注意
点击 这里 下载完整的示例代码
学习基础 || 快速入门 || 张量 || 数据集和数据加载器 || 变换 || 构建模型 || 自动微分 || 优化 || 保存和加载模型
优化模型参数¶
现在我们有了模型和数据，是时候通过优化模型参数来训练、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，计算其猜测的误差（损失），收集误差相对于其参数的导数（正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，请查看有关来自 3Blue1Brown 的反向传播的视频。
先决条件代码¶
我们从先前章节中加载代码，这些章节介绍了数据集和数据加载器以及构建模型。
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<01:12, 363kB/s]
1%| | 229k/26.4M [00:00<00:38, 684kB/s]
4%|3 | 950k/26.4M [00:00<00:11, 2.19MB/s]
15%|#4 | 3.83M/26.4M [00:00<00:02, 7.63MB/s]
38%|###7 | 9.96M/26.4M [00:00<00:00, 17.1MB/s]
61%|###### | 16.1M/26.4M [00:01<00:00, 22.8MB/s]
84%|########3 | 22.2M/26.4M [00:01<00:00, 26.3MB/s]
100%|##########| 26.4M/26.4M [00:01<00:00, 19.4MB/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, 163kB/s]
100%|##########| 29.5k/29.5k [00:00<00:00, 162kB/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%|##1 | 950k/4.42M [00:00<00:01, 2.18MB/s]
87%|########6 | 3.83M/4.42M [00:00<00:00, 7.60MB/s]
100%|##########| 4.42M/4.42M [00:00<00:00, 6.09MB/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, 33.3MB/s]
Extracting data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz to data/FashionMNIST/raw
超参数¶
超参数是可以调整的参数，它们可以让你控制模型优化过程。不同的超参数值会影响模型训练和收敛速度（了解更多关于超参数调优的信息）。
- 我们为训练定义以下超参数：
时期数 - 在数据集上迭代的次数。
批次大小 - 在更新参数之前，通过网络传播的数据样本数量。
学习率 - 在每次批次/时期更新模型参数的幅度。较小的值会导致学习速度缓慢，而较大的值可能会导致训练过程中的不可预测行为。
learning_rate = 1e-3
batch_size = 64
epochs = 5
优化循环¶
在设置了超参数后，我们就可以使用优化循环来训练和优化模型。优化循环的每次迭代被称为一个时期。
- 每个时期包含两个主要部分：
训练循环 - 在训练数据集上迭代，并尝试收敛到最佳参数。
验证/测试循环 - 在测试数据集上迭代，检查模型性能是否有所提升。
让我们简要了解一下训练循环中使用的概念。跳过此部分直接查看完整实现的优化循环。
损失函数¶
当给定一些训练数据时，我们的未训练网络可能无法给出正确的结果。损失函数衡量获得的结果与目标值的差异程度，我们希望在训练过程中最小化损失函数。为了计算损失，我们使用给定数据样本的输入进行预测，并将预测结果与真实数据标签值进行比较。
常见的损失函数包括nn.MSELoss（均方误差），适用于回归任务，以及nn.NLLLoss（负对数似然），适用于分类任务。nn.CrossEntropyLoss将nn.LogSoftmax和nn.NLLLoss结合在一起。
我们将模型的输出 logits 传递给nn.CrossEntropyLoss，它会对 logits 进行归一化并计算预测误差。
# Initialize the loss function
loss_fn = nn.CrossEntropyLoss()
优化器¶
优化是指调整模型参数以减少每次训练步骤中的模型误差的过程。优化算法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 还提供许多不同的优化器，例如 ADAM 和 RMSProp，它们更适合不同的模型和数据类型。
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
optimizer.zero_grad()重置模型参数的梯度。默认情况下，梯度会累加；为了防止重复计数，我们在每次迭代中显式地将其归零。使用
loss.backward()反向传播预测损失。PyTorch 将损失相对于每个参数的梯度存储起来。在获得梯度后，我们调用
optimizer.step()根据反向传播中收集的梯度调整参数。
完整实现¶
我们定义了train_loop来循环执行优化代码，以及test_loop来评估模型在测试数据上的性能。
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 * 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")
我们初始化了损失函数和优化器，并将其传递给train_loop和test_loop。可以随意增加时期数，以跟踪模型性能的提升。
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!
