目录
1、过拟合
2、权值衰减
3、Dropout
3.1案例
3.1.1案例结果
3.1.2代码实现如下:
1、trainer.py
2、multi_layer_net_extend.py
3、overfit_dropout.py
该文章是对《深度学习入门 基于Python的理论与实现》的总结,作者是[日]斋藤康毅
机器学习的问题中,过拟合是一个很常见的问题。过拟合指的是只能拟合训练数据,但不能很好地拟合不包含在训练数据中的其他数据的状态。机器学习的目标是提高泛化能力,即便是没有包含在训练数据里的未观测数据,也希望模型可以进行正确的识别。我们可以制作复杂的、表现力强的模型,但是相应地,抑制过拟合的技巧也很重要。
过拟合原因:
• 模型拥有大量参数、表现力强。
• 训练数据少
例:为满足以上两个条件,制造过拟合现象。为此,要从MNIST数据集原本的60000个训练数据中只选定300个,并且,为了增加网络的复杂度,使用7层网络(每层有100个神经元,激活函数为ReLU)。
目录结构如下:
对于(funtions.py, gradient.py, layers.py,multi_layer_net.py optimizer.py, util.py)见前面博文,运行overfit_weight_decay.py结果如下。
【注】由上可知,当weight_decay_lambda=0时,过了100个epoch左右后,用训练数据测量到的识别精度几乎都为100%。但是,对于测试数据,离100%的识别精度还有较大的差距。如此大的识别精度差距,是只拟合了训练数据的结果。从图中可知,模型对训练时
没有使用的一般数据(测试数据)拟合得不是很好。
overfit_weight_decay.py代码实现如下:
# coding: utf-8
import os
import sys
sys.path.append(os.pardir)
import numpy as np
import matplotlib.pyplot as plt
from dataset.mnist import load_mnist
from common.multi_layer_net import MultiLayerNet
from common.optimizer import SGD
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True)
# 为了再现backward时使用的中间数据意思过度学习,削减学习数据
x_train = x_train[:300]
t_train = t_train[:300]
# weight decay (负荷衰减)设定 =======================
weight_decay_lambda = 0 # 不使用weight decay的情况
# weight_decay_lambda = 0.1
# ====================================================
network = MultiLayerNet(input_size=784, hidden_size_list=[100, 100, 100, 100, 100, 100], output_size=10,
weight_decay_lambda=weight_decay_lambda)
optimizer = SGD(lr=0.01)
max_epochs = 201
train_size = x_train.shape[0]
batch_size = 100
train_loss_list = []
train_acc_list = []
test_acc_list = []
iter_per_epoch = max(train_size / batch_size, 1)
epoch_cnt = 0
for i in range(1000000000):
batch_mask = np.random.choice(train_size, batch_size)
x_batch = x_train[batch_mask]
t_batch = t_train[batch_mask]
grads = network.gradient(x_batch, t_batch)
optimizer.update(network.params, grads)
if i % iter_per_epoch == 0:
train_acc = network.accuracy(x_train, t_train)
test_acc = network.accuracy(x_test, t_test)
train_acc_list.append(train_acc)
test_acc_list.append(test_acc)
print("epoch:" + str(epoch_cnt) + ", train acc:" + str(train_acc) + ", test acc:" + str(test_acc))
epoch_cnt += 1
if epoch_cnt >= max_epochs:
break
# 3.绘制图表==========
markers = {'train': 'o', 'test': 's'}
x = np.arange(max_epochs)
plt.plot(x, train_acc_list, marker='o', label='train', markevery=10)
plt.plot(x, test_acc_list, marker='s', label='test', markevery=10)
plt.xlabel("epochs")
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
plt.legend(loc='lower right')
plt.show()
权值衰减是一直以来经常被使用的一种抑制过拟合的方法。该方法通过在学习的过程中对大的权重进行惩罚,来抑制过拟合。很多过拟合原本就是因为权重参数取值过大才发生的。
神经网络的学习目的是减小损失函数的值。这时,例如为损失函数加上权重的平方范数(L2范数)。这样一来,就可以抑制权重变大。用符号表示的话,如果将权重记为W,L2范数的权值衰减就是 ,然后将这个 加到损失函数上。这里,λ是控制正则化强度的超参数。λ
设置得越大,对大的权重施加的惩罚就越重。此外, 开头的 是用于将 的求导结果变成λW的调整用常量。
例:对于上面实现的过拟合实验,此时将权值衰减weight_decay_lambda设置为0.1,得到下面结果。
【注】使用权值衰减虽然训练数据的识别精度和测试数据的识别精度之间有差距,但是与没有使用权值衰减的结果相比,差距变小了。这说明过拟合受到了抑制。此外,还要注意,训练数据的识别精度没有达到100%(1.0)。
作为抑制过拟合的方法,前面我们介绍了为损失函数加上权重的L2范数的权值衰减方法。该方法可以简单地实现,在某种程度上能够抑制过拟合。但是,如果网络的模型变得很复杂,只用权值衰减就难以应对了。在这种情况下,我们经常会使用Dropout方法。
