from U(k,k)\mathcal{U}(-\sqrt{k}, \sqrt{k}) where k=groupsCini=02kernel_size[i]k = \frac{groups}{C_\text{in} * \prod_{i=0}^{2}\text{kernel\_size}[i]}


>>> # 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 = torch.randn(20, 16, 10, 50, 100)
>>> output = m(input)


Access comprehensive developer documentation for PyTorch

View Docs


Get in-depth tutorials for beginners and advanced developers

View Tutorials


Find development resources and get your questions answered

View Resources