SpaceToBatch for N-D tensors of type T.

This operation divides "spatial" dimensions [1, ..., M] of the input into a grid of blocks of shape block_shape, 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.

input A Tensor. N-D with shape input_shape = [batch] + spatial_shape + remaining_shape, where spatial_shape has M dimensions.
block_shape A Tensor. Must be one of the following types: int32, int64. 1-D with shape [M], all values must be >= 1.
paddings A Tensor. Must be one of the following types: int32, int64. 2-D with shape [M, 2], all values must be >= 0. paddings[i] = [pad_start, pad_end] specifies the padding for input dimension i + 1, which corresponds to spatial dimension i. It is required that block_shape[i] divides input_shape[i + 1] + pad_start + pad_end.

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 padded_shape.

  2. Reshape padded to reshaped_padded of shape:

[batch] + [padded_shape[1] / block_shape[0], block_shape[0], ..., padded_shape[M] / block_shape[M-1], block_shape[M-1]] + remaining_shape

  1. Permute dimensions of reshaped_padded to produce permuted_reshaped_padded of shape:

block_shape + [batch] + [padded_shape[1] / block_shape[0], ..., padded_shape[M] / block_shape[M-1]] + remaining_shape

  1. Reshape permuted_reshaped_padded to flatten block_shape into the batch dimension, producing an output tensor of shape:

[batch * prod(block_shape)] + [padded_shape[1] / block_shape[0], ..., padded_shape[M] / block_shape[M-1]] + remaining_shape

Some examples:

(1) For the following input of shape