Warning: This project is deprecated. TensorFlow Addons has stopped development, The project will only be providing minimal maintenance releases until May 2024. See the full announcement here or on github.

tfa.image.cutout

View source on GitHub

Apply cutout to images.

tfa.image.cutout(
 images: tfa.types.TensorLike ,
 mask_size: tfa.types.TensorLike ,
 offset: tfa.types.TensorLike = (0, 0),
 constant_values: tfa.types.Number = 0
) -> tf.Tensor

This operation applies a (mask_height x mask_width) mask of zeros to a location within images specified by the offset. The pixel values filled in will be of the value constant_values. The location where the mask will be applied is randomly chosen uniformly over the whole images.

Args

images A tensor of shape (batch_size, height, width, channels) (NHWC).
mask_size Specifies how big the zero mask that will be generated is that is applied to the images. The mask will be of size (mask_height x mask_width). Note: mask_size should be divisible by 2.
offset A tuple of (height, width) or (batch_size, 2)
constant_values What pixel value to fill in the images in the area that has the cutout mask applied to it.

Returns

A Tensor of the same shape and dtype as images.

Raises

InvalidArgumentError if mask_size can't be divisible by 2.

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.

Last updated 2023年05月25日 UTC.