“深度学习”学习日记。与学习有关的技巧--正则化
2023.1.29
在机器学习的过程中，过拟合是一个常见的问题。过拟合指的是只能够拟合训练数据，但不能很好的拟合测试数据；机器学习的目的就是提高泛化能力，即便是没有包括在训练数据里的测试数据，也希望神经网络模型可以正确识别。
关于过拟合现象可能出现的情景在这篇文章：https://blog.csdn.net/m0_72675651/article/details/128671496
对应的，学习抑制过拟合的技巧是非常重要的
一、过拟合：
原因：1，模型拥有大量的参数；2，训练数据很少；
根据教材内容，利用MNIST数据集模拟过拟合现象。基本情况：7层神经网络，每层100个神经元，激活函数为ReLU函数，只用300个训练数据；
实验代码：
from dataset.mnist import load_mnist
import numpy as np
from collections import OrderedDict
import sys
import os
import matplotlib.pyplot as plt
sys.path.append(os.pardir)
def softmax(x):
if x.ndim == 2:
x = x.T
x = x - np.max(x, axis=0)
y = np.exp(x) / np.sum(np.exp(x), axis=0)
return y.T
x = x - np.max(x)
return np.exp(x) / np.sum(np.exp(x))
def sigmoid(x):
return 1 / (1 + np.exp(-x))
class Relu:
def __init__(self):
self.mask = None
def forward(self, x):
self.mask = (x <= 0)
out = x.copy()
out[self.mask] = 0
return out
def backward(self, dout):
dout[self.mask] = 0
dx = dout
return dx
class Sigmoid:
def __init__(self):
self.out = None
def forward(self, x):
out = sigmoid(x)
self.out = out
return out
def backward(self, dout):
dx = dout * (1.0 - self.out) * self.out
return dx
def cross_entropy_error(y, t):
if y.ndim == 1:
t = t.reshape(1, t.size)
y = y.reshape(1, y.size)
if t.size == y.size:
t = t.argmax(axis=1)
batch_size = y.shape[0]
return -np.sum(np.log(y[np.arange(batch_size), t] + 1e-7)) / batch_size
class Affine:
def __init__(self, W, b):
self.W = W
self.b = b
self.x = None
self.original_x_shape = None
# 权重和偏置参数的导数
self.dW = None
self.db = None
def forward(self, x):
# 对应张量
self.original_x_shape = x.shape
x = x.reshape(x.shape[0], -1)
self.x = x
out = np.dot(self.x, self.W) + self.b
return out
def backward(self, dout):
dx = np.dot(dout, self.W.T)
self.dW = np.dot(self.x.T, dout)
self.db = np.sum(dout, axis=0)
dx = dx.reshape(*self.original_x_shape) # 还原输入数据的形状（对应张量）
return dx
class SoftmaxWithLoss:
def __init__(self):
self.loss = None
self.y = None # softmax的输出
self.t = None # 监督数据
def forward(self, x, t):
self.t = t
self.y = softmax(x)
self.loss = cross_entropy_error(self.y, self.t)
return self.loss
def backward(self, dout=1):
batch_size = self.t.shape[0]
if self.t.size == self.y.size: # 监督数据是one-hot-vector的情况
dx = (self.y - self.t) / batch_size
else:
dx = self.y.copy()
dx[np.arange(batch_size), self.t] -= 1
dx = dx / batch_size
return dx
def numerical_gradient(f, x):
h = 1e-4 # 0.0001
grad = np.zeros_like(x)
it = np.nditer(x, flags=['multi_index'], op_flags=['readwrite'])
while not it.finished:
idx = it.multi_index
tmp_val = x[idx]
x[idx] = float(tmp_val) + h
fxh1 = f(x) # f(x+h)
x[idx] = tmp_val - h
fxh2 = f(x) # f(x-h)
grad[idx] = (fxh1 - fxh2) / (2 * h)
x[idx] = tmp_val # 还原值
it.iternext()
return grad
class MultiLayerNet:
"""全连接的多层神经网络
Parameters
----------
input : 输入大小（MNIST的情况下为784）
hidden_list : 隐藏层的神经元数量的列表（e.g. [100, 100, 100]）
output : 输出大小（MNIST的情况下为10）
activation : 'relu' or 'sigmoid'
weight_init_std : 指定权重的标准差（e.g. 0.01）
指定'relu'或'he'的情况下设定“He的初始值”
指定'sigmoid'或'xavier'的情况下设定“Xavier的初始值”
weight_decay_lambda : Weight Decay（L2范数）的强度
"""
