python计算两个三维图的psnr

要计算两个三维图像的PSNR，可以使用以下代码：

import cv2
import numpy as np
import math

def psnr(target, ref):
    # 将图像格式转为float64
    target_data = np.array(target, dtype=np.float64)
    ref_data = np.array(ref, dtype=np.float64)
    
    # 直接相减，求差值
    diff = ref_data - target_data
    
    # 按第三个通道顺序把三维矩阵拉平
    diff = diff.flatten('C')
    
    # 计算MSE值
    rmse = math.sqrt(np.mean(diff ** 2.))
    
    # 精度
    eps = np.finfo(np.float64).eps
    if rmse == 0:
        rmse = eps
    
    return 20 * math.log10(255.0 / rmse)

# 读取两个三通道图像
IMG_1 = cv2.imread("image1.jpg")
IMG_2 = cv2.imread("image2.jpg")

# 计算PSNR值
psnr_value = psnr(IMG_1, IMG_2)
print("PSNR:", psnr_value)

请注意，这段代码假设输入的图像是三通道的。如果输入的图像是灰度图像，需要对代码进行相应的修改。此外，为了得到有意义的PSNR值，两个图像的大小应该相同。如果大小不同，可以使用`cv2.resize()`函数将它们调整为相同的大小。
#### 引用[.reference_title]
- *1* *2* [python/c++计算psnr](https://blog.csdn.net/cd_yourheart/article/details/121156270)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v91^insert_down28v1,239^v3^insert_chatgpt"}} ] [.reference_item]
- *3* [【Python】计算psnr和ssim值](https://blog.csdn.net/Resume_f/article/details/103339722)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v91^insert_down28v1,239^v3^insert_chatgpt"}} ] [.reference_item]
[ .reference_list ]