【深度学习PyTorch入门】6.Optimizing Model Parameters 优化模型参数

Optimizing Model Parameters 优化模型参数

文章目录

• [Optimizing Model Parameters 优化模型参数](#Optimizing Model Parameters 优化模型参数)
• [Optimizing Model Parameters 优化模型参数](#Optimizing Model Parameters 优化模型参数)
• 前置代码
• [Hyperparameters 超参数](#Hyperparameters 超参数)
• [Optimization Loop 优化循环](#Optimization Loop 优化循环)
• • [Loss Function 损失函数](#Loss Function 损失函数)
  • [Optimizer 优化器](#Optimizer 优化器)
• [Full Implementation 全面实施](#Full Implementation 全面实施)
• [Further Reading 进一步阅读](#Further Reading 进一步阅读)
• 参考文献
• Github

Optimizing Model Parameters 优化模型参数

现在我们有了模型和数据，是时候通过优化数据上的参数来训练、验证和测试我们的模型了。训练模型是一个迭代过程；在每次迭代中，模型都会对输出进行猜测，计算其猜测中的误差（损失 ），收集相对于其参数的导数的误差（如我们在上一节中看到的），并使用梯度下降优化 这些参数。有关此过程的更详细演练，请观看3Blue1Brown 的反向传播有关视频。

前置代码

我们加载前面有关数据集和数据加载器 以及构建模型的代码。

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

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().__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()

Out:

Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz to data/FashionMNIST/raw/train-images-idx3-ubyte.gz

  0%|          | 0/26421880 [00:00<?, ?it/s]
  0%|          | 65536/26421880 [00:00<01:12, 363612.43it/s]
  1%|          | 229376/26421880 [00:00<00:38, 681614.69it/s]
  4%|3         | 950272/26421880 [00:00<00:11, 2185311.70it/s]
 13%|#2        | 3375104/26421880 [00:00<00:03, 6583220.66it/s]
 35%|###5      | 9306112/26421880 [00:00<00:00, 19065043.44it/s]
 45%|####5     | 11894784/26421880 [00:00<00:00, 17548305.75it/s]
 66%|######6   | 17465344/26421880 [00:01<00:00, 22251664.98it/s]
 87%|########6 | 22937600/26421880 [00:01<00:00, 29364458.17it/s]
100%|#########9| 26378240/26421880 [00:01<00:00, 26030331.64it/s]
100%|##########| 26421880/26421880 [00:01<00:00, 18174652.40it/s]
Extracting data/FashionMNIST/raw/train-images-idx3-ubyte.gz to data/FashionMNIST/raw

Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz to data/FashionMNIST/raw/train-labels-idx1-ubyte.gz

  0%|          | 0/29515 [00:00<?, ?it/s]
100%|##########| 29515/29515 [00:00<00:00, 327007.45it/s]
Extracting data/FashionMNIST/raw/train-labels-idx1-ubyte.gz to data/FashionMNIST/raw

Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz to data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz

  0%|          | 0/4422102 [00:00<?, ?it/s]
  1%|1         | 65536/4422102 [00:00<00:12, 363040.95it/s]
  5%|5         | 229376/4422102 [00:00<00:06, 683295.29it/s]
 21%|##1       | 950272/4422102 [00:00<00:01, 2194682.48it/s]
 75%|#######4  | 3309568/4422102 [00:00<00:00, 7145453.07it/s]
100%|##########| 4422102/4422102 [00:00<00:00, 6093019.93it/s]
Extracting data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz to data/FashionMNIST/raw

Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-labels-idx1-ubyte.gz
Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-labels-idx1-ubyte.gz to data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz

  0%|          | 0/5148 [00:00<?, ?it/s]
100%|##########| 5148/5148 [00:00<00:00, 38905003.59it/s]
Extracting data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz to data/FashionMNIST/raw

Hyperparameters 超参数

超参数是可调整的参数，可让您控制模型优化过程。不同的超参数值会影响模型训练和收敛速度（阅读有关超参数调整的更多信息）

我们定义以下训练超参数：

• Number of Epochs - 迭代数据集的次数
• Batch Size - 参数更新之前，通过网络传播的数据样本数量
• Learning Rate- 每个batch/epoch更新模型参数的量。较小的值会导致学习速度较慢，而较大的值可能会导致训练期间出现不可预测的行为。

