1、线性回归
1.1 损失函数
在模型训练中,我们需要衡量价格预测值与真实值之间的误差。通常我们会选取一个非负数作为误差,且数值越小表示误差越小。一个常用的选择是平方函数。 它在评估索引为 i 的样本误差的表达式为
ℓ
(
i
)
(
w
1
,
w
2
,
b
)
=
1
2
(
y
^
(
i
)
−
y
(
i
)
)
2
,
\ell^{(i)}(w_1, w_2, b) = \frac{1}{2} \left(\hat{y}^{(i)} - y^{(i)}\right)^2,
ℓ(i)(w1,w2,b)=21(y^(i)−y(i))2,
用训练数据集中所有样本误差的平均来衡量模型预测的质量
ℓ
(
w
1
,
w
2
,
b
)
=
1
n
∑
i
=
1
n
ℓ
(
i
)
(
w
1
,
w
2
,
b
)
=
1
n
∑
i
=
1
n
1
2
(
x
1
(
i
)
w
1
+
x
2
(
i
)
w
2
+
b
−
y
(
i
)
)
2
.
\ell(w_1, w_2, b) =\frac{1}{n} \sum_{i=1}^n \ell^{(i)}(w_1, w_2, b) =\frac{1}{n} \sum_{i=1}^n \frac{1}{2}\left(x_1^{(i)} w_1 + x_2^{(i)} w_2 + b - y^{(i)}\right)^2.
ℓ(w1,w2,b)=n1i=1∑nℓ(i)(w1,w2,b)=n1i=1∑n21(x1(i)w1+x2(i)w2+b−y(i))2.
求出参数来最小化损失函数:
w
1
∗
,
w
2
∗
,
b
∗
=
*
a
r
g
m
i
n
w
1
,
w
2
,
b
ℓ
(
w
1
,
w
2
,
b
)
.
w_1^*, w_2^*, b^* = \operatorname*{argmin}_{w_1, w_2, b}\ \ell(w_1, w_2, b).
w1∗,w2∗,b∗=*argminw1,w2,b ℓ(w1,w2,b).
1.2 线性回归简洁实现
import torch
from torch import nn
import numpy as np
torch.manual_seed(1)
print(torch.__version__)
torch.set_default_tensor_type('torch.FloatTensor')
生成数据集
num_inputs = 2
num_examples = 1000
true_w = [2, -3.4]
true_b = 4.2
features = torch.tensor(np.random.normal(0, 1, (num_examples, num_inputs)), dtype=torch.float)
labels = true_w[0] * features[:, 0] + true_w[1] * features[:, 1] + true_b
labels += torch.tensor(np.random.normal(0, 0.01, size=labels.size()), dtype=torch.float)
读取数据集
import torch.utils.data as Data
batch_size = 10
# combine featues and labels of dataset
dataset = Data.TensorDataset(features, labels)
# put dataset into DataLoader
data_iter = Data.DataLoader(
dataset=dataset, # torch TensorDataset format
batch_size=batch_size, # mini batch size
shuffle=True, # whether shuffle the data or not
num_workers=2, # read data in multithreading
)
for X, y in data_iter:
print(X, '\n', y)
break
定义模型
class LinearNet(nn.Module):
def __init__(self, n_feature):
super(LinearNet, self).__init__() # call father function to init
self.linear = nn.Linear(n_feature, 1) # function prototype: `torch.nn.Linear(in_features, out_features, bias=True)`
def forward(self, x):
y = self.linear(x)
return y
net = LinearNet(num_inputs)
print(net)
ways to init a multilayer network
# method one
net = nn.Sequential(
nn.Linear(num_inputs, 1)
# other layers can be added here
)
# method two
net = nn.Sequential()
net.add_module('linear', nn.Linear(num_inputs, 1))
# net.add_module ......
# method three
from collections import OrderedDict
net = nn.Sequential(OrderedDict([
('linear', nn.Linear(num_inputs, 1))
