multilayer perceptron
activation function
The activation function (activation function) determines whether the neuron should be activated by calculating the weighted sum and adding the bias. They convert the input signal into the differentiable operation of the output. Most activation functions are non-linear. Since the activation function is the basis of deep learning, some common activation functions are briefly introduced below.
#引入包
%matplotlib inline
import torch
from d2l import torch as d2l
ReLU function
x = torch.arange(-8.0, 8.0, 0.1, requires_grad=True)
y = torch.relu(x)
d2l.plot(x.detach(), y.detach(), 'x', 'relu(x)', figsize=(5, 2.5))
y.backward(torch.ones_like(x), retain_graph=True)
d2l.plot(x.detach(), x.grad, 'x', 'grad of relu', figsize=(5, 2.5))
公式:
pReLU ( x ) = max ( 0 , x ) + α min ( 0 , x ) . \operatorname{pReLU}(x) = \max(0, x) + \alpha \min(0, x).pReLU ( x )=max(0,x)+amin(0,x).
sigmoid function
[ For a domain in R \mathbb{R}input in R
, the sigmoid functiontransforms the input into an output on the interval (0, 1)].
Therefore, sigmoid is often calleda squashing function:
it compresses any input in the range (-inf, inf) to some value in the interval (0, 1):
sigmoid ( x ) = 1 1 + exp ( − x ) . \operatorname{sigmoid}(x) = \frac{1}{1 + \exp(-x)}.sigmoid(x)=1+exp(−x)1.Function
graph:
y = torch.sigmoid(x)
d2l.plot(x.detach(), y.detach(), 'x', 'sigmoid(x)', figsize=(5, 2.5))
The derivative of the sigmoid function is the following formula:
d d x sigmoid ( x ) = exp ( − x ) ( 1 + exp ( − x ) ) 2 = sigmoid ( x ) ( 1 − sigmoid ( x ) ) . \frac{d}{dx} \operatorname{sigmoid}(x) = \frac{\exp(-x)}{(1 + \exp(-x))^2} = \operatorname{sigmoid}(x)\left(1-\operatorname{sigmoid}(x)\right). dxdsigmoid(x)=(1+exp(−x))2exp(−x)=sigmoid(x)(1−sigmoid(x)).
# 清除以前的梯度
x.grad.data.zero_()
y.backward(torch.ones_like(x),retain_graph=True)
d2l.plot(x.detach(), x.grad, 'x', 'grad of sigmoid', figsize=(5, 2.5))
tanh function
Similar to the sigmoid function,
[ the tanh (hyperbolic tangent) function can also compress and convert its input to the interval (-1, 1) ].
The formula of the tanh function is as follows:
tanh ( x ) = 1 − exp ( − 2 x ) 1 + exp ( − 2 x ) . \operatorname{tanh}(x) = \frac{1 - \exp(-2x )}{1 + \exp(-2x)}.tanh ( x )=1+exp(−2x)1−exp(−2x).Function
graph:
y = torch.tanh(x)
d2l.plot(x.detach(), y.detach(), 'x', 'tanh(x)', figsize=(5, 2.5))
The derivative of the tanh function is:
ddx tanh ( x ) = 1 − tanh 2 ( x ) . \frac{d}{dx} \operatorname{tanh}(x) = 1 - \operatorname{tanh}^2(x).dxdtanh ( x )=1−fishy2(x).
Derivative image:
# 清除以前的梯度
x.grad.data.zero_()
y.backward(torch.ones_like(x),retain_graph=True)
d2l.plot(x.detach(), x.grad, 'x', 'grad of tanh', figsize=(5, 2.5))
A Scratch Implementation of a Multilayer Perceptron
#初始化模型参数
num_inputs, num_outputs, num_hiddens = 784, 10, 256
W1 = nn.Parameter(torch.randn(
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]
#激活函数
def relu(X):
a = torch.zeros_like(X)
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)
#损失函数
loss = nn.CrossEntropyLoss(reduction='none')
#训练
num_epochs, lr = 10, 0.1
updater = torch.optim.SGD(params, lr=lr)
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, updater)
#评估
d2l.predict_ch3(net, test_iter)
Simple Implementation of Multilayer Perceptron
import torch
from torch import nn
from d2l import torch as d2l
#模型
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(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)
polynomial regression
import math
import numpy as np
import torch
from torch import nn
from d2l import torch as d2l
#生成数据集
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])
features = np.random.normal(size=(n_train + n_test, 1))
np.random.shuffle(features)
poly_features = np.power(features, np.arange(max_degree).reshape(1, -1))
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]]
features[:2], poly_features[:2, :], labels[:2]
#对模型进行训练和测试
def evaluate_loss(net, data_iter, loss): #@save
"""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=400):
loss = nn.MSELoss(reduction='none')
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))
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((test_features, test_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())
Third-order polynomial function fitting (normal)
# 从多项式特征中选择前4个维度,即1,x,x^2/2!,x^3/3!
train(poly_features[:n_train, :4], poly_features[n_train:, :4],
labels[:n_train], labels[n_train:]
Linear function fitting (underfitting)
# 从多项式特征中选择前2个维度,即1和x
train(poly_features[:n_train, :2], poly_features[n_train:, :2],
labels[:n_train], labels[n_train:])
Higher order polynomial function fitting (overfitting)
# 从多项式特征中选取所有维度
train(poly_features[:n_train, :], poly_features[n_train:, :],
labels[:n_train], labels[n_train:], num_epochs=1500)
weight decay
High-dimensional linear regression implemented from scratch
%matplotlib inline
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, is_train=False)
#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
def l2_penalty(w):
return torch.sum(w.pow(2)) / 2
# 定义训练代码实现
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:
# 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
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())
#忽略正则化直接训练
train(lambd=0)
#使用权重衰减
train(lambd=3)
Concise implementation
def train_concise(wd):
net = nn.Sequential(nn.Linear(num_inputs, 1))
for param in net.parameters():
param.data.normal_()
loss = nn.MSELoss(reduction='none')
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},
{
"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())
train_concise(0)
train_concise(3)
Dropout
Implemented from scratch
import torch
from torch import nn
from d2l import torch as d2l
def dropout_layer(X, dropout):
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()
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.))
#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
net = Net(num_inputs, num_outputs, num_hiddens1, num_hiddens2)
#训练和测试
num_epochs, lr, batch_size = 10, 0.5, 256
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)
Concise implementation
net = nn.Sequential(nn.Flatten(),
nn.Linear(784, 256),
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),
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))
def init_weights(m):
if type(m) == nn.Linear:
nn.init.normal_(m.weight, std=0.01)
net.apply(init_weights);
trainer = torch.optim.SGD(net.parameters(), lr=lr)
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer)