03 感知机、衰退、丢弃

最新推荐文章于 2024-09-03 10:06:50 发布

CPU疼

最新推荐文章于 2024-09-03 10:06:50 发布

阅读量478

点赞数 1

分类专栏：李沐_动手学pytorch 学习笔记文章标签：深度学习 pytorch 神经网络

本文链接：https://blog.csdn.net/weixin_54424184/article/details/123313024

版权

李沐_动手学pytorch 学习笔记专栏收录该内容

10 篇文章 4 订阅

订阅专栏

对应沐神B站课程10_P2

import torch
from torch import nn
from d2l import torch as d2l

# 激活函数
def relu(X):
    a = torch.zeros_like(X)  # 生成与X同型但值全为0的
    return torch.max(X, a)

# 模型
def net(X):
    X = X.reshape((-1, num_inputs))
    H = relu(X@W1 + b1)  # 这里“@”代表矩阵乘法
    return (H@W2 + b2)

if __name__ == '__main__':
    # 初始化模型参数
    batch_size = 256
    num_epochs, lr = 10, 0.1
    # 初始化模型参数
    num_inputs, num_outputs, num_hiddens = 784, 10, 256
    # 随机生成一个784*256的矩阵
    W1 = nn.Parameter(torch.randn(   # nn.Parameter声明W1是torch的参数，可不加。
        num_inputs, num_hiddens, requires_grad=True) * 0.01)
    b1 = nn.Parameter(torch.zeros(num_hiddens, requires_grad=True))
    W2 = nn.Parameter(torch.randn(
        num_hiddens, num_outputs, requires_grad=True) * 0.01)
    b2 = nn.Parameter(torch.zeros(num_outputs, requires_grad=True))
    params = [W1, b1, W2, b2]
    # 加载数据
    train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
    # 内置函数来计算softmax和交叉熵损失
    loss = nn.CrossEntropyLoss(reduction='none')
    updater = torch.optim.SGD(params, lr=lr)
    d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, updater)
    d2l.plt.show()

笔记

import torch
from torch import nn
from d2l import torch as d2l


def init_weights(m):
    if type(m) == nn.Linear:
        nn.init.normal_(m.weight, std=0.01)

if __name__ == '__main__':
    batch_size, lr, num_epochs = 256, 0.1, 10
    net = nn.Sequential(nn.Flatten(),
                        nn.Linear(784, 256),
                        nn.ReLU(),
                        nn.Linear(256, 10))
    net.apply(init_weights)
    loss = nn.CrossEntropyLoss(reduction='none')
    trainer = torch.optim.SGD(net.parameters(), lr=lr)
    train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
    d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer)
    d2l.plt.show()

对应沐神B站课程11_P3

import math
import numpy as np
import torch
from torch import nn
from d2l import torch as d2l


def evaluate_loss(net, data_iter, loss):
    """评估给定数据集上模型的损失"""
    metric = d2l.Accumulator(2)  # 损失的总和,样本数量
    for X, y in data_iter:
        out = net(X)
        y = y.reshape(out.shape)
        l = loss(out, y)
        metric.add(l.sum(), l.numel())
    return metric[0] / metric[1]

def train(train_features, test_features, train_labels, test_labels,
          num_epochs=600):
    loss = nn.MSELoss(reduction='none')  # 使用均方差损失 返回向量
    input_shape = train_features.shape[-1]
    # 不设置偏置，因为我们已经在多项式中实现了它
    net = nn.Sequential(nn.Linear(input_shape, 1, bias=False))   # 使用nn.线性模型
    batch_size = min(10, train_labels.shape[0])  # batch_size
    train_iter = d2l.load_array((train_features, train_labels.reshape(-1,1)),
                                batch_size)
    test_iter = d2l.load_array((test_features, test_labels.reshape(-1,1)),
                               batch_size, is_train=False)
    trainer = torch.optim.SGD(net.parameters(), lr=0.01)     # 默认参数为weight
    animator = d2l.Animator(xlabel='epoch', ylabel='loss', yscale='log',
                            xlim=[1, num_epochs], ylim=[1e-3, 1e2],
                            legend=['train', 'test'])
    for epoch in range(num_epochs):
        d2l.train_epoch_ch3(net, train_iter, loss, trainer)
        if epoch == 0 or (epoch + 1) % 20 == 0:
            animator.add(epoch + 1, (evaluate_loss(net, train_iter, loss),
                                     evaluate_loss(net, test_iter, loss)))
    print('weight:', net[0].weight.data.numpy())