def __init__(self, input, hidden_list, output,
activation='relu', weight_init_std='relu', weight_decay_lambda=0): # 权值衰减设置为0
self.input_size = input
self.output_size = output
self.hidden_size_list = hidden_list
self.hidden_layer_num = len(hidden_list)
self.weight_decay_lambda = weight_decay_lambda
self.params = {}
# 初始化权重
self.__init_weight(weight_init_std)
# 生成层
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)])
self.layers['Activation_function' + str(idx)] = activation_layer[activation]()
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()
def __init_weight(self, weight_init_std):
"""设定权重的初始值
Parameters
----------
weight_init_std : 指定权重的标准差（e.g. 0.01）
指定'relu'或'he'的情况下设定“He的初始值”
指定'sigmoid'或'xavier'的情况下设定“Xavier的初始值”
"""
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]) # 使用ReLU的情况下推荐的初始值
elif str(weight_init_std).lower() in ('sigmoid', 'xavier'):
scale = np.sqrt(1.0 / all_size_list[idx - 1]) # 使用sigmoid的情况下推荐的初始值
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):
for layer in self.layers.values():
x = layer.forward(x)
return x
def loss(self, x, t):
"""求损失函数
Parameters
----------
x : 输入数据
t : 监督标签
Returns
-------
损失函数的值
"""
y = self.predict(x)
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):
y = self.predict(x)
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):
"""求梯度（数值微分）
Parameters
----------
x : 输入数据
t : 监督标签
Returns
-------
具有各层的梯度的字典变量
grads['W1']、grads['W2']、...是各层的权重
grads['b1']、grads['b2']、...是各层的偏置
"""
loss_W = lambda W: self.loss(x, t)
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)])
return grads
def gradient(self, x, t):
"""求梯度（误差反向传播法）
Parameters
----------
x : 输入数据
t : 教师标签
Returns
-------
具有各层的梯度的字典变量
grads['W1']、grads['W2']、...是各层的权重
grads['b1']、grads['b2']、...是各层的偏置
"""
# forward
self.loss(x, t)
# backward
dout = 1
dout = self.last_layer.backward(dout)
layers = list(self.layers.values())
layers.reverse()
for layer in layers:
dout = layer.backward(dout)
# 设定
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.layers[
'Affine' + str(idx)].W
grads['b' + str(idx)] = self.layers['Affine' + str(idx)].db
return grads
class SGD:
"""随机梯度下降法（Stochastic Gradient Descent）"""
def __init__(self, lr=0.01):
self.lr = lr
def update(self, params, grads):
for key in params.keys():
params[key] -= self.lr * grads[key]
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True)
# 满足训练数据少的条件
# 为了再现过拟合，减少学习数据
x_train = x_train[:300]
t_train = t_train[:300] # 方便观察测试数据也用300张MINIST图片
network = MultiLayerNet(input=784, hidden_list=[100, 100, 100, 100, 100, 100], output=10,
weight_decay_lambda=0) # 满足模型有大量参数的条件
# 超参数
lr = 0.01
optimizer = SGD(lr)
# 按epoch分别算出所有训练数据和所以测试数据的识别精度
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) # mini_batch 处理
x_batch = x_train[batch_mask]
t_batch = t_train[batch_mask]
grads = network.gradient(x_batch, t_batch)
optimizer.update(network.params, grads) # 更新参数 神经网络的学习
if i % iter_per_epoch == 0:
train_acc = network.accuracy(x_train, t_train) # 计算识别精度
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.绘制图形==========
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()
