功能
自动求取梯度
函数
torch.autograd.backward(tensors, grad_tensors=None, retain_graph=None, create_graph=False)
参数
tensors:tensors
不是标量且需要求梯度的时候使用。
retain_graph:False
,则用于释放计算grad
的图。请注意,在几乎所有情况下,没有必要将此选项设置为True
,通常可以以更有效的方式解决。默认值为create_graph
的值。
create_graph:True
,则将构造派生图,允许计算更高阶的派生产品。默认为False
简单的应用:
给定w=1.0,x=2.0,{a=w+xb=w+1y=a×b,求∂y∂w
给定w=1.0,x=2.0,
\begin{cases}
a = w + x \\
b = w + 1 \\
y = a \times b
\end{cases},
求\frac{\partial y}{\partial w}
给定w=1.0,x=2.0,⎩⎪⎨⎪⎧a=w+xb=w+1y=a×b,求∂w∂y
import torch
w = torch.tensor([1.0], requires_grad=True) # requires_grad=True表明需要求它的梯度
x = torch.tensor([2.0], requires_grad=True)
a = torch.add(w, x)
b = torch.add(w, 1)
y = torch.mul(a, b)
y.backward() # 此方法内部调用的就是torch.autograd.backward()
print(w.grad) # tensor([5.])
retain_graph的作用:
# 前面代码一样,只是最后连续两次调用backward()方法
y.backward()
y.backward() # 报错,因为计算完成默认不保存计算图
# 可以改为:
# y.backward(retain_graph=True) dy/dw=5
# y.backward() dy/dw=10了
#
# # # # # # # # # # # # 相当于 # # # # # # # # # # # #
#
# loss = torch.cat([y0, y1], dim=0)
# grad_tensors = torch.tensor([1., 1.])
# loss.backward(gradient=grad_tensors) 其实是对 loss = 1 * y + 1 * y 进行反向传播
grad_tensors的作用:
我们手工计算时是可以出现Tensor对Tensor求导的,但是折回使程序异常复杂,所以PyTorch里只能是标量对Tensor求导
import torch
w = torch.tensor([1.0], requires_grad=True)
x = torch.tensor([2.0], requires_grad=True)
a = torch.add(w, x)
b = torch.add(w, 1)
y0 = torch.mul(a, b) # y0 = (x+w) * (w+1) 前面求过 dy0/dw = 5
y1 = torch.add(a, b) # y1 = (x+w)+ (w+1) dy1/dw = 2
loss = torch.cat([y0, y1], dim=0)
grad_tensors = torch.tensor([1., 2.])
# 这里真正求梯度的不是loss,而是loss与grad_tensors的内积
loss.backward(gradient=grad_tensors) # 其实是对 loss = 1 * y0 + 2 * y1 进行反向传播
print(w.grad) # tensor([9.]) dw = 1 * dy0/dw + 2 * dy1/dw
1.2 torch.autograd.grad()
功能
求取梯度
函数
torch.autograd.grad(outputs, inputs, grad_outputs=None, retain_graph=None,
create_graph=False,only_inputs=True, allow_unused=False)
参数
outputs:简单应用:
import torch
x = torch.tensor([3.], requires_grad=True)
y = torch.pow(x, 2) # y = x**2
grad_1 = torch.autograd.grad(y, x, create_graph=True) # grad_1 = dy/dx = 2x = 2 * 3 = 6
print(grad_1) # (tensor([6.], grad_fn=),)
grad_2 = torch.autograd.grad(grad_1[0], x) # grad_2 = d(dy/dx)/dx = 2
print(grad_2) # (tensor([2.]),)
1.3 autograd的Tips
梯度不自动清零
import torch
w = torch.tensor([1.], requires_grad=True)
x = torch.tensor([2.], requires_grad=True)
for i in range(4):
a = torch.add(w, x)
b = torch.add(w, 1)
y = torch.mul(a, b)
y.backward()
print(w.grad)
# ========输出结果==========
# tensor([5.])
# tensor([10.])
# tensor([15.])
# tensor([20.])
这里原因类似前面使用retain_graph=True
的情况,那如何每次求到正确的梯度呢?
