Level protection and deep learning

本文主要是介绍Level protection and deep learning，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！

1.模拟生成的数据

import randomdef generate_data(level, num_samples):if level not in [2, 3, 4]:return Nonedata_list = []for _ in range(num_samples):# 构建指定等级的数据data = str(level)for _ in range(321):data += str(random.randint(0, 9))data_list.append(data)return data_listdef save_data_to_txt(data, filename):with open(filename, 'a') as f:for item in data:f.write("%s\n" % item)print(f"Data saved to {filename}")# 创建一个文件用于存储所有数据
output_filename = "combined_data.txt"# 生成等级为2的一万条数据，并保存到文件
level_2_data = generate_data(2, 100)
save_data_to_txt(level_2_data, output_filename)# 生成等级为3的一万条数据，并保存到文件
level_3_data = generate_data(3, 100)
save_data_to_txt(level_3_data, output_filename)# 生成等级为4的一万条数据，并保存到文件
level_4_data = generate_data(4, 100)
save_data_to_txt(level_4_data, output_filename)

将生成数据和对应的指标的表结合修改

import os
import pandas as pddef multiply_lists(list1, list2):if len(list1) != len(list2):return Noneresult = []result.append(str(list2[0]))for i in range(1, len(list1)):result.append(str(list1[i] * list2[i]))return "".join(result) def save_data_to_txt(data, filename):try:with open(filename, 'a') as f:f.write(data + "\n")print(f"数据已保存到 {filename}")except Exception as e:print(f"保存数据时发生错误：{e}")# 读取Excel文件
df = pd.read_excel('F:\python level Guarantee 2.0\LG.xlsx', header=None)
# 将每一行转换为列表
rows_as_lists = df.values.tolist()
print(rows_as_lists)
level2 = rows_as_lists.pop()
print(rows_as_lists)
level3 = rows_as_lists.pop()
print(rows_as_lists)
level4 = rows_as_lists.pop()output_filename = "F:/python level Guarantee 2.0/test.txt"with open('F:/python level Guarantee 2.0/combined_data.txt', 'r', encoding='utf-8') as f:data_str_list = [line.strip() for line in f]for i in data_str_list:data = list(i)if int(data[0]) == int(level2[0]):result = multiply_lists(data, level2)save_data_to_txt(result, output_filename)if int(data[0]) == int(level3[0]):result = multiply_lists(data, level3)save_data_to_txt(result, output_filename)if int(data[0]) == int(level4[0]):result = multiply_lists(data, level4)save_data_to_txt(result, output_filename)

2.trian

import torch
from torch import nn
from torch.utils.data import Dataset, DataLoader
import numpy as np
from torch.utils.tensorboard import SummaryWriter
DEVICE = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')class Model(nn.Module):def __init__(self):super(Model, self).__init__()self.net = nn.Sequential(nn.Linear(321, 159),nn.ReLU(),nn.Linear(159,81),nn.ReLU(),nn.Linear(81, 3),)def forward(self, input):return self.net(input)class DataRemake(Dataset):def __init__(self, path):self.data, self.label = self.transform(path)self.len = len(self.label)def __getitem__(self, index):label = self.label[index]data = self.data[index]return label, datadef __len__(self):return self.lendef transform(self, path):data_tensor_list = []label_list = []with open(path, mode='r', encoding='utf-8') as fp:data_str_list = [line.strip() for line in fp]for i in data_str_list:data = list(i)label = int(data[0])# 转换标签为 one-hot 编码if label == 2:label = [1, 0, 0]elif label == 3:label = [0, 1, 0]elif label == 4:label = [0, 0, 1]else:raise ValueError(f"未知的标签值：{label}")data = data[1:]# 检查数据的长度并进行处理if len(data) != 321:# 如果数据长度不是321，进行填充或截断操作if len(data) < 322:# 填充数据，这里假设用0填充data.extend([0] * (321 - len(data)))else:# 截断数据data = data[:321]data = np.array(list(map(float, data))).astype(np.float32)label = np.array(label).astype(np.float32)data = torch.from_numpy(data)label = torch.from_numpy(label)data_tensor_list.append(data)label_list.append(label)return data_tensor_list, label_list# 路径可能需要根据实际情况修改
train_data = DataRemake('result1.txt')
train_dataloader = DataLoader(dataset=train_data, batch_size=10)net = Model().to(DEVICE)
optimizer = torch.optim.SGD(net.parameters(), lr=0.005)
loss_func = nn.MSELoss().to(DEVICE)list_pre = []writer = SummaryWriter('logs')# 在每个epoch结束时，记录损失值
for epoch in range(1000):for labels, datas in train_dataloader:labels = labels.to(DEVICE)datas = datas.to(DEVICE)output = net(datas)loss = loss_func(output, labels)optimizer.zero_grad()loss.backward()optimizer.step()if epoch % 100 == 0:list_pre.append(output)print('epoch:{} \n loss:{}'.format(epoch, round(loss.item(), 10)))# 记录损失值到TensorBoardwriter.add_scalar('Loss/train', loss.item(), epoch)# 记得在训练结束后关闭SummaryWriter
writer.close()# 保存模型
torch.save(net.state_dict(), 'model.pth')

