Pytorch（一） - 技术栈

线性模型，梯度下降和反向传播已经在深度学习中学习过了，这里就直接学习怎么用pytorch来实现这些过程。

一、实现线性模型

python 复制代码

import numpy as np
import matplotlib.pyplot as plt
 
x_data = [1.0, 2.0, 3.0]
y_data = [2.0, 4.0, 6.0]
 
 
def forward(x):
    return x*w
 
 
def loss(x, y):
    y_pred = forward(x)
    return (y_pred - y)**2
 
 
# 穷举法
w_list = []
mse_list = []
for w in np.arange(0.0, 4.1, 0.1):
    print("w=", w)
    l_sum = 0
    for x_val, y_val in zip(x_data, y_data):
        y_pred_val = forward(x_val)
        loss_val = loss(x_val, y_val)
        l_sum += loss_val
        print('\t', x_val, y_val, y_pred_val, loss_val)
    print('MSE=', l_sum/3)
    w_list.append(w)
    mse_list.append(l_sum/3)
    
plt.plot(w_list,mse_list)
plt.ylabel('Loss')
plt.xlabel('w')
plt.show()

二、实现梯度下降

python 复制代码

import matplotlib.pyplot as plt
 
# prepare the training set
x_data = [1.0, 2.0, 3.0]
y_data = [2.0, 4.0, 6.0]
 
# initial guess of weight 
w = 1.0
 
# define the model linear model y = w*x
def forward(x):
    return x*w
 
#define the cost function MSE 
def cost(xs, ys):
    cost = 0
    for x, y in zip(xs,ys):
        y_pred = forward(x)
        cost += (y_pred - y)**2
    return cost / len(xs)
 
# define the gradient function  gd
def gradient(xs,ys):
    grad = 0
    for x, y in zip(xs,ys):
        grad += 2*x*(x*w - y)
    return grad / len(xs)
 
epoch_list = []
cost_list = []
print('predict (before training)', 4, forward(4))
for epoch in range(100):
    cost_val = cost(x_data, y_data)
    grad_val = gradient(x_data, y_data)
    w-= 0.01 * grad_val  # 0.01 learning rate
    print('epoch:', epoch, 'w=', w, 'loss=', cost_val)
    epoch_list.append(epoch)
    cost_list.append(cost_val)
 
print('predict (after training)', 4, forward(4))
plt.plot(epoch_list,cost_list)
plt.ylabel('cost')
plt.xlabel('epoch')
plt.show()

三、反向传播

python 复制代码

import torch
x_data = [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 # 需要计算梯度
 
def forward(x):
    return x*w  # w是一个Tensor
 
 
def loss(x, y):
    y_pred = forward(x)
    return (y_pred - y)**2
 
print("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 forward, compute the loss
        l.backward() #  backward,compute grad for Tensor whose requires_grad set to True
        print('\tgrad:', x, y, w.grad.item())
        w.data = w.data - 0.01 * w.grad.data   # 权重更新时，注意grad也是一个tensor
 
        w.grad.data.zero_() # after update, remember set the grad to zero
 
    print('progress:', epoch, l.item()) # 取出loss使用l.item，不要直接使用l（l是tensor会构建计算图）
 
print("predict (after training)", 4, forward(4).item())