优化模型参数

Datasets & DataLoaders 和Build Model 

import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensor, Lambda

training_data = datasets.FashionMNIST(
    root="data",
    train=True,
    download=True,
    transform=ToTensor()
)

test_data = datasets.FashionMNIST(
    root="data",
    train=False,
    download=True,
    transform=ToTensor()
)

train_dataloader = DataLoader(training_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)

class NeuralNetwork(nn.Module):
    def __init__(self):
        super(NeuralNetwork, self).__init__()
        self.flatten = nn.Flatten()
        self.linear_relu_stack = nn.Sequential(
            nn.Linear(28*28, 512),
            nn.ReLU(),
            nn.Linear(512, 512),
            nn.ReLU(),
            nn.Linear(512, 10),
        )

    def forward(self, x):
        x = self.flatten(x)
        logits = self.linear_relu_stack(x)
        return logits

model = NeuralNetwork()

定义超参数

• Number of Epochs - 迭代数据集的次数
• Batch Size - 在更新参数之前通过网络传播的数据样本数量
• 学习率- 在每个批次/时期更新模型参数的程度。较小的值会导致学习速度变慢，而较大的值可能会导致训练过程中出现不可预测的行为。

learning_rate = 1e-3
batch_size = 64
epochs = 5

优化循环

一旦我们设置了我们的超参数，我们就可以使用优化循环来训练和优化我们的模型。优化循环的每次迭代称为一个epoch。

每个时代由两个主要部分组成：

• 训练循环- 迭代训练数据集并尝试收敛到最佳参数。
• 验证/测试循环- 迭代测试数据集以检查模型性能是否正在提高。

损失函数

损失函数衡量得到的结果与目标值的不相似程度，是我们在训练过程中想要最小化的损失函数。为了计算损失，我们使用给定数据样本的输入进行预测，并将其与真实数据标签值进行比较。

常见的损失函数包括用于回归任务的nn.MSELoss（均方误差）和 用于分类的nn.NLLLoss（负对数似然）。 nn.CrossEntropyLoss结合nn.LogSoftmax和nn.NLLLoss。

# Initialize the loss function
loss_fn = nn.CrossEntropyLoss()

优化器

优化算法定义了这个过程是如何执行的（在这个例子中我们使用随机梯度下降）。所有优化逻辑都封装在optimizer对象中。在这里，我们使用 SGD 优化器；此外， PyTorch 中有许多不同的优化器可用，例如 ADAM 和 RMSProp，它们更适用于不同类型的模型和数据。

我们通过注册模型需要训练的参数并传入学习率超参数来初始化优化器。

optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)

在训练循环中，优化分三步进行：

• 调用optimizer.zero_grad()以重置模型参数的梯度。默认情况下渐变相加；为了防止重复计算，我们在每次迭代时明确地将它们归零。
• 调用 来反向传播预测损失loss.backwards()。PyTorch 存储了每个参数的损失梯度。
• 一旦我们有了梯度，我们就调用optimizer.step()在向后传递中收集的梯度来调整参数。

全面实施 

def train_loop(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    for batch, (X, y) in enumerate(dataloader):
        # Compute prediction and loss
        pred = model(X)
        loss = loss_fn(pred, y)

        # Backpropagation
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if batch % 100 == 0:
            loss, current = loss.item(), batch * len(X)
            print(f"loss: {loss:>7f}  [{current:>5d}/{size:>5d}]")


def a_loop(dataloader, model, loss_fn):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    test_loss, correct = 0, 0

    with torch.no_grad():
        for X, y in dataloader:
            pred = model(X)
            test_loss += loss_fn(pred, y).item()
            correct += (pred.argmax(1) == y).type(torch.float).sum().item()

    test_loss /= num_batches
    correct /= size
    print(f"Test Error: \n Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} \n")

我们初始化损失函数和优化器，并将其传递给train_loop和test_loop。随意增加 epochs 的数量以跟踪模型的改进性能。

loss_fn = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)

epochs = 10
for t in range(epochs):
    print(f"Epoch {t+1}\n-------------------------------")
    train_loop(train_dataloader, model, loss_fn, optimizer)
    a_loop(test_dataloader, model, loss_fn)
print("Done!")

完整代码

import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensor, Lambda

training_data = datasets.FashionMNIST(
    root="data",
    train=True,
    download=True,
    transform=ToTensor()
)

test_data = datasets.FashionMNIST(
    root="data",
    train=False,
    download=True,
    transform=ToTensor()
)

train_dataloader = DataLoader(training_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)

class NeuralNetwork(nn.Module):
    def __init__(self):
        super(NeuralNetwork, self).__init__()
        self.flatten = nn.Flatten()
        self.linear_relu_stack = nn.Sequential(
            nn.Linear(28*28, 512),
            nn.ReLU(),
            nn.Linear(512, 512),
            nn.ReLU(),
            nn.Linear(512, 10),
        )

    def forward(self, x):
        x = self.flatten(x)
        logits = self.linear_relu_stack(x)
        return logits

model = NeuralNetwork()

learning_rate = 1e-3
batch_size = 64
epochs = 5

# Initialize the loss function
loss_fn = nn.CrossEntropyLoss()

optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)

def train_loop(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    for batch, (X, y) in enumerate(dataloader):
        # Compute prediction and loss
        pred = model(X)
        loss = loss_fn(pred, y)

        # Backpropagation
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if batch % 100 == 0:
            loss, current = loss.item(), batch * len(X)
            print(f"loss: {loss:>7f}  [{current:>5d}/{size:>5d}]")


def a_loop(dataloader, model, loss_fn):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    test_loss, correct = 0, 0

    with torch.no_grad():
        for X, y in dataloader:
            pred = model(X)
            test_loss += loss_fn(pred, y).item()
            correct += (pred.argmax(1) == y).type(torch.float).sum().item()

    test_loss /= num_batches
    correct /= size
    print(f"Test Error: \n Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} \n")
loss_fn = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)

epochs = 10
for t in range(epochs):
    print(f"Epoch {t+1}\n-------------------------------")
    train_loop(train_dataloader, model, loss_fn, optimizer)
    a_loop(test_dataloader, model, loss_fn)
print("Done!")

结果

参考链接：

pytorch官网https://pytorch.org/tutorials/beginner/basics/optimization_tutorial.html#full-impl-labelhttps://pytorch.org/tutorials/beginner/basics/optimization_tutorial.html#full-impl-label