Pytorch基础（三）

多层感知机的简洁实现

# -*- coding: utf-8 -*-

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

net = nn.Sequential(nn.Flatten(),
                    nn.Linear(784, 256),
                    nn.ReLU(),
                    nn.Linear(256, 10))
def init_weights(m):
    if type(m) == nn.Linear:
        nn.init.normal_(m.weight, std=0.01)
        
net.apply(init_weights)

batch_size, lr, num_epochs = 256, 0.1, 10
loss = nn.CrossEntropyLoss()
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)       

Out:

多项式拟合

# -*- coding: utf-8 -*-
import torch
import numpy as np
import math
from torch import nn
from d2l import torch as d2l

#多项式的最大阶数
max_degree = 20
#训练集和测试集大小
n_train, n_test = 100,100
true_w = np.zeros(max_degree)
true_w[:4] = np.array([5, 1.2, -3.4, 5.6])

features = np.random.normal(size=(n_train+n_test, 1))
np.random.shuffle(features)
#poly_features的shape为(200, 20)
poly_features = np.power(features, np.arange(max_degree).reshape(1, -1))
#gamma(n)=(n-1)!
for i in range(max_degree):
    poly_features[:, i] /= math.gamma(i + 1)
#labels的shape为(200,)
labels = np.dot(poly_features, true_w)
labels += np.random.normal(scale=0.1, size=labels.shape)

#ndarry转换为tensor
true_w, features, poly_features, labels = [torch.tensor(x, dtype=d2l.float32) for x in [true_w, features, poly_features, labels]]

#评估损失
def evaluate_loss(net, data_iter, loss):
    metric = d2l.Accumulator(2)
    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]

#定义训练函数
def train(train_features, test_features, train_labels, test_labels, num_epochs=400):
    loss = nn.MSELoss()
    input_shape = train_features.shape[-1]
    #不设置偏置
    net = nn.Sequential(nn.Linear(input_shape, 1, bias=False))
    batch_size = min(10, train_labels.shape[0])
    train_iter = d2l.load_array((train_features, train_labels.reshape(-1,1)), batch_size)
    test_iter = d2l.load_array((train_features, train_labels.reshape(-1,1)), batch_size, is_train=False)
    trainer = torch.optim.SGD(net.parameters(), lr=0.01)
    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())

#从多项式特征中选择前4个维度
train(poly_features[:n_train, :4], poly_features[n_train:, :4],
      labels[:n_train], labels[n_train:])

Out:

高维线性回归

# -*- coding: utf-8 -*-

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

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)

#初始化模型参数
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]

#定义L2范数惩罚项
def l2_penalty(w):
    return torch.sum(w.pow(2))/2

#定义训练
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:
            with torch.enable_grad():
                l = loss(net(X),y) + lambd * l2_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())

#lambd=0
train(lambd=0)

Out:

w的L2范数是： 14.963050842285156

高维线性回归的简洁实现

# -*- coding: utf-8 -*-
import torch
from torch import nn
from d2l import torch as d2l

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)

def train_concise(wd):
    net = nn.Sequential(nn.Linear(num_inputs, 1))
    for param in net.parameters():
        param.data.normal_()
    loss = nn.MSELoss()
    num_epochs, lr = 100, 0.003
    trainer = torch.optim.SGD(
        [{"params":net[0].weight, "weight_decay":wd},
        {"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:
            with torch.enable_grad():
                trainer.zero_grad()
                l = loss(net(X), y)
            l.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())

train_concise(0)

Out:

w的L2范数： 12.891228675842285

dropout层

# -*- coding: utf-8 -*-

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

def dropout_layer(X, dropout):
    assert 0 <= dropout <= 1
    if dropout == 1:
        return torch.zeros_like(X)
    if dropout == 0:
        return X
    mask = (torch.rand(X.shape) > dropout).float()
    return mask * X / (1.0-dropout)

#定义模型参数
num_inputs, num_outputs, num_hiddens1, num_hiddens2 = 784, 10, 256, 256

#定义模型
dropout1, dropout2 = 0.2, 0.5
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)
        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
            
net = Net(num_inputs, num_outputs, num_hiddens1, num_hiddens2)

#训练和测试
num_epochs, lr, batch_size = 10, 0.5, 10
loss = nn.CrossEntropyLoss()
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)