Function convGeneralDilated

convGeneralDilated(
    lhs: Array,
    rhs: Array,
    windowStrides: number[],
    padding: PaddingType,
    __namedParameters?: {
        featureGroupCount?: number;
        lhsDilation?: number[];
        rhsDilation?: number[];
    },
): Array
General n-dimensional convolution operator, with optional dilation.

The semantics of this operation mimic the jax.lax.conv_general_dilated function in JAX, which wraps XLA's general convolution operator.
Parameters
- lhs: Array
  Input tensor; shape [N, C_in, ...xs]
- rhs: Array
  Convolution kernel; shape [C_out, C_in / G, ...ks]
- windowStrides: number[]
  Strides for each spatial dimension
- padding: PaddingType
  Padding for each spatial dimension, or a string ("VALID", "SAME", or "SAME_LOWER")
- __namedParameters: { featureGroupCount?: number; lhsDilation?: number[]; rhsDilation?: number[] } = {}
Returns Array
- Defined in src/library/lax.ts:172