观察结果：
可以看出模型对测试数据的拟合效果不是很好，出现了过拟合现象；
二，权值衰减：
权值衰减是一种用来抑制过拟合的方法，其作用是通过在学习的过程中对大的权重进行惩罚，来抑制过拟合现象（防止权重值更大产生过拟合现象）；
神经网络的学习的目的是为了减小损失函数的值。这时，将权重的范数加到损失函数的上，这样就可以抑制权重变大。
计算过程：
有权重 
，其平方范数的权值衰减就是 
，然后将这个值，加到损失函数值上 
其中 
是正则化的超参数，其值越大则衰减效果越强。 
用于方便计算反向传播的导数
# weight decay（权值衰减）的设定
# weight_decay_lambda = 0 # 不使用权值衰减的情况 出现过拟合
# weight_decay_lambda = 0.1
# 设定
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.layers['Affine' + str(idx)].W
grads['b' + str(idx)] = self.layers['Affine' + str(idx)].db
return grads
设置 weight_decay_lambda = 0.1 ，带入上一段代码
network = MultiLayerNet(input_size=784, hidden_size_list=[100, 100, 100, 100, 100, 100], output_size=10, weight_decay_lambda=weight_decay_lambda) 实验结果：
在没有使用权值衰减时，训练数据的精度达到了100%，训练数据的精度和测试数据的精度相差很大；使用以后，训练数据的精度并没有达到100%，而且测试数据与训练数据的精度差距也变小。
权值衰减在某种程度上可以“惩罚”权重，去抑制过拟合，但是，当网络模型变得复杂时，就很难对付了。
三，Droput：
Droput是一种在学习过程随机删除神经元的方法。训练时，随机选出隐匿层的神经元，然后将其删除。被删除的神经元不再进行信号传递；
Droput工作方式（来自教材）：
在神经网络的学习阶段，每次传递一次数据，Droput就会随机删除一些神经元，然后，测试是，虽然会传递所有的神经元信号，但是对于各个神经元的输出，要乘以训练时的删除比例在输出。
class Dropout:
def __init__(self, droput_ratio=0.5):
self.droput_ratio = droput_ratio
self.mask = None
def forward(self, x, train_flg=True):
if train_flg:
self.mask = np.random.rand(*x.shape) > self.droput_ratio
return x * self.mask
else:
return x * (1.0 - self.droput_ratio)
def backward(self, dout):
return dout * self.mask
实验代码：
import os
import sys
from collections import OrderedDict
import numpy as np
import matplotlib.pyplot as plt
from dataset.mnist import load_mnist
sys.path.append(os.pardir) # 为了导入父目录的文件而进行的设定
class SGD:
def __init__(self, lr=0.01):
self.lr = lr
def update(self, params, grads):
for key in params.keys():
params[key] -= self.lr * grads[key]
class Momentum:
def __init__(self, lr=0.01, momentum=0.9):
self.lr = lr
self.momentum = momentum
self.v = None
def update(self, params, grads):
if self.v is None:
self.v = {}
for key, val in params.items():
self.v[key] = np.zeros_like(val)
for key in params.keys():
self.v[key] = self.momentum * self.v[key] - self.lr * grads[key]
params[key] += self.v[key]
class Nesterov:
def __init__(self, lr=0.01, momentum=0.9):
self.lr = lr
self.momentum = momentum
self.v = None
def update(self, params, grads):
if self.v is None:
self.v = {}
for key, val in params.items():
self.v[key] = np.zeros_like(val)
for key in params.keys():
self.v[key] *= self.momentum
self.v[key] -= self.lr * grads[key]
params[key] += self.momentum * self.momentum * self.v[key]
params[key] -= (1 + self.momentum) * self.lr * grads[key]
class AdaGrad:
def __init__(self, lr=0.01):
self.lr = lr
self.h = None
def update(self, params, grads):
if self.h is None:
self.h = {}
for key, val in params.items():
self.h[key] = np.zeros_like(val)
for key in params.keys():
self.h[key] += grads[key] * grads[key]
params[key] -= self.lr * grads[key] / (np.sqrt(self.h[key]) + 1e-7)
class RMSprop:
def __init__(self, lr=0.01, decay_rate=0.99):
self.lr = lr
self.decay_rate = decay_rate
self.h = None
def update(self, params, grads):
if self.h is None:
self.h = {}
for key, val in params.items():
