Function conv3dTranspose

  • conv3dTranspose<T>(x, filter, outputShape, strides, pad): T

  • Computes the transposed 3D convolution of a volume, also known as a deconvolution.

    Type Parameters

    Parameters

    • x: TensorLike | T

      The input image, of rank 5 or rank 4, of shape [batch, depth, height, width, inDepth]. If rank 4, batch of 1 is assumed.

    • filter: TensorLike | Tensor5D

      The filter, rank 4, of shape [depth, filterHeight, filterWidth, outDepth, inDepth]. inDepth must match inDepth in x.

    • outputShape: [number, number, number, number] | [number, number, number, number, number]

      Output shape, of rank 5 or rank 4: [batch, depth, height, width, outDepth]. If rank 3, batch of 1 is assumed.

    • strides: number | [number, number, number]

      The strides of the original convolution: [strideDepth, strideHeight, strideWidth].

    • pad: "same" | "valid"

      The type of padding algorithm used in the non-transpose version of the op.

    Returns T

    Doc

Settings

Member Visibility

Theme

Generated using TypeDoc