为什么当我在 'with torch.no_grad():' 中包含 'loss.backward()' 时，反向传播过程仍然可以工作？

Question

我正在 PyTorch 中使用线性回归示例。我知道我在 'with torch.no_grad():' 中包含 'loss.backward()' 是错误的，但是为什么它与我的代码运行良好？

根据pytorch docs，torch.autograd.no_grad是一个禁用梯度计算的上下文管理器。所以我真的很困惑。

代码在这里：

import torch
import torch.nn as nn
import numpy as np
import matplotlib.pyplot as plt
# Toy dataset
x_train = np.array([[3.3], [4.4], [5.5], [6.71], [6.93], [4.168], 
                    [9.779], [6.182], [7.59], [2.167], [7.042], 
                    [10.791], [5.313], [7.997], [3.1]], dtype=np.float32)

y_train = np.array([[1.7], [2.76], [2.09], [3.19], [1.694], [1.573], 
                    [3.366], [2.596], [2.53], [1.221], [2.827], 
                    [3.465], [1.65], [2.904], [1.3]], dtype=np.float32)

input_size = 1
output_size = 1
epochs = 100
learning_rate = 0.05

model = nn.Linear(input_size, output_size)


criterion = nn.MSELoss(reduction='sum')
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

# training
for epoch in range(epochs):
    # convert numpy to tensor
    inputs = torch.from_numpy(x_train)
    targets = torch.from_numpy(y_train)

    # forward
    out = model(inputs)
    loss = criterion(out, targets)

    # backward
    with torch.no_grad():
        model.zero_grad()
        loss.backward()
        optimizer.step()
        print('inputs grad : ', inputs.requires_grad)
    if epoch % 5 == 0:
        print ('Epoch [{}/{}], Loss: {:.4f}'.format(epoch+1, epochs, loss.item()))

predicted = model(torch.from_numpy(x_train)).detach().numpy()
plt.plot(x_train, y_train, 'ro', label='Original data')
plt.plot(x_train, predicted, label='Fitted line')
plt.legend()
plt.show()

# Save the model checkpoint
torch.save(model.state_dict(), 'model\linear_model.ckpt')

预先感谢您回答我的问题。

Answer 1

这是有效的，因为损失计算发生在 之前，no_grad并且您继续根据该损失计算（该计算启用了梯度）计算梯度。

基本上，您继续使用在no_grad.

当您实际使用时no_grad：

for epoch in range(epochs):
    # convert numpy to tensor
    inputs = torch.from_numpy(x_train)
    targets = torch.from_numpy(y_train)
    with torch.no_grad():  # no_grad used here
    # forward
        out = model(inputs)
        loss = criterion(out, targets)
        model.zero_grad()
        loss.backward()
        optimizer.step()
        print('inputs grad : ', inputs.requires_grad)
    if epoch % 5 == 0:
        print ('Epoch [{}/{}], Loss: {:.4f}'.format(epoch+1, epochs, loss.item()))

然后你会得到正确的错误，说：

element 0 of tensors does not require grad and does not have a grad_fn.

也就是你no_grad在不合适的地方使用它。

如果你打印.requires_gradof loss，那么你会看到 loss has requires_grad。

也就是说，当你这样做时：

for epoch in range(epochs):
    # convert numpy to tensor
    inputs = torch.from_numpy(x_train)
    targets = torch.from_numpy(y_train)

    # forward
    out = model(inputs)
    loss = criterion(out, targets)

    # backward
    with torch.no_grad():
        model.zero_grad()
        loss.backward()

        optimizer.step()
        print('inputs grad : ', inputs.requires_grad)
        print('loss grad : ', loss.requires_grad)  # Prints loss.require_rgad
    if epoch % 5 == 0:
        print ('Epoch [{}/{}], Loss: {:.4f}'.format(epoch+1, epochs, loss.item()))

你会看见：

inputs grad :  False
loss grad :  True

此外，该

print('inputs grad : ', inputs.requires_grad)

将始终打印False。也就是说，如果你这样做

for epoch in range(epochs):
    # convert numpy to tensor
    inputs = torch.from_numpy(x_train)
    targets = torch.from_numpy(y_train)

    print('inputs grad : ', inputs.requires_grad). # Print the inputs.requires_grad

    # forward
    out = model(inputs)
    loss = criterion(out, targets)

    # backward
    with torch.no_grad():
        model.zero_grad()
        loss.backward()

        optimizer.step()
        print('inputs grad : ', inputs.requires_grad)
        print('loss grad : ', loss.requires_grad)
    if epoch % 5 == 0:
        print ('Epoch [{}/{}], Loss: {:.4f}'.format(epoch+1, epochs, loss.item()))

你会得到：

inputs grad :  False
inputs grad :  False
loss grad :  True

也就是说，您正在使用错误的东西来检查您做错了什么。你能做的最好的事情是再次阅读 PyTorch 关于梯度力学的文档。