3.test

import torch
from torch import nn
from torch.utils.data import DataLoader
from sklearn.metrics import accuracy_score
from torch.utils.data import Dataset, DataLoader
import numpy as npDEVICE = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')class Model(nn.Module):def __init__(self):super(Model, self).__init__()self.net = nn.Sequential(nn.Linear(321, 159),nn.ReLU(),nn.Linear(159,81),nn.ReLU(),nn.Linear(81, 3),)def forward(self, input):return self.net(input)class DataRemake(Dataset):def __init__(self, path):self.data, self.label = self.transform(path)self.len = len(self.label)def __getitem__(self, index):label = self.label[index]data = self.data[index]return label, datadef __len__(self):return self.lendef transform(self, path):data_tensor_list = []label_list = []with open(path, mode='r', encoding='utf-8') as fp:data_str_list = [line.strip() for line in fp]for i in data_str_list:data = list(i)label = int(data[0])# 转换标签为 one-hot 编码if label == 2:label = [1, 0, 0]elif label == 3:label = [0, 1, 0]elif label == 4:label = [0, 0, 1]else:raise ValueError(f"未知的标签值：{label}")data = data[1:]# 检查数据的长度并进行处理if len(data) != 321:# 如果数据长度不是321，进行填充或截断操作if len(data) < 322:# 填充数据，这里假设用0填充data.extend([0] * (321 - len(data)))else:# 截断数据data = data[:321]data = np.array(list(map(float, data))).astype(np.float32)label = np.array(label).astype(np.float32)  # 转换标签数据类型为浮点型data = torch.from_numpy(data)label = torch.from_numpy(label)data_tensor_list.append(data)label_list.append(label)return data_tensor_list, label_list# 加载模型
model = Model().to(DEVICE)
model.load_state_dict(torch.load('model.pth'))
model.eval()  # 将模型设置为评估模式# 准备测试数据
test_data = DataRemake('test.txt')  # 假设测试数据的路径为'test_data.txt'
test_dataloader = DataLoader(dataset=test_data, batch_size=10)# 初始化用于存储预测结果和真实标签的列表
predicted_labels = []
true_labels = []# 迭代测试集，并进行预测
with torch.no_grad():for labels, datas in test_dataloader:labels = labels.to(DEVICE)datas = datas.to(DEVICE)output = model(datas)# 将输出转换为预测的标签_, predicted = torch.max(output, 1)# 将预测结果和真实标签添加到列表中predicted_labels.extend(predicted.cpu().numpy())true_labels.extend(labels.cpu().numpy())# 计算准确率
accuracy = accuracy_score(np.argmax(true_labels, axis=1), predicted_labels)  # 使用 np.argmax 获取真实标签的类别
print(f"模型在测试集上的准确率为: {accuracy}")
# import torch# # 加载模型
# model = Model().to(DEVICE)
# model.load_state_dict(torch.load('model.pth'))
# model.eval()  # 将模型设置为评估模式# # 准备输入数据
# input_data = torch.randn(10, 321).to(DEVICE)  # 示例数据，需要根据实际情况调整形状和数据类型# # 使用模型进行预测
# with torch.no_grad():
#     output = model(input_data)# # 获取预测结果
# _, predicted_labels = torch.max(output, 1)# print("预测结果:", predicted_labels)

这篇关于Level protection and deep learning的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！

---