Dropout是一种在学习的过程中随机删除神经元的方法。训练时,随机选出隐藏层的神经元,然后将其删除。被删除的神经元不再进行信号的传递,如下图所示。训练时,每传递一次数据,就会随机选择要删除的神经元。
Dropout代码实现如下:
class Dropout:
def __init__(self, dropout_ratio=0.5):
self.dropout_ratio = dropout_ratio
self.mask = None
def forward(self, x, train_flg=True):
if train_flg:
# 将生成的数组的值大于0.5的设置为True
self.mask = np.random.rand(*x.shape) > self.dropout_ratio
return x * self.mask
else:
return x * (1.0 - self.dropout_ratio)
def backward(self, dout):
return dout * self.mask
【注】每次正向传播时, self.mask 中都会以 False 的形式保存要删除的神经元。 self.mask 会随机生成和 x 形状相同的数组,并将值比
dropout_ratio 大的元素设为 True 。反向传播时的行为和ReLU相同。也就是说,正向传播时传递了信号的神经元,反向传播时按原样传递信号;正向传播时没有传递信号的神经元,反向传播时信号将停在那里。
例:使用MNIST数据集进行验证,以确认Dropout的效果。
目录结构如下:
对于(funtions.py, gradient.py, layers.py, optimizer.py, util.py)见前面博文,运行overfit_dropout.py结果如下。
运行结果如下:
【注】通过使用Dropout,训练数据和测试数据的识别精度的差距变小了。并且,训练数据也没有到达100%的识别精度。像这样,通过使用Dropout,即便是表现力强的网络,也可以抑制过拟合。
# coding: utf-8
import sys, os
sys.path.append(os.pardir) # 用于导入父目录文件
import numpy as np
from common.optimizer import *
class Trainer:
"""神经网络训练
"""
def __init__(self, network, x_train, t_train, x_test, t_test,
epochs=20, mini_batch_size=100,
optimizer='SGD', optimizer_param={'lr':0.01},
evaluate_sample_num_per_epoch=None, verbose=True):
self.network = network
self.verbose = verbose
self.x_train = x_train
self.t_train = t_train
self.x_test = x_test
self.t_test = t_test
self.epochs = epochs
self.batch_size = mini_batch_size
self.evaluate_sample_num_per_epoch = evaluate_sample_num_per_epoch
# optimizer
optimizer_class_dict = {'sgd':SGD, 'momentum':Momentum, 'nesterov':Nesterov,
'adagrad':AdaGrad, 'rmsprpo':RMSprop, 'adam':Adam}
self.optimizer = optimizer_class_dict[optimizer.lower()](**optimizer_param)
self.train_size = x_train.shape[0]
self.iter_per_epoch = max(self.train_size / mini_batch_size, 1)
self.max_iter = int(epochs * self.iter_per_epoch)
self.current_iter = 0
self.current_epoch = 0
self.train_loss_list = []
self.train_acc_list = []
self.test_acc_list = []
def train_step(self):
batch_mask = np.random.choice(self.train_size, self.batch_size)
x_batch = self.x_train[batch_mask]
t_batch = self.t_train[batch_mask]
grads = self.network.gradient(x_batch, t_batch)
self.optimizer.update(self.network.params, grads)
loss = self.network.loss(x_batch, t_batch)
self.train_loss_list.append(loss)
if self.verbose: print("train loss:" + str(loss))
if self.current_iter % self.iter_per_epoch == 0:
self.current_epoch += 1
x_train_sample, t_train_sample = self.x_train, self.t_train
x_test_sample, t_test_sample = self.x_test, self.t_test
if not self.evaluate_sample_num_per_epoch is None:
t = self.evaluate_sample_num_per_epoch
x_train_sample, t_train_sample = self.x_train[:t], self.t_train[:t]
x_test_sample, t_test_sample = self.x_test[:t], self.t_test[:t]
train_acc = self.network.accuracy(x_train_sample, t_train_sample)
test_acc = self.network.accuracy(x_test_sample, t_test_sample)
self.train_acc_list.append(train_acc)
self.test_acc_list.append(test_acc)
if self.verbose: print("=== epoch:" + str(self.current_epoch) + ", train acc:" + str(train_acc) + ", test acc:" + str(test_acc) + " ===")
self.current_iter += 1