# ......
]))
print(net)
print(net[0])
模型初始化
from torch.nn import init
init.normal_(net[0].weight, mean=0.0, std=0.01)
init.constant_(net[0].bias, val=0.0) # or you can use `net[0].bias.data.fill_(0)` to modify it directly
for param in net.parameters():
print(param)
定义损失函数
loss = nn.MSELoss() # nn built-in squared loss function
# function prototype: `torch.nn.MSELoss(size_average=None, reduce=None, reduction='mean')`
定义优化函数
import torch.optim as optim
optimizer = optim.SGD(net.parameters(), lr=0.03) # built-in random gradient descent function
print(optimizer) # function prototype: `torch.optim.SGD(params, lr=, momentum=0, dampening=0, weight_decay=0, nesterov=False)`
训练
num_epochs = 3
for epoch in range(1, num_epochs + 1):
for X, y in data_iter:
output = net(X)
l = loss(output, y.view(-1, 1))
optimizer.zero_grad() # reset gradient, equal to net.zero_grad()
l.backward()
optimizer.step()
print('epoch %d, loss: %f' % (epoch, l.item()))
# result comparision
dense = net[0]
print(true_w, dense.weight.data)
print(true_b, dense.bias.data)
2. softmax和分类模型
import torch
import torchvision
import numpy as np
import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l
print(torch.__version__)
print(torchvision.__version__)
获取数据
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
模型参数初始化
num_inputs = 784
print(28*28)
num_outputs = 10
W = torch.tensor(np.random.normal(0, 0.01, (num_inputs, num_outputs)), dtype=torch.float)
b = torch.zeros(num_outputs, dtype=torch.float)
W.requires_grad_(requires_grad=True)
b.requires_grad_(requires_grad=True)
定义softmax操作
def softmax(X):
X_exp = X.exp()
partition = X_exp.sum(dim=1, keepdim=True)
# print("X size is ", X_exp.size())
# print("partition size is ", partition, partition.size())
return X_exp / partition # 这里应用了广播机制
回归模型
def net(X):
return softmax(torch.mm(X.view((-1, num_inputs)), W) + b)
损失函数
def cross_entropy(y_hat, y):
return - torch.log(y_hat.gather(1, y.view(-1, 1)))
准确率
def accuracy(y_hat, y):
return (y_hat.argmax(dim=1) == y).float().mean().item()
训练模型
num_epochs, lr = 5, 0.1
# 本函数已保存在d2lzh_pytorch包中方便以后使用
def train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size,
params=None, lr=None, optimizer=None):
for epoch in range(num_epochs):
train_l_sum, train_acc_sum, n = 0.0, 0.0, 0
for X, y in train_iter:
y_hat = net(X)
l = loss(y_hat, y).sum()
# 梯度清零
if optimizer is not None:
optimizer.zero_grad()
elif params is not None and params[0].grad is not None:
for param in params:
param.grad.data.zero_()
l.backward()
if optimizer is None:
d2l.sgd(params, lr, batch_size)
else:
optimizer.step()
train_l_sum += l.item()
train_acc_sum += (y_hat.argmax(dim=1) == y).sum().item()
n += y.shape[0]
test_acc = evaluate_accuracy(test_iter, net)
print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f'
% (epoch + 1, train_l_sum / n, train_acc_sum / n, test_acc))
train_ch3(net, train_iter, test_iter, cross_entropy, num_epochs, batch_size, [W, b], lr)
模型预测
X, y = iter(test_iter).next()
true_labels = d2l.get_fashion_mnist_labels(y.numpy())
pred_labels = d2l.get_fashion_mnist_labels(net(X).argmax(dim=1).numpy())
titles = [true + '\n' + pred for true, pred in zip(true_labels, pred_labels)]
d2l.show_fashion_mnist(X[0:9], titles[0:9])
3. 多层感知机
import torch
import numpy as np
import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l
print(torch.__version__)
获取训练集
import torch
import numpy as np
import sys
sys.path.append("/home/kesci/input")
import d2lzh1981 as d2l
print(torch.__version__)
定义模型参数
num_inputs, num_outputs, num_hiddens = 784, 10, 256
W1 = torch.tensor(np.random.normal(0, 0.01, (num_inputs, num_hiddens)), dtype=torch.float)
b1 = torch.zeros(num_hiddens, dtype=torch.float)
W2 = torch.tensor(np.random.normal(0, 0.01, (num_hiddens, num_outputs)), dtype=torch.float)
b2 = torch.zeros(num_outputs, dtype=torch.float)
