07 2023 档案
摘要：import torch from Utils.utils import * def getHighLowFre(image): f = torch.fft.fft2(image) # 计算频率 freqs = torch.fft.fftfreq(image.shape[-1]) # print(f
阅读全文
摘要：import numpy import torch import torch.nn.functional as F from torchvision import models class Vgg19(torch.nn.Module): def __init__(self, requires_gra
阅读全文
摘要：f = torch.fft.fft2(image) # 计算频率 freqs = torch.fft.fftfreq(image.shape[-1]) print(freqs) # 设定阈值，用于分离高频和低频信息 threshold = 0.1 # 创建掩码，用于分离高频和低频信息 mask =
阅读全文
摘要：import torch from torch import nn import numpy as np import matplotlib.pyplot as plt from PIL import Image from torchvision import transforms from mat
阅读全文
摘要：1. 声明教师，学生网络 backbone_model = Net(gps=opt.gps, blocks=opt.blocks) backbone_model = backbone_model.to(device) ema_model = Net(gps=opt.gps, blocks=opt.b
阅读全文
摘要：1.
阅读全文
摘要：1、导入pyiqa包(要求torch>1.10) 2、外网下载niqe_modelparameters.mat、brisque_svm_weights.pth 3、把外网下载的两个文件放在制定目录（.cache/......），ctrl+H打开ubuntu隐藏文件夹
阅读全文
