https://github.com/richzhang/PerceptualSimilarity
源代码链接如上
我的方法是首先安装lpips包
pip install lpips
安装成功之后,新建.py文件命名为lpips1文件
# coding=gbk
import cv2
import lpips
import torchvision.transforms as transforms
import torch
# 载入指标模型
loss_fn_alex = lpips.LPIPS(net='alex') # best forward scores
loss_fn_vgg = lpips.LPIPS(net='vgg') # closer to "traditional" perceptual loss, when used for optimization
# 读取图片
test1 = cv2.imread('1.png')
test2 = cv2.imread('2.png')
# 分割目标图片
test1_org = test1[:, :512, :] / 255 # 原始图片
test1_res = test1[:, 512:1024, :] / 255 # 模型输出结果
test1_label = test1[:, 1024:1536, :] / 255 # label图片
test2_org = test2[:, :512, :] / 255
test2_res = test2[:, 512:1024, :] / 255
test2_label = test2[:, 1024:1536, :] / 255
# 转为tensor
transf = transforms.ToTensor()
test1_org = transf(test1_org)
test1_res = transf(test1_res)
test1_label = transf(test1_label)
test2_org = transf(test2_org)
test2_res = transf(test2_res)
test2_label = transf(test2_label)
# 转换数据类型
test1_orgg = test1_org.to(torch.float32)
test1_ress = test1_res.to(torch.float32)
test1_labell = test1_label.to(torch.float32)
test2_orgg = test2_org.to(torch.float32)
test2_ress = test2_res.to(torch.float32)
test2_labell = test2_label.to(torch.float32)
# 测试
d11 = loss_fn_alex(test1_ress, test1_labell)
d12 = loss_fn_alex(test1_ress, test2_labell)
print('d11:', d11)
print('d12:', d12)
d22 = loss_fn_alex(test2_ress, test2_labell)
d21 = loss_fn_alex(test2_ress, test1_labell)
print('d22:', d22)
print('d121:', d21)