Help protect the Great Barrier Reef with TensorFlow on Kaggle

tf.compat.v1.batch_to_space_nd

BatchToSpace for N-D tensors of type T.

This operation reshapes the "batch" dimension 0 into M + 1 dimensions of shape block_shape + [batch], interleaves these blocks back into the grid defined by the spatial dimensions [1, ..., M], to obtain a result with the same rank as the input. The spatial dimensions of this intermediate result are then optionally cropped according to crops to produce the output. This is the reverse of SpaceToBatch. 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.
crops A Tensor. Must be one of the following types: int32, int64. 2-D with shape [M, 2], all values must be >= 0. crops[i] = [crop_start, crop_end] specifies the amount to crop from input dimension i + 1, which corresponds to spatial dimension i. It is required that crop_start[i] + crop_end[i] <= block_shape[i] * input_shape[i + 1].

This operation is equivalent to the following steps:

1. Reshape input to reshaped of shape: [block_shape, ..., block_shape[M-1], batch / prod(block_shape), input_shape, ..., input_shape[N-1]]

2. Permute dimensions of reshaped to produce permuted of shape [batch / prod(block_shape),

input_shape, block_shape, ..., input_shape[M], block_shape[M-1],

input_shape[M+1], ..., input_shape[N-1]]

1. Reshape permuted to produce reshaped_permuted of shape [batch / prod(block_shape),

input_shape * block_shape, ..., input_shape[M] * block_shape[M-1],

input_shape[M+1], ..., input_shape[N-1]]

1. Crop the start and end of dimensions [1, ..., M] of reshaped_permuted according to crops to produce the output of shape: [batch / prod(block_shape),

input_shape * block_shape - crops[0,0] - crops[0,1], ..., input_shape[M] * block_shape[M-1] - crops[M-1,0] - crops[M-1,1],

input_shape[M+1], ..., input_shape[N-1]]

Some examples:

(1) For the following input of shape [4, 1, 1, 1], block_shape = [2, 2], and crops = [[0, 0], [0, 0]]:

[[[]], [[]], [[]], [[]]]

The output tensor has shape [1, 2, 2, 1] and value:

x = [[[, ], [, ]]]

(2) For the following input of shape [4, 1, 1, 3], block_shape = [2, 2], and crops = [[0, 0], [0, 0]]:

[[[[1, 2, 3]]], [[[4, 5, 6]]], [[[7, 8, 9]]], [[[10, 11, 12]]]]

The output tensor has shape [1, 2, 2, 3] and value:

x = [[[[1, 2, 3], [4, 5, 6]],
[[7, 8, 9], [10, 11, 12]]]]

(3) For the following input of shape [4, 2, 2, 1], block_shape = [2, 2], and crops = [[0, 0], [0, 0]]:

x = [[[, ], [, ]],
[[, ], [, ]],
[[, ], [, ]],
[[, ], [, ]]]

The output tensor has shape [1, 4, 4, 1] and value:

x = [[[,   ,  ,  ],
[,   ,  ,  ],
[,  , ,  ],
[, , ,  ]]]

(4) For the following input of shape [8, 1, 3, 1], block_shape = [2, 2], and crops = [[0, 0], [2, 0]]:

x = [[[, , ]], [[, , ]],
[[, , ]], [[, , ]],
[[, , ]], [[, , ]],
[[, , ]], [[, , ]]]

The output tensor has shape [2, 2, 4, 1] and value:

x = [[[,   ,  ,  ],
[,   ,  ,  ]],
[[,  , ,  ],
[, , ,  ]]]

name A name for the operation (optional).

A Tensor. Has the same type as input.

[{ "type": "thumb-down", "id": "missingTheInformationINeed", "label":"Missing the information I need" },{ "type": "thumb-down", "id": "tooComplicatedTooManySteps", "label":"Too complicated / too many steps" },{ "type": "thumb-down", "id": "outOfDate", "label":"Out of date" },{ "type": "thumb-down", "id": "samplesCodeIssue", "label":"Samples / code issue" },{ "type": "thumb-down", "id": "otherDown", "label":"Other" }]
[{ "type": "thumb-up", "id": "easyToUnderstand", "label":"Easy to understand" },{ "type": "thumb-up", "id": "solvedMyProblem", "label":"Solved my problem" },{ "type": "thumb-up", "id": "otherUp", "label":"Other" }]