上一页 1 2 3 4 5 6 7 8 9 10 ··· 27 下一页
摘要: 1、23arxiv_LLDiffusion: Learning Degradation Representations in Diffusion Models for Low-Light Image Enhancement中提到 LOL-v2文献来源:Sparse gradient regulari 阅读全文
posted @ 2023-08-08 14:53 helloWorldhelloWorld 阅读(833) 评论(0) 推荐(0)
摘要: 1、将visio图保存为pdf,打开pdf 2、采用shift+win+s进行屏幕 ,选择区域截图 3、将截图放入pycharm中,利用代码转化为灰度图 from PIL import Image rgb_image = Image.open('img/1111.png') gray_image = 阅读全文
posted @ 2023-08-07 11:01 helloWorldhelloWorld 阅读(581) 评论(0) 推荐(0)
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
posted @ 2023-07-29 15:00 helloWorldhelloWorld 阅读(26) 评论(0) 推荐(0)
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
posted @ 2023-07-29 14:49 helloWorldhelloWorld 阅读(17) 评论(0) 推荐(0)
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
posted @ 2023-07-24 16:10 helloWorldhelloWorld 阅读(73) 评论(0) 推荐(0)
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
posted @ 2023-07-24 09:18 helloWorldhelloWorld 阅读(67) 评论(0) 推荐(0)
摘要: 阅读全文
posted @ 2023-07-17 16:00 helloWorldhelloWorld 阅读(23) 评论(0) 推荐(0)
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
posted @ 2023-07-17 15:59 helloWorldhelloWorld 阅读(91) 评论(0) 推荐(0)
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
posted @ 2023-07-02 19:48 helloWorldhelloWorld 阅读(397) 评论(0) 推荐(0)
上一页 1 2 3 4 5 6 7 8 9 10 ··· 27 下一页