W3cubDocs

/TensorFlow 2.3

tf.required_space_to_batch_paddings

View source on GitHub

Calculate padding required to make block_shape divide input_shape.

This function can be used to calculate a suitable paddings argument for use with space_to_batch_nd and batch_to_space_nd.

Args
input_shape int32 Tensor of shape [N].
block_shape int32 Tensor of shape [N].
base_paddings Optional int32 Tensor of shape [N, 2]. Specifies the minimum amount of padding to use. All elements must be >= 0. If not specified, defaults to 0.
name string. Optional name prefix.
Returns
(paddings, crops), where:

paddings and crops are int32 Tensors of rank 2 and shape [N, 2]

satisfying paddings[i, 0] = base_paddings[i, 0]. 0 <= paddings[i, 1] - base_paddings[i, 1] < block_shapei % block_shape[i] == 0

crops[i, 0] = 0 crops[i, 1] = paddings[i, 1] - base_paddings[i, 1]

Raises: ValueError if called with incompatible shapes.

© 2020 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/versions/r2.3/api_docs/python/tf/required_space_to_batch_paddings