pytorch学习笔记：autograd

# flag = True
flag = False
if flag:
    w = torch.tensor([1.], requires_grad=True)
    x = torch.tensor([2.], requires_grad=True)

    a = torch.add(w, x)     # retain_grad()
    b = torch.add(w, 1)

    y0 = torch.mul(a, b)    # y0 = (x+w) * (w+1)
    y1 = torch.add(a, b)    # y1 = (x+w) + (w+1)    dy1/dw = 2

    loss = torch.cat([y0, y1], dim=0)       # [y0, y1]
    grad_tensors = torch.tensor([1., 2.])

    loss.backward(gradient=grad_tensors)    # gradient 传入 torch.autograd.backward()中的grad_tensors

    print(w.grad)

利用gra实现高阶求导

# flag = True
flag = False
if flag:

    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 创建倒数计算图才能继续求高阶导
    print(grad_1)

    grad_2 = torch.autograd.grad(grad_1[0], x)              # grad_2 = d(dy/dx)/dx = d(2x)/dx = 2
    print(grad_2)

autugrad注意事项

• 梯度不自动清零

# flag = True
flag = False
if flag:

    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)  #当不手动清零梯度时会不断叠加

        w.grad.zero_()  #_in-place操作，原位操作（覆盖旧的值）

• 依赖于叶子结点的结点，requires_grads默认为true，但想查看非叶子结点的梯度需要设置retain_grad为true，默认会被释放

# flag = True
flag = False
if flag:

    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)

• 叶子结点不可执行in-place

# flag = True
flag = False
if flag:

    a = torch.ones((1, ))
    print(id(a), a)

    # a = a + torch.ones((1, ))
    # print(id(a), a)   #地址发生了改变，非原位操作

    a += torch.ones((1, ))
    print(id(a), a)   #原位操作，在原始地址上修改参数值

# flag = True
flag = False
if flag:

    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)

    w.add_(1)
    y.backward()   #会报错执行了in-place操作
    

为什么叶子结点不能执行in-place操作呢？
因为我们在前向传播过程中记录了叶子结点的地址用于反向传播时计算梯度，如果此时修改了叶子结点的值，则会造成梯度求解错误。就好像我们去超市购物时把包存到了一个柜子里，如果工作人员把柜子里的包换到别的柜子，你出来就无法找到自己的包了

机器学习模型的五大模块

• 数据
• 模型
• 损失函数
• 优化器
• 迭代训练

逻辑回归模型实现

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 > 0.99:
            break

本文为深度之眼Pytorch课程的学习笔记，仅供自己学习使用，如有问题欢迎讨论！关于课程可以扫描下图二维码