pyiqa.archs.psnr_arch¶
Peak signal-to-noise ratio (PSNR) Metric
Created by: https://github.com/photosynthesis-team/piq
Modified by: Jiadi Mo (https://github.com/JiadiMo)
- Refer to:
Wikipedia from https://en.wikipedia.org/wiki/Peak_signal-to-noise_ratio QIQA from https://github.com/francois-rozet/piqa/blob/master/piqa/psnr.py
Module Contents¶
- pyiqa.archs.psnr_arch.psnr(x, y, test_y_channel=False, data_range=1.0, eps=1e-08, color_space='yiq')[source]¶
Compute Peak Signal-to-Noise Ratio for a batch of images. Supports both greyscale and color images with RGB channel order. :param - x: An input tensor. Shape \((N, C, H, W)\). :param - y: A target tensor. Shape \((N, C, H, W)\). :param - test_y_channel: Convert RGB image to YCbCr format and computes PSNR :type - test_y_channel: Boolean :param only on luminance channel if True. Compute on all 3 channels otherwise.: :param - data_range: Maximum value range of images (default 1.0).
- Returns:
PSNR Index of similarity between two images.
- class pyiqa.archs.psnr_arch.PSNR(test_y_channel=False, crop_border=0, **kwargs)[source]¶
Bases:
torch.nn.Module- Parameters:
X (-) – distorted image and reference image tensor with shape (B, 3, H, W)
Y (torch.Tensor) – distorted image and reference image tensor with shape (B, 3, H, W)
test_y_channel (-) – Convert RGB image to YCbCr format and computes PSNR only on luminance channel if True. Compute on all 3 channels otherwise.
kwargs (-) – other parameters, including - data_range: maximum numeric value - eps: small constant for numeric stability
- Returns:
(B, 1)
- Return type:
score (torch.Tensor)