03 2021 档案
摘要:import time from options.train_options import TrainOptions from data import create_dataset from models import create_model from util.visualizer import
阅读全文
摘要:import os import cv2 import numpy as np Adir = './trainA/' Bdir = './trainB/' ABdir = './datasets/train/' num=0 for fi in os.listdir(Adir): im_A = cv2
阅读全文
摘要:论文:《A fast and robust convolutional neural network-based defect detection model in product quality control》 论文地址:http://personalpages.to.infn.it/~muss
阅读全文
摘要:论文《Deep learning-based crack damage detection using convolutional neural networks》 问题:混凝土裂缝检测 做法:大概意思就是说采用了下面的这样一个网络,对切块后的图像进行了分类。图像切块的策略见最后的图所示: 实验结果
阅读全文
摘要:论文题目《Automatic Defect Detection of Fasteners on the Catenary Support Device Using Deep Convolutional Neural Network》 下载地址:https://ieeexplore.ieee.org/
阅读全文
摘要:将1*(1024*128)降维为(1*1024),将(1*1024)降维为(1*512); 将(1*512)升维为(1*1024),将(1*1024)升维为1*(1024*128); self.fc = nn.Sequential( nn.Linear(1024*128, 1024), nn.Lin
阅读全文
摘要:将x4平铺成一维向量,得到x5; 将x5压缩成和x4shape一样,得到x6 x5 = x4.view(x4.size(0), -1) x6 = x5.detach().view_as(x4)
阅读全文
摘要:特征 局部or全局 尺度不变性 亮度不变性 旋转不变性 仿射不变性 CNN SIFT 局部 1、性质解释 尺度不变性: 建议看看这个人的博客:https://zhuanlan.zhihu.com/p/67080514 比如有两个数据集: 数据集A:图像被resize大小512*512,图像中目标的大
阅读全文
摘要:模糊图像可以变高清,高清图像是否可以变模糊?模拟正常的模糊。 基于低质量图像的分类、检测、检索、识别研究
阅读全文
摘要:数据集: UC Merced Land-Use Data Set数据集下载地址:http://weegee.vision.ucmerced.edu/datasets/landuse.html RSSCN7 Data Set数据集下载地址:https://sites.google.com/site/q
阅读全文
摘要:f_label_img = cv2.imread('1.jpg') f_label_img = cv2.cvtColor(f_label_img, cv2.COLOR_BGR2GRAY) contours, hierarchy = cv2.findContours(f_label_img, cv2.
阅读全文
摘要:def load_images(IMG_SIZE = 256): avatars = [] filenames = [] images_list = sorted(glob.glob(f'{opt.avatars}/*')) for i, f in enumerate(images_list): i
阅读全文
摘要:f='1.jpg' f.endswith('.jpg') or f.endswith('.jpeg') or f.endswith('.png')
阅读全文
摘要:w_size = 512 h_size = 256 sub_input_label = torch.zeros([input_label.shape[0],input_label.shape[1],h_size,w_size], dtype=torch.float32,device=input_la
阅读全文
摘要:import torch # 正向传播时:开启自动求导的异常侦测 torch.autograd.set_detect_anomaly(True) # 反向传播时:在求导时开启侦测 with torch.autograd.detect_anomaly(): loss.backward()
阅读全文
摘要:错误: RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [3, 32, 1, 1
阅读全文
摘要:Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection~WACV2021 单位: 一、下载 paper: https://openaccess.thecvf.com/content/WACV2021/pap
阅读全文