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

Optimization Loop 优化循环

一旦我们设置了超参数，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 epoch由两个主要部分组成：

• The Train Loop- 迭代训练数据集并尝试收敛到最佳参数。
• **The Validation/Test Loop **- 迭代测试数据集以检查模型性能是否有所改善。

让我们简单熟悉一下训练循环中使用的一些概念。向前跳转查看优化循环的完整实现。

Loss Function 损失函数

当提供一些训练数据时，我们未经训练的网络可能不会给出正确的答案。损失函数衡量的是得到的结果与目标值的不相似程度，它是我们在训练时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（Mean Square Error 均方误差）和 用于分类的nn.NLLLoss（Negative Log Likelihood 负对数似然）。 nn.CrossEntropyLoss结合了nn.LogSoftmax和nn.NLLLoss。

我们将模型的输出 logits 传递给nn.CrossEntropyLoss，这将标准化 logits 并计算预测误差。

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

Optimizer 优化器

优化是调整模型参数以减少每个训练步骤中模型误差的过程。Optimization algorithms 定义了如何执行此过程（在本例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。这里，我们使用SGD优化器；此外，PyTorch 中还有许多不同的优化器 ，例如 ADAM 和 RMSProp，它们可以更好地处理不同类型的模型和数据。

注册需要训练的模型参数，并传入学习率超参数。我们通过这种方式，来初始化优化器。

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

在训练循环中，优化分三个步骤进行：

• 调用optimizer.zero_grad()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。
• 通过调用loss.backward()来反向传播预测损失。PyTorch 存储每个参数的损失梯度。
• 一旦我们有了梯度，通过后向传递中收集的梯度，我们就可以调用optimizer.step()来调整参数。

Full Implementation 全面实施

我们定义了train_loop优化代码的循环，test_loop根据我们的测试数据评估模型的性能。

def train_loop(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    # Set the model to training mode - important for batch normalization and dropout layers
    # Unnecessary in this situation but added for best practices
    model.train()
    for batch, (X, y) in enumerate(dataloader):
        # Compute prediction and loss
        pred = model(X)
        loss = loss_fn(pred, y)

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

        if batch % 100 == 0:
            loss, current = loss.item(), (batch + 1) * len(X)
            print(f"loss: {loss:>7f}  [{current:>5d}/{size:>5d}]")


def test_loop(dataloader, model, loss_fn):
    # Set the model to evaluation mode - important for batch normalization and dropout layers
    # Unnecessary in this situation but added for best practices
    model.eval()
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    test_loss, correct = 0, 0

    # Evaluating the model with torch.no_grad() ensures that no gradients are computed during test mode
    # also serves to reduce unnecessary gradient computations and memory usage for tensors with requires_grad=True
    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。请随意增加epoch数来跟踪模型改进的性能。

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)
    test_loop(test_dataloader, model, loss_fn)
print("Done!")

Out:

Epoch 1
-------------------------------
loss: 2.298730  [   64/60000]
loss: 2.289123  [ 6464/60000]
loss: 2.273286  [12864/60000]
loss: 2.269406  [19264/60000]
loss: 2.249603  [25664/60000]
loss: 2.229407  [32064/60000]
loss: 2.227368  [38464/60000]
loss: 2.204261  [44864/60000]
loss: 2.206193  [51264/60000]
loss: 2.166651  [57664/60000]
Test Error:
 Accuracy: 50.9%, Avg loss: 2.166725

Epoch 2
-------------------------------
loss: 2.176750  [   64/60000]
loss: 2.169595  [ 6464/60000]
loss: 2.117500  [12864/60000]
loss: 2.129272  [19264/60000]
loss: 2.079674  [25664/60000]
loss: 2.032928  [32064/60000]
loss: 2.050115  [38464/60000]
loss: 1.985236  [44864/60000]
loss: 1.987887  [51264/60000]
loss: 1.907162  [57664/60000]
Test Error:
 Accuracy: 55.9%, Avg loss: 1.915486

Epoch 3
-------------------------------
loss: 1.951612  [   64/60000]
loss: 1.928685  [ 6464/60000]
loss: 1.815709  [12864/60000]
loss: 1.841552  [19264/60000]
loss: 1.732467  [25664/60000]
loss: 1.692914  [32064/60000]
loss: 1.701714  [38464/60000]
loss: 1.610632  [44864/60000]
loss: 1.632870  [51264/60000]
loss: 1.514263  [57664/60000]
Test Error:
 Accuracy: 58.8%, Avg loss: 1.541525

