注意
单击此处下载完整的示例代码
了解基础知识 ||快速入门 ||张量 ||数据集和数据加载器 ||变换 ||构建模型 ||Autograd ||优化 ||保存并加载模型
优化模型参数¶
创建时间： Feb 09， 2021 |上次更新时间：2024 年 1 月 31 日 |上次验证： Nov 05， 2024
现在我们已经有了模型和数据，是时候通过优化模型的参数来训练、验证和测试我们的模型了 我们的数据。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 guess （loss） 中的误差收集了误差相对于其参数的导数（正如我们在 上一节），并使用梯度下降优化这些参数。如需更多 此过程的详细演练，请观看 3Blue1Brown 的反向传播视频。
先决条件代码¶
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()
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%| | 0.00/26.4M [00:00<?, ?B/s]
0%| | 65.5k/26.4M [00:00<01:13, 360kB/s]
1%| | 197k/26.4M [00:00<00:45, 572kB/s]
3%|2 | 721k/26.4M [00:00<00:12, 2.03MB/s]
6%|6 | 1.61M/26.4M [00:00<00:07, 3.39MB/s]
22%|##1 | 5.77M/26.4M [00:00<00:01, 13.5MB/s]
35%|###5 | 9.34M/26.4M [00:00<00:01, 16.4MB/s]
56%|#####6 | 14.8M/26.4M [00:01<00:00, 25.7MB/s]
70%|######9 | 18.4M/26.4M [00:01<00:00, 26.7MB/s]
82%|########1 | 21.6M/26.4M [00:01<00:00, 25.5MB/s]
100%|##########| 26.4M/26.4M [00:01<00:00, 19.2MB/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%| | 0.00/29.5k [00:00<?, ?B/s]
100%|##########| 29.5k/29.5k [00:00<00:00, 330kB/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%| | 0.00/4.42M [00:00<?, ?B/s]
1%|1 | 65.5k/4.42M [00:00<00:12, 362kB/s]
5%|5 | 229k/4.42M [00:00<00:06, 681kB/s]
21%|## | 918k/4.42M [00:00<00:01, 2.59MB/s]
44%|####3 | 1.93M/4.42M [00:00<00:00, 4.09MB/s]
100%|##########| 4.42M/4.42M [00:00<00:00, 6.08MB/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%| | 0.00/5.15k [00:00<?, ?B/s]
100%|##########| 5.15k/5.15k [00:00<00:00, 29.2MB/s]
Extracting data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz to data/FashionMNIST/raw
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率 （阅读有关超参数优化的更多信息）
- 我们定义以下用于训练的超参数：
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
学习率 - 在每个批次/epoch 更新模型参数的量。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期间出现不可预知的行为。
learning_rate = 1e-3
batch_size = 64
epochs = 5
优化循环¶
设置超参数后，我们就可以使用优化循环来训练和优化我们的模型。每 优化循环的迭代称为 epoch。
- 每个 epoch 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。
让我们简要熟悉一下训练循环中使用的一些概念。跳转到 请参阅 优化循环的完整实现 。
损失函数¶
当看到一些训练数据时，我们未经训练的网络可能无法给出正确的 答。损失函数测量获得的结果与目标值的差异程度， 这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，我们做了一个 prediction 的 Alpha 数据 Sample，并将其与 True Data Label 值进行比较。
常见的损失函数包括 nn.MSELoss（均方误差）用于回归任务，nn.用于分类的 NLLLoss （Negative Log Likelihood）。nn.CrossEntropyLoss 结合了 和 。nn.LogSoftmaxnn.NLLLoss
我们将模型的输出 logits 传递给 ，后者将对 logit 进行归一化并计算预测误差。nn.CrossEntropyLoss
# Initialize the loss function
loss_fn = nn.CrossEntropyLoss()
优化¶
优化是调整模型参数以减少每个训练步骤中的模型误差的过程。优化算法定义了此过程的执行方式（在此示例中，我们使用随机梯度下降）。
所有优化逻辑都封装在对象中。在这里，我们使用 SGD 优化器;此外，PyTorch 中还提供了许多不同的优化器，例如 ADAM 和 RMSProp，它们更适合不同类型的模型和数据。optimizer
我们通过注册需要训练的模型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，优化分三个步骤进行：
调用 重置模型参数的梯度。默认情况下，梯度累加;为了防止重复计数，我们在每次迭代时都将它们显式归零。
optimizer.zero_grad()通过调用 .PyTorch 会根据每个参数来存储损失的梯度。
loss.backward()一旦我们有了梯度，我们就会调用以通过在 backward pass 中收集的梯度来调整参数。
optimizer.step()
全面实施¶
我们定义了 that 在优化代码上循环，并且
根据我们的测试数据评估模型的性能。train_looptest_loop
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 * batch_size + 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 和 。
随意增加 epoch 的数量来跟踪模型的改进性能。train_looptest_loop
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!")
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!