params = [W1, b1, W2, b2]
for param in params:
param.requires_grad_(requires_grad=True)
激活函数
def relu(X):
return torch.max(input=X, other=torch.tensor(0.0))
定义网络和损失函数
def net(X):
X = X.view((-1, num_inputs))
H = relu(torch.matmul(X, W1) + b1)
return torch.matmul(H, W2) + b2
loss = torch.nn.CrossEntropyLoss()
训练
num_epochs, lr = 5, 100.0
# def train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size,
# params=None, lr=None, optimizer=None):
# for epoch in range(num_epochs):
# train_l_sum, train_acc_sum, n = 0.0, 0.0, 0
# for X, y in train_iter:
# y_hat = net(X)
# l = loss(y_hat, y).sum()
#
# # 梯度清零
# if optimizer is not None:
# optimizer.zero_grad()
# elif params is not None and params[0].grad is not None:
# for param in params:
# param.grad.data.zero_()
#
# l.backward()
# if optimizer is None:
# d2l.sgd(params, lr, batch_size)
# else:
# optimizer.step() # “softmax回归的简洁实现”一节将用到
#
#
# train_l_sum += l.item()
# train_acc_sum += (y_hat.argmax(dim=1) == y).sum().item()
# n += y.shape[0]
# test_acc = evaluate_accuracy(test_iter, net)
# print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f'
# % (epoch + 1, train_l_sum / n, train_acc_sum / n, test_acc))
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, params, lr)
4. 文本预处理
文本是一类序列数据,一篇文章可以看作是字符或单词的序列,本节将介绍文本数据的常见预处理步骤,预处理通常包括四个步骤:
- 读入文本
- 分词
- 建立字典,将每个词映射到一个唯一的索引(index)
- 将文本从词的序列转换为索引的序列,方便输入模型
5. 语言模型之时序数据的采样
5.1 随机采样
import torch
import random
def data_iter_random(corpus_indices, batch_size, num_steps, device=None):
# 减1是因为对于长度为n的序列,X最多只有包含其中的前n - 1个字符
num_examples = (len(corpus_indices) - 1) // num_steps # 下取整,得到不重叠情况下的样本个数
example_indices = [i * num_steps for i in range(num_examples)] # 每个样本的第一个字符在corpus_indices中的下标
random.shuffle(example_indices)
def _data(i):
# 返回从i开始的长为num_steps的序列
return corpus_indices[i: i + num_steps]
if device is None:
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
for i in range(0, num_examples, batch_size):
# 每次选出batch_size个随机样本
batch_indices = example_indices[i: i + batch_size] # 当前batch的各个样本的首字符的下标
X = [_data(j) for j in batch_indices]
Y = [_data(j + 1) for j in batch_indices]
yield torch.tensor(X, device=device), torch.tensor(Y, device=device)
5.2 相邻采样
import torch
import random
def data_iter_random(corpus_indices, batch_size, num_steps, device=None):
# 减1是因为对于长度为n的序列,X最多只有包含其中的前n - 1个字符
num_examples = (len(corpus_indices) - 1) // num_steps # 下取整,得到不重叠情况下的样本个数
example_indices = [i * num_steps for i in range(num_examples)] # 每个样本的第一个字符在corpus_indices中的下标
random.shuffle(example_indices)
def _data(i):
# 返回从i开始的长为num_steps的序列
return corpus_indices[i: i + num_steps]
if device is None:
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
for i in range(0, num_examples, batch_size):
# 每次选出batch_size个随机样本
batch_indices = example_indices[i: i + batch_size] # 当前batch的各个样本的首字符的下标
X = [_data(j) for j in batch_indices]
Y = [_data(j + 1) for j in batch_indices]
yield torch.tensor(X, device=device), torch.tensor(Y, device=device)
6. 循环神经网络从零开始
import torch
import torch.nn as nn
import time
import math
import sys
sys.path.append("/home/kesci/input")
import d2l_jay9460 as d2l
(corpus_indices, char_to_idx, idx_to_char, vocab_size) = d2l.load_data_jay_lyrics()
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
one-hot 向量
我们需要将字符表示成向量,这里采用one-hot向量。假设词典大小是 N ,每次字符对应一个从 0 到 N−1 的唯一的索引,则该字符的向量是一个长度为 N 的向量,若字符的索引是 i ,则该向量的第 i 个位置为 1 ,其他位置为 0 。下面分别展示了索引为0和2的one-hot向量,向量长度等于词典大小。
def one_hot(x, n_class, dtype=torch.float32):
result = torch.zeros(x.shape[0], n_class, dtype=dtype, device=x.device) # shape: (n, n_class)
result.scatter_(1, x.long().view(-1, 1), 1) # result[i, x[i, 0]] = 1
return result
x = torch.tensor([0, 2])
x_one_hot = one_hot(x, vocab_size)
print(x_one_hot)
print(x_one_hot.shape)
print(x_one_hot.sum(axis=1))
def to_onehot(X, n_class):
