详解Pytorch自动求导机制

x = torch.tensor(1.).requires_grad_() # 第一种
x = torch.tensor(1., requires_grad=True) # 第二种

import torch
x=torch.tensor(1.,requires_grad=True)
b=torch.tensor(2.,requires_grad=True)
w=torch.tensor(3.,requires_grad=True)
z=w*x+b
z.backward()#反向传播
print(x.grad)#x导数值
print(w.grad)#w导数值
print(b.grad)#b导数值

import torch
x = torch.tensor(2.).requires_grad_()
y = torch.tensor(3.).requires_grad_()
z = x * x * y
z.backward(create_graph=True) # x.grad = 12
print(x.grad)
x.grad.data.zero_() #PyTorch使用backward()时默认会累加梯度，需要手动把前一次的梯度清零
x.grad.backward() #对x一次求导后为2xy，然后再次反向传播
print(x.grad)

import torch
# 创建一个多元函数，即Y=XW+b=Y=x1*w1+x2*w2*x3*w3+b，x不可求导，W,b设置可求导
X = torch.tensor([1.5, 2.5, 3.5], requires_grad=False)
W = torch.tensor([0.2, 0.4, 0.6], requires_grad=True)
b = torch.tensor(0.1, requires_grad=True)
Y = torch.add(torch.dot(X, W), b)
# 求导，通过backward函数来实现
Y.backward()
# 查看导数，也即所谓的梯度
print(W.grad)
print(b.grad)

 
import torch
import numpy as np
import torch.nn as nn
import torch.optim as optim
x_values=[i for i in range(11)]
x_train=np.array(x_values,dtype=np.float32)
x_train=x_train.reshape(-1,1)
y_values=[2*i +1 for i in x_values]
y_values=np.array(y_values,dtype=np.float32)
y_train=y_values.reshape(-1,1)
#这里线性回归就相当于不加激活函数的全连接层
class LinearRegression(nn.Module):
    def __init__(self):
        super(LinearRegression, self).__init__()
        self.linear = nn.Linear(1, 1)
    def forward(self, x):
        return self.linear(x)
#使用GPU训练
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# 创建模型实例和优化器
model = LinearRegression()
model.to(device)
optimizer = optim.SGD(model.parameters(), lr=0.01)
# 定义损失函数
criterion = nn.MSELoss()
for epoch in range(100):
    # 创建数据集
    inputs = torch.from_numpy(x_train).to(device)
    targets = torch.from_numpy(y_train).to(device)
    # 前向传播
    outputs = model(inputs)
    loss = criterion(outputs, targets)
    # 反向传播和优化器更新
    #梯度清零每一次迭代
    optimizer.zero_grad()
    #反向传播
    loss.backward()
    #更新权重参数
    optimizer.step()
    #每10轮，打印一下损失函数
    if epoch%10==0:
        print("epoch {}, loss {}".format(epoch,loss.item()))
#使用训练完的模型进行数据的预测
predicted=model(torch.from_numpy(x_train).to(device))
print(predicted)
print(targets)