def train(self):
for i in range(self.max_iter):
self.train_step()
test_acc = self.network.accuracy(self.x_test, self.t_test)
if self.verbose:
print("=============== Final Test Accuracy ===============")
print("test acc:" + str(test_acc))
# coding: utf-8
import sys, os
sys.path.append(os.pardir)
import numpy as np
from collections import OrderedDict
from common.layers import *
from common.gradient import numerical_gradient
class MultiLayerNetExtend:
"""
Weiht Decay、Dropout、Batch Normalization
Parameters
----------
input_size : 784
hidden_size_list : ( [100, 100, 100])
output_size : 10
activation : 'relu' or 'sigmoid'
weight_init_std : 0.01
'relu': he初始值
'sigmoid':Xavier初始值
weight_decay_lambda : Weight Decay(
use_dropout: Dropout
dropout_ration : Dropout
use_batchNorm: Batch Normalization
"""
def __init__(self, input_size, hidden_size_list, output_size,
activation='relu', weight_init_std='relu', weight_decay_lambda=0,
use_dropout = False, dropout_ration = 0.5, use_batchnorm=False):
self.input_size = input_size
self.output_size = output_size
self.hidden_size_list = hidden_size_list
self.hidden_layer_num = len(hidden_size_list)
self.use_dropout = use_dropout
self.weight_decay_lambda = weight_decay_lambda
self.use_batchnorm = use_batchnorm
self.params = {}
# 权重初始化
self.__init_weight(weight_init_std)
# 激活函数层
activation_layer = {'sigmoid': Sigmoid, 'relu': Relu}
self.layers = OrderedDict()
for idx in range(1, self.hidden_layer_num+1):
self.layers['Affine' + str(idx)] = Affine(self.params['W' + str(idx)],
self.params['b' + str(idx)])
if self.use_batchnorm:
self.params['gamma' + str(idx)] = np.ones(hidden_size_list[idx-1])
self.params['beta' + str(idx)] = np.zeros(hidden_size_list[idx-1])
self.layers['BatchNorm' + str(idx)] = BatchNormalization(self.params['gamma' + str(idx)], self.params['beta' + str(idx)])
self.layers['Activation_function' + str(idx)] = activation_layer[activation]()
if self.use_dropout:
self.layers['Dropout' + str(idx)] = Dropout(dropout_ration)
idx = self.hidden_layer_num + 1
self.layers['Affine' + str(idx)] = Affine(self.params['W' + str(idx)], self.params['b' + str(idx)])
self.last_layer = SoftmaxWithLoss()
# 初始化权重
def __init_weight(self, weight_init_std):
"""
Parameters
----------
weight_init_std : 标准差为0.01
'relu':He初始值
'sigmoid':Xavier初始值
"""
all_size_list = [self.input_size] + self.hidden_size_list + [self.output_size]
for idx in range(1, len(all_size_list)):
scale = weight_init_std
if str(weight_init_std).lower() in ('relu', 'he'):
scale = np.sqrt(2.0 / all_size_list[idx - 1]) # ReLU初始值
elif str(weight_init_std).lower() in ('sigmoid', 'xavier'):
scale = np.sqrt(1.0 / all_size_list[idx - 1]) # sigmoid初始值
self.params['W' + str(idx)] = scale * np.random.randn(all_size_list[idx-1], all_size_list[idx])
self.params['b' + str(idx)] = np.zeros(all_size_list[idx])
def predict(self, x, train_flg=False):
for key, layer in self.layers.items():
if "Dropout" in key or "BatchNorm" in key:
x = layer.forward(x, train_flg)
else:
x = layer.forward(x)
return x
def loss(self, x, t, train_flg=False):
"""损失函数
"""
y = self.predict(x, train_flg)
weight_decay = 0
