Day 37 MLP神经网络的训练

@浙大疏锦行

1.cuda 的检查

import torch torch.cuda if torch.cuda.is_available(): print("CUDA可用!") device_count = torch.cuda.device_count() print(f"可用的CUDA设备数量:{device_count}") current_device = torch.cuda.current_device() print(f"当前使用的CUDA设备索引:{current_device}") device_name = torch.cuda.get_device_name(current_device) print(f"当前CUDA设备的名称:{device_name}") cuda_version = torch.version.cuda print(f"CUDA版本:{cuda_version}") else: print("CUDA不可用。")

2.简单神经网络的流程

a.数据预处理

from sklearn.datasets import load_iris from sklearn.model_selection import train_test_split import numpy as np iris = load_iris() X = iris.data y = iris.target X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=42) print(X_train.shape) print(y_train.shape) print(X_test.shape) print(y_test.shape) from sklearn.preprocessiong import MinMaxScaler scaler = MinMaxScaler() X_train = scaler.fit_transform(X_train) X_test = scaler.transform(X_test) X_train = torch.FloatTensor(X_train) y_train = torch.LongTensor(y_train) X_test = torch.FloatTensor(X_test) y_test = torch.LongTensor(y_test)

b.模型的定义

i.继承nn.Module类

ii.定义每一个层

iii.定义前向传播流程

import torch import torch.nn as nn import torch.optim as optim class MLP(nn.Module): def__init__(self): super(MLP,self).__init__() self.fc1 = nn.Linear(4,10) self.relu = nn.ReLU() self.fc2 = nn.Linear(10,3) def forward(self,x): out = self.fc1(x) out = self.relu(out) out = self.fc2(out) return out model = MLP()

c.定义损失函数和优化器

criterion = nn.CrossEntropyLoss() optimizer = optim.SGD(model.parameters(), 1r=0.01)

d.定义训练流程

num_epochs = 20000 losses = [] for epoch in range(num_epochs): outputs = model.forward(X_train) loss = criterison(outputs,y_train) optimizer.zero_grad() loss.backward() optimizer.step() losses.append(loss.item()) if(epoch + 1) % 100 == 0: print(f'Epoch [{epoch+1}/{num_epochs}], Loss: {loss.item():.4f})

e.可视化loss过程

import matplotlib.pyplot as plt plt.plot(range(num_epochs),losses) plt.xlabel('Epoch') plt.ylabel('Loss') plt.title('Training Loss over Epochs') plt.show()