pytorch 入门学习反向传播

反向传播

import  numpy as np
import matplotlib.pyplot as plt
import torchdef forward(x):return x * wdef loss(x,y):y_pred = forward(x)return (y_pred - y) **2x_data = [1.0, 2.0, 3.0]
y_data = [2.0 ,4.0, 6.0]w = torch.Tensor([1.0])
w.requires_grad = Trueprint("predict (before training)",4,forward(4).item())for epoch in range(10):for x,y  in zip(x_data,y_data):l = loss(x,y)l.backward()  #反向传播，计算梯度print('\tgrad:',x,y,w.grad.item())w.data = w.data - 0.01*w.grad.dataw.grad.data.zero_()  #清空梯度print("progress:",epoch,l.item())
print("predict (after training)",4,forward(4).item())

#out:
predict (before training) 4 4.0grad: 1.0 2.0 -2.0grad: 2.0 4.0 -7.840000152587891grad: 3.0 6.0 -16.228801727294922
progress: 0 7.315943717956543grad: 1.0 2.0 -1.478623867034912grad: 2.0 4.0 -5.796205520629883grad: 3.0 6.0 -11.998146057128906
progress: 1 3.9987640380859375grad: 1.0 2.0 -1.0931644439697266grad: 2.0 4.0 -4.285204887390137grad: 3.0 6.0 -8.870372772216797
progress: 2 2.1856532096862793grad: 1.0 2.0 -0.8081896305084229grad: 2.0 4.0 -3.1681032180786133grad: 3.0 6.0 -6.557973861694336
progress: 3 1.1946394443511963grad: 1.0 2.0 -0.5975041389465332grad: 2.0 4.0 -2.3422164916992188grad: 3.0 6.0 -4.848389625549316
progress: 4 0.6529689431190491grad: 1.0 2.0 -0.4417421817779541grad: 2.0 4.0 -1.7316293716430664grad: 3.0 6.0 -3.58447265625
progress: 5 0.35690122842788696grad: 1.0 2.0 -0.3265852928161621grad: 2.0 4.0 -1.2802143096923828grad: 3.0 6.0 -2.650045394897461
progress: 6 0.195076122879982grad: 1.0 2.0 -0.24144840240478516grad: 2.0 4.0 -0.9464778900146484grad: 3.0 6.0 -1.9592113494873047
progress: 7 0.10662525147199631grad: 1.0 2.0 -0.17850565910339355grad: 2.0 4.0 -0.699742317199707grad: 3.0 6.0 -1.4484672546386719
progress: 8 0.0582793727517128grad: 1.0 2.0 -0.1319713592529297grad: 2.0 4.0 -0.5173273086547852grad: 3.0 6.0 -1.070866584777832
progress: 9 0.03185431286692619
predict (after training) 4 7.804864406585693Process finished with exit code 0

pytorch 入门学习反向传播-4相关推荐

pytorch学习 -- 反向传播backward
pytorch学习 – 反向传播backward 入门学习pytorch,在查看pytorch代码时对autograd的backard函数的使用和具体原理有些疑惑,在查看相关文章和学习后,简单说下我自 ...
pytorch 入门学习多分类问题-9
pytorch 入门学习多分类问题运行结果 [1, 300] loss: 2.287[1, 600] loss: 2.137[1, 900] loss: 1.192 Accuracy on test ...
pytorch 入门学习加载数据集-8
pytorch 入门学习加载数据集 import torch import numpy as np import torchvision import numpy as np from torch.u ...
pytorch 入门学习处理多维特征输入-7
pytorch 入门学习处理多维特征输入处理多维特征输入 import torch import numpy as np import torchvision import numpy as np ...
pytorch 入门学习使用逻辑斯蒂做二分类-6
pytorch 入门学习使用逻辑斯蒂做二分类使用pytorch实现逻辑斯蒂做二分类 import torch import torchvision import numpy as np import ...
pytorch 入门学习实现线性回归-5
pytorch 入门学习实现线性回归使用pytorch实现线性回归 import numpy as np import matplotlib.pyplot as plt import torch#p ...
深度学习入门-误差反向传播法（人工神经网络实现mnist数据集识别）
文章目录误差反向传播法 5.1 链式法则与计算图 5.2 计算图代码实践 5.3激活函数层的实现 5.4 简单矩阵求导 5.5 Affine 层的实现 5.6 softmax-with-loss层计 ...
Pytorch(5)-梯度反向传播
自动求梯度 1. 函数对自变量x求梯度--ax^2+b 2. 网络对参数w求梯度- loss(w,x) 3. 自动求梯度的底层支持--torch.autograd 3.1 Variable 3.1.1 ...
程序媛养成第0天--pytorch入门学习
本篇基于<深度学习框架-pytorch入门与实践>陈云有一起监督学习打卡的小伙伴请私信 2.2 pytorch入门第一步 2.2.1 Tensor # 分配矩阵空间但不初始化 #使用 [ ...

pytorch 入门学习反向传播-4

pytorch 入门学习反向传播

pytorch 入门学习反向传播-4相关推荐

最新文章

热门文章