return [one_hot(X[:, i], n_class) for i in range(X.shape[1])]
X = torch.arange(10).view(2, 5)
inputs = to_onehot(X, vocab_size)
print(len(inputs), inputs[0].shape)
初始化参数
num_inputs, num_hiddens, num_outputs = vocab_size, 256, vocab_size
# num_inputs: d
# num_hiddens: h, 隐藏单元的个数是超参数
# num_outputs: q
def get_params():
def _one(shape):
param = torch.zeros(shape, device=device, dtype=torch.float32)
nn.init.normal_(param, 0, 0.01)
return torch.nn.Parameter(param)
# 隐藏层参数
W_xh = _one((num_inputs, num_hiddens))
W_hh = _one((num_hiddens, num_hiddens))
b_h = torch.nn.Parameter(torch.zeros(num_hiddens, device=device))
# 输出层参数
W_hq = _one((num_hiddens, num_outputs))
b_q = torch.nn.Parameter(torch.zeros(num_outputs, device=device))
return (W_xh, W_hh, b_h, W_hq, b_q)
定义模型
def rnn(inputs, state, params):
# inputs和outputs皆为num_steps个形状为(batch_size, vocab_size)的矩阵
W_xh, W_hh, b_h, W_hq, b_q = params
H, = state
outputs = []
for X in inputs:
H = torch.tanh(torch.matmul(X, W_xh) + torch.matmul(H, W_hh) + b_h)
Y = torch.matmul(H, W_hq) + b_q
outputs.append(Y)
return outputs, (H,)
def init_rnn_state(batch_size, num_hiddens, device):
return (torch.zeros((batch_size, num_hiddens), device=device), )
裁剪梯度
def grad_clipping(params, theta, device):
norm = torch.tensor([0.0], device=device)
for param in params:
norm += (param.grad.data ** 2).sum()
norm = norm.sqrt().item()
if norm > theta:
for param in params:
param.grad.data *= (theta / norm)
预测函数
def predict_rnn(prefix, num_chars, rnn, params, init_rnn_state,
num_hiddens, vocab_size, device, idx_to_char, char_to_idx):
state = init_rnn_state(1, num_hiddens, device)
output = [char_to_idx[prefix[0]]] # output记录prefix加上预测的num_chars个字符
for t in range(num_chars + len(prefix) - 1):
# 将上一时间步的输出作为当前时间步的输入
X = to_onehot(torch.tensor([[output[-1]]], device=device), vocab_size)
# 计算输出和更新隐藏状态
(Y, state) = rnn(X, state, params)
# 下一个时间步的输入是prefix里的字符或者当前的最佳预测字符
if t < len(prefix) - 1:
output.append(char_to_idx[prefix[t + 1]])
else:
output.append(Y[0].argmax(dim=1).item())
return ''.join([idx_to_char[i] for i in output])
困惑度
def train_and_predict_rnn(rnn, get_params, init_rnn_state, num_hiddens,
vocab_size, device, corpus_indices, idx_to_char,
char_to_idx, is_random_iter, num_epochs, num_steps,
lr, clipping_theta, batch_size, pred_period,
pred_len, prefixes):
if is_random_iter:
data_iter_fn = d2l.data_iter_random
else:
data_iter_fn = d2l.data_iter_consecutive
params = get_params()
loss = nn.CrossEntropyLoss()
for epoch in range(num_epochs):
if not is_random_iter: # 如使用相邻采样,在epoch开始时初始化隐藏状态
state = init_rnn_state(batch_size, num_hiddens, device)
l_sum, n, start = 0.0, 0, time.time()
data_iter = data_iter_fn(corpus_indices, batch_size, num_steps, device)
for X, Y in data_iter:
if is_random_iter: # 如使用随机采样,在每个小批量更新前初始化隐藏状态
state = init_rnn_state(batch_size, num_hiddens, device)
else: # 否则需要使用detach函数从计算图分离隐藏状态
for s in state:
s.detach_()
# inputs是num_steps个形状为(batch_size, vocab_size)的矩阵
inputs = to_onehot(X, vocab_size)
# outputs有num_steps个形状为(batch_size, vocab_size)的矩阵
(outputs, state) = rnn(inputs, state, params)
# 拼接之后形状为(num_steps * batch_size, vocab_size)
outputs = torch.cat(outputs, dim=0)
# Y的形状是(batch_size, num_steps),转置后再变成形状为
# (num_steps * batch_size,)的向量,这样跟输出的行一一对应
y = torch.flatten(Y.T)
# 使用交叉熵损失计算平均分类误差
l = loss(outputs, y.long())
# 梯度清0
if params[0].grad is not None:
for param in params:
param.grad.data.zero_()
l.backward()
grad_clipping(params, clipping_theta, device) # 裁剪梯度
d2l.sgd(params, lr, 1) # 因为误差已经取过均值,梯度不用再做平均
l_sum += l.item() * y.shape[0]
n += y.shape[0]
if (epoch + 1) % pred_period == 0:
print('epoch %d, perplexity %f, time %.2f sec' % (
epoch + 1, math.exp(l_sum / n), time.time() - start))
for prefix in prefixes:
print(' -', predict_rnn(prefix, pred_len, rnn, params, init_rnn_state,
num_hiddens, vocab_size, device, idx_to_char, char_to_idx))