for idx in range(1, self.hidden_layer_num + 2):
W = self.params['W' + str(idx)]
weight_decay += 0.5 * self.weight_decay_lambda * np.sum(W**2)
return self.last_layer.forward(y, t) + weight_decay
def accuracy(self, X, T):
"""
计算精度
:param X:
:param T:
:return:
"""
Y = self.predict(X, train_flg=False)
Y = np.argmax(Y, axis=1)
if T.ndim != 1:
T = np.argmax(T, axis=1)
accuracy = np.sum(Y == T) / float(X.shape[0])
return accuracy
def numerical_gradient(self, X, T):
"""计算梯度(数值微分)
Parameters
----------
X : 训练集
T : 训练标签
Returns
-------
每层的参数的梯度
grads['W1']、grads['W2']、...各层权重梯度值
grads['b1']、grads['b2']、...各层偏置梯度值
"""
loss_W = lambda W: self.loss(X, T, train_flg=True)
grads = {}
for idx in range(1, self.hidden_layer_num+2):
grads['W' + str(idx)] = numerical_gradient(loss_W, self.params['W' + str(idx)])
grads['b' + str(idx)] = numerical_gradient(loss_W, self.params['b' + str(idx)])
if self.use_batchnorm and idx != self.hidden_layer_num+1:
grads['gamma' + str(idx)] = numerical_gradient(loss_W, self.params['gamma' + str(idx)])
grads['beta' + str(idx)] = numerical_gradient(loss_W, self.params['beta' + str(idx)])
return grads
def gradient(self, x, t):
# forward
self.loss(x, t, train_flg=True)
# backward
dout = 1
dout = self.last_layer.backward(dout)
layers = list(self.layers.values())
layers.reverse()
for layer in layers:
dout = layer.backward(dout)
#
grads = {}
for idx in range(1, self.hidden_layer_num+2):
grads['W' + str(idx)] = self.layers['Affine' + str(idx)].dW + self.weight_decay_lambda * self.params['W' + str(idx)]
grads['b' + str(idx)] = self.layers['Affine' + str(idx)].db
if self.use_batchnorm and idx != self.hidden_layer_num+1:
grads['gamma' + str(idx)] = self.layers['BatchNorm' + str(idx)].dgamma
grads['beta' + str(idx)] = self.layers['BatchNorm' + str(idx)].dbeta
return grads
# coding: utf-8
import os
import sys
sys.path.append(os.pardir) # 导入父目录文件
import numpy as np
import matplotlib.pyplot as plt
from dataset.mnist import load_mnist
from common.multi_layer_net_extend import MultiLayerNetExtend
from common.trainer import Trainer
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True)
# 为了再现过度学习,削减学习数据
x_train = x_train[:300]
t_train = t_train[:300]
# 有无Dropuout、配置比例 ========================
use_dropout = True # 没有Dropout的情况False
dropout_ratio = 0.2
# ====================================================
network = MultiLayerNetExtend(input_size=784, hidden_size_list=[100, 100, 100, 100, 100, 100],
output_size=10, use_dropout=use_dropout, dropout_ration=dropout_ratio)
trainer = Trainer(network, x_train, t_train, x_test, t_test,
epochs=301, mini_batch_size=100,
optimizer='sgd', optimizer_param={'lr': 0.01}, verbose=True)
trainer.train()
train_acc_list, test_acc_list = trainer.train_acc_list, trainer.test_acc_list
# 绘制图表==========
markers = {'train': 'o', 'test': 's'}
x = np.arange(len(train_acc_list))
plt.plot(x, train_acc_list, marker='o', label='train', markevery=10)
plt.plot(x, test_acc_list, marker='s', label='test', markevery=10)
plt.xlabel("epochs")
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
plt.legend(loc='lower right')
plt.show()