Function spaceToBatchND

  • spaceToBatchND<T>(x, blockShape, paddings): T

  • This operation divides "spatial" dimensions [1, ..., M] of the input into a grid of blocks of shape blockShape, and interleaves these blocks with the "batch" dimension (0) such that in the output, the spatial dimensions [1, ..., M] correspond to the position within the grid, and the batch dimension combines both the position within a spatial block and the original batch position. Prior to division into blocks, the spatial dimensions of the input are optionally zero padded according to paddings. See below for a precise description.

    const x = tf.tensor4d([1, 2, 3, 4], [1, 2, 2, 1]);
    const blockShape = [2, 2];
    const paddings = [[0, 0], [0, 0]];

    x.spaceToBatchND(blockShape, paddings).print();

    Type Parameters

    Parameters

    • x: TensorLike | T

      A tf.Tensor. N-D with x.shape = [batch] + spatialShape + remainingShape, where spatialShape has M dimensions.

    • blockShape: number[]

      A 1-D array. Must have shape [M], all values must be >= 1.

    • paddings: number[][]

      A 2-D array. Must have shape [M, 2], all values must be >= 0. paddings[i] = [padStart, padEnd] specifies the amount to zero-pad from input dimension i + 1, which corresponds to spatial dimension i. It is required that (inputShape[i + 1] + padStart + padEnd) % blockShape[i] === 0

      This operation is equivalent to the following steps:

      1. Zero-pad the start and end of dimensions [1, ..., M] of the input according to paddings to produce padded of shape paddedShape.

      2. Reshape padded to reshapedPadded of shape: [batch] + [paddedShape[1] / blockShape[0], blockShape[0], ..., paddedShape[M] / blockShape[M-1], blockShape[M-1]] + remainingShape

      3. Permute dimensions of reshapedPadded to produce permutedReshapedPadded of shape: blockShape + [batch] + [paddedShape[1] / blockShape[0], ..., paddedShape[M] / blockShape[M-1]] + remainingShape

      4. Reshape permutedReshapedPadded to flatten blockShape into the batch dimension, producing an output tensor of shape: [batch * prod(blockShape)] + [paddedShape[1] / blockShape[0], ..., paddedShape[M] / blockShape[M-1]] + remainingShape

    Returns T

    Doc

Settings

Member Visibility

Theme

Generated using TypeDoc