答案是每次求玩梯度后清零
import torch
w = torch.tensor([1.], requires_grad=True)
x = torch.tensor([2.], requires_grad=True)
for i in range(4):
a = torch.add(w, x)
b = torch.add(w, 1)
y = torch.mul(a, b)
y.backward()
print(w.grad)
w.grad.zero_() # 下划线结尾的操作是原位操作
# ========输出结果==========
# tensor([5.])
# tensor([5.])
# tensor([5.])
# tensor([5.])
依赖于叶子结点的结点,requires_grad
默认为True
简单说,下层变量requires_grad
设为True
的话,用它来进行张量运算的结果,requires_grad
的默认值也是True
import torch
w = torch.tensor([1.], requires_grad=True)
x = torch.tensor([2.], requires_grad=True)
a = torch.add(w, x)
b = torch.add(w, 1)
y = torch.mul(a, b)
print(a.requires_grad, b.requires_grad, y.requires_grad) # True True True
叶子结点不能执行in-place操作
2. 机器学习模型训练步骤 3. Logistic回归的简单实现import torch
import torch.nn as nn
import matplotlib.pyplot as plt
import numpy as np
torch.manual_seed(10)
# ============================ step 1/5 生成数据 ============================
sample_nums = 100
mean_value = 1.7
bias = 1
n_data = torch.ones(sample_nums, 2)
x0 = torch.normal(mean_value * n_data, 1) + bias # 类别0 数据 shape=(100, 2)
y0 = torch.zeros(sample_nums) # 类别0 标签 shape=(100, 1)
x1 = torch.normal(-mean_value * n_data, 1) + bias # 类别1 数据 shape=(100, 2)
y1 = torch.ones(sample_nums) # 类别1 标签 shape=(100, 1)
train_x = torch.cat((x0, x1), 0)
train_y = torch.cat((y0, y1), 0)
# ============================ step 2/5 选择模型 ============================
class LR(nn.Module):
def __init__(self):
super(LR, self).__init__()
self.features = nn.Linear(2, 1)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
x = self.features(x)
x = self.sigmoid(x)
return x
lr_net = LR() # 实例化逻辑回归模型
# ============================ step 3/5 选择损失函数 ============================
loss_fn = nn.BCELoss()
# ============================ step 4/5 选择优化器 ============================
lr = 0.01 # 学习率
optimizer = torch.optim.SGD(lr_net.parameters(), lr=lr, momentum=0.9)
# ============================ step 5/5 模型训练 ============================
for iteration in range(1000):
# 前向传播
y_pred = lr_net(train_x)
# 计算 loss
loss = loss_fn(y_pred.squeeze(), train_y)
# 反向传播
loss.backward()
# 更新参数
optimizer.step()
# 清空梯度
optimizer.zero_grad()
# 绘图
if iteration % 20 == 0:
mask = y_pred.ge(0.5).float().squeeze() # 以0.5为阈值进行分类
correct = (mask == train_y).sum() # 计算正确预测的样本个数
acc = correct.item() / train_y.size(0) # 计算分类准确率
plt.scatter(x0.data.numpy()[:, 0], x0.data.numpy()[:, 1], c='r', label='class 0')
plt.scatter(x1.data.numpy()[:, 0], x1.data.numpy()[:, 1], c='b', label='class 1')
w0, w1 = lr_net.features.weight[0]
w0, w1 = float(w0.item()), float(w1.item())
plot_b = float(lr_net.features.bias[0].item())
plot_x = np.arange(-6, 6, 0.1)
plot_y = (-w0 * plot_x - plot_b) / w1
plt.xlim(-5, 7)
plt.ylim(-7, 7)
plt.plot(plot_x, plot_y)
plt.text(-5, 5, 'Loss=%.4f' % loss.data.numpy(), fontdict={'size': 20, 'color': 'red'})
plt.title("Iteration: {}\nw0:{:.2f} w1:{:.2f} b: {:.2f} accuracy:{:.2%}".format(iteration, w0, w1, plot_b, acc))
plt.legend()
plt.show()
plt.pause(0.5)
if acc > 0.999:
break