tf.image.psnr | TensorFlow v2.16.1 (original) (raw)

tf.image.psnr

Stay organized with collections Save and categorize content based on your preferences.

Returns the Peak Signal-to-Noise Ratio between a and b.

View aliases

Compat aliases for migration

tf.compat.v1.image.psnr

tf.image.psnr(
    a, b, max_val, name=None
)

Used in the notebooks

Used in the tutorials
Image Super Resolution using ESRGAN

This is intended to be used on signals (or images). Produces a PSNR value for each image in batch.

The last three dimensions of input are expected to be [height, width, depth].

Example:

    # Read images from file.
    im1 = tf.decode_png('path/to/im1.png')
    im2 = tf.decode_png('path/to/im2.png')
    # Compute PSNR over tf.uint8 Tensors.
    psnr1 = tf.image.psnr(im1, im2, max_val=255)

    # Compute PSNR over tf.float32 Tensors.
    im1 = tf.image.convert_image_dtype(im1, tf.float32)
    im2 = tf.image.convert_image_dtype(im2, tf.float32)
    psnr2 = tf.image.psnr(im1, im2, max_val=1.0)
    # psnr1 and psnr2 both have type tf.float32 and are almost equal.

Args
a	First set of images.
b	Second set of images.
max_val	The dynamic range of the images (i.e., the difference between the maximum the and minimum allowed values).
name	Namespace to embed the computation in.

Returns
The scalar PSNR between a and b. The returned tensor has type tf.float32and shape [batch_size, 1].

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 2024-04-26 UTC.