Pytorch深度学习|Pytorch深度学习实践（b站刘二大人）_04讲（反向传播）深度学习|python|pytorch

本节课讲的是反向传播。
课堂代码：

#反向传播课上代码import torchx_data = https://www.it610.com/article/[1.0, 2.0, 3.0] y_data = [2.0, 4.0, 6.0]w = torch.tensor([1.0])# w的初值为1.0 w.requires_grad = True# 默认为False，True表示需要计算梯度def forward(x): return x * wdef loss(x, y): y_pred = forward(x) return (y_pred - y) ** 2print("predict (before training)", 4, forward(4).item())for epoch in range(100): for x, y in zip(x_data, y_data): l = loss(x, y)# l是一个张量，tensor主要是在建立计算图 l.backward() print('\tgrad:', x, y, w.grad.item()) w.data = https://www.it610.com/article/w.data - 0.01 * w.grad.data# 权重更新时，需要用到标量，注意grad也是一个tensorw.grad.data.zero_()# 将梯度置为0print('progress:', epoch, l.item())# 取出loss使用l.item，直接使用l会构建计算图print("predict (after training)", 4, forward(4).item())

运行结果图：

Pytorch深度学习|Pytorch深度学习实践（b站刘二大人）_04讲（反向传播）

文章图片

课后作业：

#import datetime# 设置函数y = x^2+2x+34应对应得到27 x_data = https://www.it610.com/article/[1.0,2.0,3.0] y_data = [6.0,11.0,18.0]w1 = torch.Tensor([0.0])# w1的初值为0.0 w1.requires_grad = True# 需要计算梯度 w2 = torch.Tensor([1.0])# w2的初值为1.0 w2.requires_grad = True b = torch.Tensor([1.0])# b的初值为1.0 b.requires_grad = Truedef forward(x): return w1 * x **2 + w2 * x + bdef loss(x,y):# 构建计算图 y_pred = forward(x) return (y_pred - y) ** 2starttime = datetime.datetime.now()print("predict (before training)", 4, forward(4).item())for epoch in range(10000): for x,y in zip(x_data,y_data): l = loss(x,y) l.backward() print('\tgrad:',x,y,w1.grad.item(),w2.grad.item(),b.grad.item()) w1.data = https://www.it610.com/article/w1.data - 0.01 * w1.grad.data # 权重更新 w2.data = w2.data - 0.01 * w2.grad.data b.data = b.data - 0.01 * b.grad.data w1.grad.data.zero_()# 释放之前计算的梯度 w2.grad.data.zero_() b.grad.data.zero_() print('progress:',epoch,l.item())print("predict (after training)", 4, forward(4).item()) #目标得到27 #endtime = datetime.datetime.now() #print('程序运行时间：') #c = (endtime - starttime).seconds #print(c)

【Pytorch深度学习|Pytorch深度学习实践（b站刘二大人）_04讲（反向传播）】运行结果图：