tfm.vision.preprocess_ops.compute_padded_size

Compute the padded size given the desired size and the stride.

tfm.vision.preprocess_ops.compute_padded_size(
    desired_size, stride
)

The padded size will be the smallest rectangle, such that each dimension is the smallest multiple of the stride which is larger than the desired dimension. For example, if desired_size = (100, 200) and stride = 32, the output padded_size = (128, 224).

Args
`desired_size`	a `Tensor` or `int` list/tuple of two elements representing [height, width] of the target output image size.
`stride`	an integer, the stride of the backbone network.

Returns
`padded_size`	a `Tensor` or `int` list/tuple of two elements representing [height, width] of the padded output image size.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.

Last updated 2024-02-02 UTC.

tfm.vision.preprocess_ops.compute_padded_size

Args

Returns