TensorFlow is back at Google I/O on May 14! Register now

tfm.vision.box_ops.jitter_boxes

Jitters the box coordinates by some noise distribution.

tfm.vision.box_ops.jitter_boxes(
    boxes, noise_scale=0.025
)

Args
`boxes`	a tensor whose last dimension is 4 representing the coordinates of boxes in ymin, xmin, ymax, xmax order.
`noise_scale`	a python float which specifies the magnitude of noise. The rule of thumb is to set this between (0, 0.1]. The default value is found to mimic the noisy detections best empirically.

Returns
`jittered_boxes`	a tensor whose shape is the same as `boxes` representing the jittered boxes.

Raises
`ValueError`	If the last dimension of boxes is not 4.

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.

Args