Epoch 4
-------------------------------
loss: 1.616448  [   64/60000]
loss: 1.582892  [ 6464/60000]
loss: 1.427595  [12864/60000]
loss: 1.487950  [19264/60000]
loss: 1.359332  [25664/60000]
loss: 1.364817  [32064/60000]
loss: 1.371491  [38464/60000]
loss: 1.298706  [44864/60000]
loss: 1.336201  [51264/60000]
loss: 1.232145  [57664/60000]
Test Error:
 Accuracy: 62.2%, Avg loss: 1.260237

Epoch 5
-------------------------------
loss: 1.345538  [   64/60000]
loss: 1.327798  [ 6464/60000]
loss: 1.153802  [12864/60000]
loss: 1.254829  [19264/60000]
loss: 1.117322  [25664/60000]
loss: 1.153248  [32064/60000]
loss: 1.171765  [38464/60000]
loss: 1.110263  [44864/60000]
loss: 1.154467  [51264/60000]
loss: 1.070921  [57664/60000]
Test Error:
 Accuracy: 64.1%, Avg loss: 1.089831

Epoch 6
-------------------------------
loss: 1.166889  [   64/60000]
loss: 1.170514  [ 6464/60000]
loss: 0.979435  [12864/60000]
loss: 1.113774  [19264/60000]
loss: 0.973411  [25664/60000]
loss: 1.015192  [32064/60000]
loss: 1.051113  [38464/60000]
loss: 0.993591  [44864/60000]
loss: 1.039709  [51264/60000]
loss: 0.971077  [57664/60000]
Test Error:
 Accuracy: 65.8%, Avg loss: 0.982440

Epoch 7
-------------------------------
loss: 1.045165  [   64/60000]
loss: 1.070583  [ 6464/60000]
loss: 0.862304  [12864/60000]
loss: 1.022265  [19264/60000]
loss: 0.885213  [25664/60000]
loss: 0.919528  [32064/60000]
loss: 0.972762  [38464/60000]
loss: 0.918728  [44864/60000]
loss: 0.961629  [51264/60000]
loss: 0.904379  [57664/60000]
Test Error:
 Accuracy: 66.9%, Avg loss: 0.910167

Epoch 8
-------------------------------
loss: 0.956964  [   64/60000]
loss: 1.002171  [ 6464/60000]
loss: 0.779057  [12864/60000]
loss: 0.958409  [19264/60000]
loss: 0.827240  [25664/60000]
loss: 0.850262  [32064/60000]
loss: 0.917320  [38464/60000]
loss: 0.868384  [44864/60000]
loss: 0.905506  [51264/60000]
loss: 0.856353  [57664/60000]
Test Error:
 Accuracy: 68.3%, Avg loss: 0.858248

Epoch 9
-------------------------------
loss: 0.889765  [   64/60000]
loss: 0.951220  [ 6464/60000]
loss: 0.717035  [12864/60000]
loss: 0.911042  [19264/60000]
loss: 0.786085  [25664/60000]
loss: 0.798370  [32064/60000]
loss: 0.874939  [38464/60000]
loss: 0.832796  [44864/60000]
loss: 0.863254  [51264/60000]
loss: 0.819742  [57664/60000]
Test Error:
 Accuracy: 69.5%, Avg loss: 0.818780

Epoch 10
-------------------------------
loss: 0.836395  [   64/60000]
loss: 0.910220  [ 6464/60000]
loss: 0.668506  [12864/60000]
loss: 0.874338  [19264/60000]
loss: 0.754805  [25664/60000]
loss: 0.758453  [32064/60000]
loss: 0.840451  [38464/60000]
loss: 0.806153  [44864/60000]
loss: 0.830360  [51264/60000]
loss: 0.790281  [57664/60000]
Test Error:
 Accuracy: 71.0%, Avg loss: 0.787271

Done!

Further Reading 进一步阅读

• Loss Functions
• torch.optim
• Warmstart Training a Model

参考文献

Optimizing Model Parameters --- PyTorch Tutorials 2.2.0+cu121 documentation

Optimizing Model Parameters --- PyTorch Tutorials 2.2.0+cu121 documentation

Github

storm-ice/Get_started_with_PyTorch

storm-ice/Get_started_with_PyTorch