if __name__ == '__main__':
    # 初始化参数
    max_degree = 20  # 多项式的最大阶数
    n_train, n_test = 100, 100  # 训练和测试数据集大小
    true_w = np.zeros(max_degree)  # 分配大量的空间
    true_w[0:4] = np.array([5, 1.2, -3.4, 5.6])
    # 生成数据集
    features = np.random.normal(size=(n_train + n_test, 1))  # 随机生成一个正态分布 200行1列的向量 x
    np.random.shuffle(features)
    poly_features = np.power(features, np.arange(max_degree).reshape(1, -1))  # 计算features中数据的指定幂次
    for i in range(max_degree):
        poly_features[:, i] /= math.gamma(i + 1)  # gamma(n)=(n-1)!
    # labels的维度:(n_train+n_test,)
    labels = np.dot(poly_features, true_w)
    labels += np.random.normal(scale=0.1, size=labels.shape)
    # NumPy ndarray转换为tensor
    true_w, features, poly_features, labels = [torch.tensor(x, dtype=
        torch.float32) for x in [true_w, features, poly_features, labels]]
    print(features[:2], poly_features[:2, :], labels[:2])

    # 从多项式特征中选择前4个维度，即1,x,x^2/2!,x^3/3!  正常拟合
    train(poly_features[:n_train, :4], poly_features[n_train:, :4],
          labels[:n_train], labels[n_train:])
    '''
    # 从多项式特征中选取所有维度  过拟合
    train(poly_features[:n_train, :], poly_features[n_train:, :],
          labels[:n_train], labels[n_train:], num_epochs=1500
    '''
    '''
    # 从多项式特征中选择前2个维度，即1和x   欠拟合
    train(poly_features[:n_train, :2], poly_features[n_train:, :2],
          labels[:n_train], labels[n_train:])
    '''
    d2l.plt.show()

笔记

对应沐神B站课程12_P2

import torch
from torch import nn
from d2l import torch as d2l


def init_params():
    w = torch.normal(0, 1, size=(num_inputs, 1), requires_grad=True)
    b = torch.zeros(1, requires_grad=True)
    return [w, b]

'''
def l2_penalty(w):
    return torch.sum(w.pow(2)) / 2
'''
def l1_penalty(w):
    return torch.sum(torch.abs(w))


def train(lambd):
    w, b = init_params()
    net, loss = lambda X: d2l.linreg(X, w, b), d2l.squared_loss
    num_epochs, lr = 100, 0.003
    animator = d2l.Animator(xlabel='epochs', ylabel='loss', yscale='log',
                            xlim=[5, num_epochs], legend=['train', 'test'])
    for epoch in range(num_epochs):
        for X, y in train_iter:  # 每次拿5行拿4次
            # 增加了L2范数惩罚项，
            # 广播机制使l2_penalty(w)成为一个长度为batch_size的向量
            # print(y.shape)
            l = loss(net(X), y) + lambd * l1_penalty(w)
            l.sum().backward()
            d2l.sgd([w, b], lr, batch_size)
        if (epoch + 1) % 5 == 0:
            animator.add(epoch + 1, (d2l.evaluate_loss(net, train_iter, loss),
                                     d2l.evaluate_loss(net, test_iter, loss)))
    print('w的L2范数是：', torch.norm(w).item())  # 输出w的L2范数  item()输出浮点型

if __name__ == '__main__':
    # 初始化参数
    n_train, n_test, num_inputs, batch_size = 20, 100, 200, 5
    true_w, true_b = torch.ones((num_inputs, 1)) * 0.01, 0.05
    # 构造数据集
    train_data = d2l.synthetic_data(true_w, true_b, n_train)  # 生成真实的X，y
    #print(train_data)
    train_iter = d2l.load_array(train_data, batch_size)  # 从train_data中随机取出5行X，train_iter为迭代器
    print(train_iter)
    test_data = d2l.synthetic_data(true_w, true_b, n_test)
    test_iter = d2l.load_array(test_data, batch_size, is_train=False)
    # 训练
    # train(lambd=0)
    train(lambd=3)
    d2l.plt.show()

笔记

import torch
from torch import nn
from d2l import torch as d2l

def train_concise(wd):
    net = nn.Sequential(nn.Linear(num_inputs, 1))
    for param in net.parameters():
        param.data.normal_()
    # loss = nn.L1Loss(reduction='none')  # l1损失
    loss = nn.MSELoss(reduction='none')  # 均方差损失
    num_epochs, lr = 100, 0.003
    # 偏置参数没有衰减
    trainer = torch.optim.SGD([
        {"params":net[0].weight,'weight_decay': wd},  # 'weight_decay'对应lambd
        {"params":net[0].bias}], lr=lr)
    animator = d2l.Animator(xlabel='epochs', ylabel='loss', yscale='log',
                            xlim=[5, num_epochs], legend=['train', 'test'])
    for epoch in range(num_epochs):
        for X, y in train_iter:
            trainer.zero_grad()
            l = loss(net(X), y)
            l.mean().backward()
            trainer.step()
        if (epoch + 1) % 5 == 0:
            animator.add(epoch + 1,
                         (d2l.evaluate_loss(net, train_iter, loss),
                          d2l.evaluate_loss(net, test_iter, loss)))
    print('w的L2范数：', net[0].weight.norm().item())

