pado.math.calculate_psnr¶
- calculate_psnr(img1, img2, data_range=1.0)[source]¶
Calculate Peak Signal-to-Noise Ratio between multi-channel tensors.
- Parameters:
img1 (torch.Tensor) – First tensor [B, Channel, R, C]
img2 (torch.Tensor) – Second tensor [B, Channel, R, C]
data_range (float, optional) – The data range of the input image (e.g., 1.0 for normalized images, 255 for uint8 images). If None, uses the detached maximum value from both images, preserving the original normalization rule.
- Returns:
Scalar PSNR in dB on the input device, +inf if images are identical
- Return type:
Examples
>>> intensity1 = light1.get_intensity() # [B, Channel, R, C] >>> intensity2 = light2.get_intensity() # [B, Channel, R, C] >>> psnr = calculate_psnr(intensity1, intensity2)