B站pytorch学习笔记(刘二大人）

算法：贪心算法，穷举法，分治法，动态规划
visdom可视化工具
np.meshgrid()用于三维图
训练失败可能是学习率太大

线性模型

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) * (y_pred - y)

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()

梯度下降

x_data = [1.0, 2.0, 3.0]
y_data = [2.0, 4.0, 6.0]

w = 1.0

def forward(x):
    return x * w

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)

def gradient(xs, ys):
    grad = 0
    for x, y in zip(xs, ys):
        grad += 2 * x * (x * w - y) # 求导的导数公式
    return grad / len(xs)

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
    print('epoch:', epoch, 'w=', w, 'loss=', cost_val)
print('predict (after training)', 4, forward(4))

随机梯度下降：取一个损失更新（以前是平均全部损失）（一加入了噪声，二大样本计算量大）

x_data = [1.0, 2.0, 3.0]
y_data = [2.0, 4.0, 6.0]

w = 1.0

def forward(x):
    return x * w

def loss(x, y):
    y_pred = forward(x)
    return (y_pred - y) ** 2

def gradient(x, y):
    return 2 * x * (x * w - y)

print('predict (before training)', 4, forward(4))
for epoch in range(100):
    for x, y in zip(x_data, y_data):
        grad = gradient(x, y)
        w -= 0.01 * grad # 及时更新，没办法并行运算，，batch
        print('\tgrad:', x, y, grad)
        l = loss(x, y)
    print("progress:", epoch, "w=", w, "loss", l)
print('predict (after training)', 4, forward(4))

反向传播

import torch

x_data = [1.0, 2.0, 3.0]
y_data = [2.0, 4.0, 6.0]

w = torch.Tensor([1.0])
w.requires_grad = True  # 需要计算梯度

def forward(x):
    return x * w  # 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) # 前向，计算loss
        l.backward() # 做完后计算图会释放
        print('\tgrad:', x, y, w.grad.item())  # item取值，要是张量计算图一直累积
        w.data -= 0.01 * w.grad.data  # 不取data会是TENSOR有计算图

        w.grad.data.zero_()  # 计算出来的梯度不清零会累加
    print("progress:", epoch, l.item())
print('predict (after training)', 4, forward(4).item())

pytorch 实现线性回归

import torch

x_data = torch.Tensor([[1.0], [2.0], [3.0]])
y_data = torch.Tensor([[2.0], [4.0], [6.0]])  # 这是几位的？3x1还是1x3

class LinearModel(torch.nn.Module):  # 可记住这个模板
    def __init__(self):  # 构造函数
        super(LinearModel, self).__init__()
        self.linear = torch.nn.Linear(1, 1)  # 构造对象，权重和偏执，，1是特征,输入输出维度

    def forward(self, x):  # model类自动反向传播
        y_pred = self.linear(x)
        return y_pred

model = LinearModel()  # 实例化，可调用

criterion = torch.nn.MSELoss(size_average=False)
optimizer