3D Convolution

Applies a 3D convolution over the input volume.

Usage

mlx_conv3d(
  input,
  weight,
  stride = c(1L, 1L, 1L),
  padding = c(0L, 0L, 0L),
  dilation = c(1L, 1L, 1L),
  groups = 1L,
  device = mlx_default_device()
)

Arguments

input

Input mlx array. Shape depends on dimensionality (see individual functions).

weight

Weight array. Shape depends on dimensionality (see individual functions).

stride

Stride of the convolution. Can be a scalar or vector (length depends on dimensionality). Default: 1 for 1D, c(1,1) for 2D, c(1,1,1) for 3D.

padding

Amount of zero padding. Can be a scalar or vector (length depends on dimensionality). Default: 0 for 1D, c(0,0) for 2D, c(0,0,0) for 3D.

dilation

Spacing between kernel elements. Can be a scalar or vector (length depends on dimensionality). Default: 1 for 1D, c(1,1) for 2D, c(1,1,1) for 3D.

groups

Number of blocked connections from input to output channels. Default: 1.

device

Execution target: supply "gpu", "cpu", or an mlx_stream created via mlx_new_stream(). Default: mlx_default_device().

Value

Convolved output array

Details

Input has shape (N, D, H, W, C_in) where N is batch size, D, H, W are depth, height and width, and C_in is number of input channels. Weight has shape (C_out, kernel_d, kernel_h, kernel_w, C_in).

See also

mlx.core.conv3d