DeniuHe的博客

"""一个简单的调用GPU的卷积神经网络示例！"""import torchimport torchvisionfrom torchvision import datasetsfrom torchvision import transformsfrom torch.utils.data import DataLoaderbatch_size = 64device = torch.device("cuda:0")class CNN(torch.nn.Module): def.

import torchdevice = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")print(device)

import osimport torchimport numpy as npfrom copy import deepcopyfrom collections import OrderedDictfrom PIL import Imagefrom sklearn.model_selection import StratifiedKFoldclass FNN_2DLDA(object): def __init__(self, X_train, y_train, labe...

import torchimport numpy as np# ======初始化一个三维矩阵=====A = torch.ones((6,3,3))# ======替换三维矩阵里面的值======A[0] = torch.ones((3,3)) *2A[1] = torch.ones((3,3)) *5A[2] = torch.ones((3,3)) *5A[3] = torch.ones((3,3)) *5A[4] = torch.ones((3,3)) *5A[5] ...

import torchimport torch.nn.functional as Ffrom torch import nnfrom torch.autograd import Variableimport pandas as pdimport numpy as npfrom sklearn.model_selection import train_test_splitfrom sklearn.metrics import accuracy_scorefrom sklearn....

该论文是对2001年Frank的一篇二分类分解的序分类模型的卷积神经网络的拓展。Frank E, Hall M. A simple approach to ordinal classification[C]//European Conference on Machine Learning. Springer, Berlin, Heidelberg, 2001: 145-156.该二分类分解方法的缺点就是预测类别之间的概率不一致性，有可能出现负概率的问题。但总之不影响模型的预测。对...

import torchimport numpy as npimport pandas as pddef convertLabel(datasetLabel): """ Labels (product ratings) from the dataset are provided to you as floats, taking the values 1.0, 2.0, 3.0, 4.0, or 5.0. You may wish to train with thes.

自定义HingeLoss class MyHingeLoss(torch.nn.Module): # 不要忘记继承Module def __init__(self): super(MyHingeLoss, self).__init__() def forward(self, output, target): """output和target都是1-D张量,换句话说,每个样例的返回是一个标量. """ hing..

import torchimport torch.nn.functional as Ffrom torch.autograd import Variableimport matplotlib.pyplot as pltimport pandas as pdimport numpy as np# data = np.array(pd.read_csv(r"D:\RegressionData\sin.csv"))# x = data[:,0]# y = data[:,-1]# print(.

import torchimport torch.nn.functional as Ffrom torch.autograd import Variableimport matplotlib.pyplot as pltimport pandas as pdimport numpy as np# data = np.array(pd.read_csv(r"D:\RegressionData\sin.csv"))# x = data[:,0]# y = data[:,-1]# print(.