深度学习_18_模型的下载与读取

news2024/12/30 3:33:58

在深度学习的过程中，需要将训练好的模型运用到我们要使用的另一个程序中，这就需要模型的下载与转移操作

代码：

import math
import torch
from torch import nn
from d2l import torch as d2l
import matplotlib.pyplot as plt

# 生成随机的数据集
max_degree = 20  # 多项式的最大阶数
n_train, n_test = 100, 100  # 训练和测试数据集大小
true_w = torch.zeros(max_degree)
true_w[0:4] = torch.Tensor([5, 1.2, -3.4, 5.6])

# 生成特征
features = torch.randn((n_train + n_test, 1))
permutation_indices = torch.randperm(features.size(0))
# 使用随机排列的索引来打乱features张量（原地修改）
features = features[permutation_indices]
poly_features = torch.pow(features, torch.arange(max_degree).reshape(1, -1))
for i in range(max_degree):
    poly_features[:, i] /= math.gamma(i + 1)

# 生成标签
labels = torch.matmul(poly_features, true_w)
labels += torch.normal(0, 0.1, size=labels.shape)


# 以下是你原来的训练函数，没有修改
def evaluate_loss(net, data_iter, loss):
    metric = d2l.Accumulator(2)
    for X, y in data_iter:
        out = net(X)
        y = y.reshape(out.shape)
        l = loss(out, y)
        metric.add(l.sum(), l.numel())
    return metric[0] / metric[1]


def l2_penalty(w):
    w = w[0].weight
    return torch.sum(w.pow(2)) / 2


def train(train_features, test_features, train_labels, test_labels, lambd,
          num_epochs=100):
    loss = d2l.squared_loss
    input_shape = train_features.shape[-1]
    net = nn.Sequential(nn.Linear(input_shape, 1, bias=False))  # 模型
    batch_size = min(10, train_labels.shape[0])

    train_iter = d2l.load_array((train_features, train_labels.reshape(-1, 1)),
                                batch_size)
    test_iter = d2l.load_array((test_features, test_labels.reshape(-1, 1)),
                               batch_size, is_train=False)

    # 用于存储训练和测试损失的列表
    train_losses = []
    test_losses = []
    total_loss = 0
    total_samples = 0
    for epoch in range(num_epochs):
        for X, y in train_iter:
            out = net(X)
            y = y.reshape(-1, 1)  # 确保y是二维的
            l = loss(out, y) + lambd * l2_penalty(net)

            # 反向传播和优化器更新
            l.sum().backward()
            d2l.sgd(net.parameters(), lr=0.01, batch_size= batch_size)
            total_loss += l.sum().item()  # 统计所有元素损失
            total_samples += y.numel()  # 统计个数
        a = total_loss / total_samples  # 本次训练的平均损失
        train_losses.append(a)
        test_loss = evaluate_loss(net, test_iter, loss)
        test_losses.append(test_loss)
        total_loss = 0
        total_samples = 0
        print(f"Epoch {epoch + 1}/{num_epochs}:")
        print(f"训练损失： {a:.4f}   测试损失： {test_loss:.4f} ")
    print(net[0].weight)

    torch.save(net.state_dict(), "NetSave")  # 存模型
    net_try = nn.Sequential(nn.Linear(input_shape, 1, bias=False))
    print("net_try")
    print(net_try[0].weight)
    net_try.load_state_dict(torch.load("NetSave"))
    net_try.eval()  # 评估模式
    print("net_try_load")
    print(net_try[0].weight)
    # 绘制损失曲线
    plt.figure(figsize=(10, 6))
    plt.plot(train_losses, label='train', color='blue', linestyle='-', marker='.')
    plt.plot(test_losses, label='test', color='purple', linestyle='--', marker='.')
    plt.xlabel('epoch')
    plt.ylabel('loss')
    plt.title('Loss over Epochs')
    plt.legend()
    plt.grid(True)
    plt.ylim(0, 1)  # 设置y轴的范围从0.01到100
    plt.show()


# 选择多项式特征中的前4个维度
train(poly_features[:n_train, :4], poly_features[n_train:, :4],
      labels[:n_train], labels[n_train:], 0)

##  net.parameters() 是一个 PyTorch 模型的方法，用于返回模型所有参数的迭代器。这个迭代器产生模型中所有可学习的参数（例如权重和偏置）。

上述代码的模型是简单线性模型

net = nn.Sequential(nn.Linear(input_shape, 1, bias=False))  # 模型

此模型的下载与储存如下

    torch.save(net.state_dict(), "NetSave")  # 存模型
    net_try = nn.Sequential(nn.Linear(input_shape, 1, bias=False))  # 搭建模型框架
    print("net_try")
    print(net_try[0].weight)
    net_try.load_state_dict(torch.load("NetSave"))  # 下载模型
    net_try.eval()  # 评估模式
    print("net_try_load")
    print(net_try[0].weight)