Skorch:如何绘制训练和验证准确性

import matplotlib.pyplot as plt
from skorch import NeuralNetClassifier
from skorch.callbacks import EpochScoring
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from torch import nn

# 加载数据集
X, y = load_iris(return_X_y=True)
X_train, X_valid, y_train, y_valid = train_test_split(X, y, test_size=0.2, random_state=42)

# 数据标准化
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_valid = scaler.transform(X_valid)

# 定义神经网络模型
class IrisClassifier(nn.Module):
    def __init__(self):
        super(IrisClassifier, self).__init__()
        self.fc1 = nn.Linear(4, 64)
        self.fc2 = nn.Linear(64, 3)

    def forward(self, x):
        x = nn.functional.relu(self.fc1(x))
        x = self.fc2(x)
        return x

# 创建神经网络分类器
net = NeuralNetClassifier(
    IrisClassifier,
    max_epochs=20,
    lr=0.01,
    device='cpu',
    callbacks=[
        ('valid_acc', EpochScoring(scoring='accuracy', lower_is_better=False, name='valid_acc')),
    ]
)

# 训练模型
net.fit(X_train, y_train)

# 获取训练和验证准确性
train_losses = net.history[:, 'train_loss']
valid_losses = net.history[:, 'valid_loss']
train_accs = net.history[:, 'train_acc']
valid_accs = net.history[:, 'valid_acc']

# 绘制图表
plt.figure(figsize=(12, 6))

plt.subplot(1, 2, 1)
plt.plot(train_losses, label='Training Loss')
plt.plot(valid_losses, label='Validation Loss')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.legend()

plt.subplot(1, 2, 2)
plt.plot(train_accs, label='Training Accuracy')
plt.plot(valid_accs, label='Validation Accuracy')
plt.xlabel('Epoch')
plt.ylabel('Accuracy')
plt.legend()

plt.show()