深度学习_18_模型的下载与读取

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].weightreturn torch.sum(w.pow(2)) / 2def train(train_features, test_features, train_labels, test_labels, lambd,num_epochs=100):loss = d2l.squared_lossinput_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 = 0total_samples = 0for 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 = 0total_samples = 0print(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100plt.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)