if __name__ == '__main__':
    n_train, n_test, num_inputs, batch_size = 20, 100, 200, 5
    true_w, true_b = torch.ones((num_inputs, 1)) * 0.01, 0.05
    train_data = d2l.synthetic_data(true_w, true_b, n_train)
    train_iter = d2l.load_array(train_data, batch_size)
    test_data = d2l.synthetic_data(true_w, true_b, n_test)
    test_iter = d2l.load_array(test_data, batch_size, is_train=False)

    # train_concise(0)
    train_concise(3)
    d2l.plt.show()

对应沐神B站课程13_P2

import torch
from torch import nn
from d2l import torch as d2l


def dropout_layer(X, dropout):   # dropout即概率p
    assert 0 <= dropout <= 1
    # 在本情况中，所有元素都被丢弃
    if dropout == 1:
        return torch.zeros_like(X)
    # 在本情况中，所有元素都被保留
    if dropout == 0:
        return X
    mask = (torch.rand(X.shape) > dropout).float()  # 0到1均匀分布的随机数
    return mask * X / (1.0 - dropout)
'''
X= torch.arange(16, dtype = torch.float32).reshape((2, 8))
print(X)
print(dropout_layer(X, 0.))
print(dropout_layer(X, 0.5))
print(dropout_layer(X, 1.))
'''
class Net(nn.Module):
    def __init__(self, num_inputs, num_outputs, num_hiddens1, num_hiddens2,
                 is_training = True):
        super(Net, self).__init__()
        self.num_inputs = num_inputs
        self.training = is_training
        self.lin1 = nn.Linear(num_inputs, num_hiddens1)   # 定义lin1层的输入num_inputs，输出num_hiddens1，自动生成权重w
        self.lin2 = nn.Linear(num_hiddens1, num_hiddens2)
        self.lin3 = nn.Linear(num_hiddens2, num_outputs)
        self.relu = nn.ReLU()

    def forward(self, X):
        H1 = self.relu(self.lin1(X.reshape((-1, self.num_inputs))))
        # 只有在训练模型时才使用dropout
        if self.training == True:
            # 在第一个全连接层之后添加一个dropout层
            H1 = dropout_layer(H1, dropout1)
        H2 = self.relu(self.lin2(H1))
        if self.training == True:
            # 在第二个全连接层之后添加一个dropout层
            H2 = dropout_layer(H2, dropout2)
        out = self.lin3(H2)
        return out

if __name__ == '__main__':
    num_epochs, lr, batch_size = 10, 0.5, 256
    num_inputs, num_outputs, num_hiddens1, num_hiddens2 = 784, 10, 256, 256
    dropout1, dropout2 = 0.2, 0.5
    net = Net(num_inputs, num_outputs, num_hiddens1, num_hiddens2)
    loss = nn.CrossEntropyLoss(reduction='none')
    train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
    trainer = torch.optim.SGD(net.parameters(), lr=lr)
    d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer)
    d2l.plt.show()

笔记

import torch
from torch import nn
from d2l import torch as d2l


def init_weights(m):
    if type(m) == nn.Linear:
        nn.init.normal_(m.weight, std=0.01)

if __name__ == '__main__':
    num_epochs, lr, batch_size = 10, 0.5, 256
    num_inputs, num_outputs, num_hiddens1, num_hiddens2 = 784, 10, 256, 256
    dropout1, dropout2 = 0.2, 0.5
    net = nn.Sequential(nn.Flatten(),
            nn.Linear(784, 256),
            # 在第一个全连接层之后添加一个激活函数
            nn.ReLU(),
            # 在第一个全连接层之后添加一个dropout层
            nn.Dropout(dropout1),
            nn.Linear(256, 256),
            # 在第二个全连接层之后添加一个激活函数
            nn.ReLU(),
            # 在第二个全连接层之后添加一个dropout层
            nn.Dropout(dropout2),
            nn.Linear(256, 10))
    net.apply(init_weights)
    loss = nn.CrossEntropyLoss(reduction='none')
    train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
    trainer = torch.optim.SGD(net.parameters(), lr=lr)
    d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer)
    d2l.plt.show()