pytorch怎么设置学习率自动下降并画出折线图，代码演示

您好，关于您的问题，可以使用PyTorch中的lr_scheduler模块实现学习率自动下降，并使用matplotlib模块绘制折线图。

以下是一个简单的示例代码，供参考：

import matplotlib.pyplot as plt
import torch
import torch.optim as optim
import torch.nn as nn
import torch.nn.functional as F
from torch.utils.data import DataLoader
from torch.optim.lr_scheduler import StepLR

# 定义模型
class MyModel(nn.Module):
    def __init__(self):
        super(MyModel, self).__init__()
        self.fc1 = nn.Linear(784, 256)
        self.fc2 = nn.Linear(256, 10)

    def forward(self, x):
        x = x.view(-1, 784)
        x = F.relu(self.fc1(x))
        x = self.fc2(x)
        return x

# 加载数据集
train_data = ...
test_data = ...
train_loader = DataLoader(train_data, batch_size=64, shuffle=True)
test_loader = DataLoader(test_data, batch_size=64)

# 定义优化器和学习率下降策略
model = MyModel()
optimizer = optim.SGD(model.parameters(), lr=0.1)
scheduler = StepLR(optimizer, step_size=1, gamma=0.1)

# 训练和测试
train_loss_list = []
test_loss_list = []

for epoch in range(5):
    # 训练
    train_loss = 0.0
    for batch_idx, (data, target) in enumerate(train_loader):
        optimizer.zero_grad()
        output = model(data)
        loss = F.cross_entropy(output, target)
        loss.backward()
        optimizer.step()
        train_loss += loss.item()
    scheduler.step()

    # 测试
    test_loss = 0.0
    for data, target in test_loader:
        output = model(data)
        loss = F.cross_entropy(output, target)
        test_loss += loss.item()

    train_loss_list.append(train_loss / len(train_loader))
    test_loss_list.append(test_loss / len(test_loader))

# 绘制折线图
plt.plot(train_loss_list, label='train loss')
plt.plot(test_loss_list, label='test loss')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.legend()
plt.show()

在代码中，StepLR类表示每个epoch后将学习率乘以gamma。在这个例子中，学习率从0.1开始，每个epoch后除以10。train_loss_list和test_loss_list分别记录训练和测试集合的平均损失，然后使用matplotlib模块画出折线图。