In this article

Convolution

|
  • Share via
  •  Edit this article

Convolutions

[class] ConvND

(ConvND in-channels out-channels kernel-size &key (groups 1) (stride 1) (dilation 1) (padding 0) (bias t))

Applies a convolution over a tensor with a given weight and optional bias. NOTE: unlike PyTorch, this implementation is not limited to only 2d convolutions and instead works for any number of dimensions.

[function] !convnd

(!convnd x weight &key (bias nil) (groups 1) (stride 1) (dilation 1) (padding 0))
Applies a convolutional layer over a tensor x with a given weight and optional bias.