pytorch学习3 -- 自动求导系统autograd

对pytorch的自动求导系统中常用两个方法：torch.autograd.back和torch.autograd.grad进行介绍

torch.autograd.backward(tensors,grad_tensors=None,retain_graph=None,create_graph=False)

• tensors：用于求导的张量，如loss
• retain_graph：保存计算图
• create_graph：创建导数计算图，用于高阶求导
• grad_tensors：多梯度权重（多个loss的比例）

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)

    y.backward(retain_graph=True)#retain_graph=True保存计算图，从而可进行第二次计算
    print(w.grad)
    y.backward()

这里张量y.backward使用的就是torch里的backgrad.

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.])#grad_tensor用于多个梯度之间权重的设置

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

    print(w.grad)

tensor([9.])

torch.autograd.grad(outputs,inputs,grad_outputs=None,retain_graph=None,create_graph=False)

• 功能：求取梯度
• outputs：用于求导的张量，如loss
• inputs：需要求梯度的张量
• create_graph：创建导数计算图，用于高阶求导
• retain_graph：保存计算图
• grad_outputs：多梯度权重

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
    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)

(tensor([6.], grad_fn=<MulBackward0>),)
(tensor([2.]),)

autograd小贴士：

• 1.梯度不自动清零
• 2.依赖于叶子结点的结点，requires_grad默认为True
• 3.叶子结点不可执行in-place

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)

        w.grad.zero_()#梯度清零，_下划线表示原位操作

tensor([5.])
tensor([5.])
tensor([5.])
tensor([5.])

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)

        #w.grad.zero_()#梯度清零，_下划线表示原位操作

tensor([5.])
tensor([10.])
tensor([15.])
tensor([20.])

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)

True True True

flag = True
#flag = False
if flag:
    a = torch.ones((1, ))
    print(id(a), a)

    a = a + torch.ones((1, ))#会开辟一个新的内存地址，在新的地址中赋用a
    print(id(a), a)

    a += torch.ones((1, ))#前后a的地址不变
    print(id(a), a)
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()



2506753264160 tensor([1.])
2506753184248 tensor([2.])
2506753184248 tensor([3.])
Traceback (most recent call last):

  File "<ipython-input-15-3433767bdebc>", line 23, in <module>
    w.add_(1)

RuntimeError: a leaf Variable that requires grad has been used in an in-place operation.

逻辑回归

逻辑回归模型是线性的二分类模型

模型表达式：

  f(x) 称为sigmoid函数，也称为logistic函数。

y< 0.5,  class 为0

线性回归是分析自变量x与因变量y（标量）之间关系的方法

 

对数几率回归

 

机器学习模型训练的五个步骤

获取数据、处理清洗数据

模型

损失函数模型选择

优化器

反复迭代训练

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()

    # 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