self.h[key] = np.zeros_like(val)
for key in params.keys():
self.h[key] *= self.decay_rate
self.h[key] += (1 - self.decay_rate) * grads[key] * grads[key]
params[key] -= self.lr * grads[key] / (np.sqrt(self.h[key]) + 1e-7)
class Adam:
def __init__(self, lr=0.001, beta1=0.9, beta2=0.999):
self.lr = lr
self.beta1 = beta1
self.beta2 = beta2
self.iter = 0
self.m = None
self.v = None
def update(self, params, grads):
if self.m is None:
self.m, self.v = {}, {}
for key, val in params.items():
self.m[key] = np.zeros_like(val)
self.v[key] = np.zeros_like(val)
self.iter += 1
lr_t = self.lr * np.sqrt(1.0 - self.beta2 ** self.iter) / (1.0 - self.beta1 ** self.iter)
for key in params.keys():
self.m[key] += (1 - self.beta1) * (grads[key] - self.m[key])
self.v[key] += (1 - self.beta2) * (grads[key] ** 2 - self.v[key])
params[key] -= lr_t * self.m[key] / (np.sqrt(self.v[key]) + 1e-7)
def softmax(x):
if x.ndim == 2:
x = x.T
x = x - np.max(x, axis=0)
y = np.exp(x) / np.sum(np.exp(x), axis=0)
return y.T
x = x - np.max(x)
return np.exp(x) / np.sum(np.exp(x))
def sigmoid(x):
return 1 / (1 + np.exp(-x))
class Relu:
def __init__(self):
self.mask = None
def forward(self, x):
self.mask = (x <= 0)
out = x.copy()
out[self.mask] = 0
return out
def backward(self, dout):
dout[self.mask] = 0
dx = dout
return dx
class Sigmoid:
def __init__(self):
self.out = None
def forward(self, x):
out = sigmoid(x)
self.out = out
return out
def backward(self, dout):
dx = dout * (1.0 - self.out) * self.out
return dx
def cross_entropy_error(y, t):
if y.ndim == 1:
t = t.reshape(1, t.size)
y = y.reshape(1, y.size)
if t.size == y.size:
t = t.argmax(axis=1)
batch_size = y.shape[0]
return -np.sum(np.log(y[np.arange(batch_size), t] + 1e-7)) / batch_size
class Affine:
def __init__(self, W, b):
self.W = W
self.b = b
self.x = None
self.original_x_shape = None
# 权重和偏置参数的导数
self.dW = None
self.db = None
def forward(self, x):
# 对应张量
self.original_x_shape = x.shape
x = x.reshape(x.shape[0], -1)
self.x = x
out = np.dot(self.x, self.W) + self.b
return out
def backward(self, dout):
dx = np.dot(dout, self.W.T)
self.dW = np.dot(self.x.T, dout)
self.db = np.sum(dout, axis=0)
dx = dx.reshape(*self.original_x_shape) # 还原输入数据的形状（对应张量）
return dx
class SoftmaxWithLoss:
def __init__(self):
self.loss = None
self.y = None # softmax的输出
self.t = None # 监督数据
def forward(self, x, t):
self.t = t
self.y = softmax(x)
self.loss = cross_entropy_error(self.y, self.t)
return self.loss
def backward(self, dout=1):
batch_size = self.t.shape[0]
if self.t.size == self.y.size: # 监督数据是one-hot-vector的情况
dx = (self.y - self.t) / batch_size
else:
dx = self.y.copy()
dx[np.arange(batch_size), self.t] -= 1
dx = dx / batch_size
return dx
def numerical_gradient(f, x):
h = 1e-4 # 0.0001
grad = np.zeros_like(x)
it = np.nditer(x, flags=['multi_index'], op_flags=['readwrite'])
while not it.finished:
idx = it.multi_index
tmp_val = x[idx]
x[idx] = float(tmp_val) + h
fxh1 = f(x) # f(x+h)
x[idx] = tmp_val - h
fxh2 = f(x) # f(x-h)
grad[idx] = (fxh1 - fxh2) / (2 * h)
x[idx] = tmp_val # 还原值
it.iternext()
return grad
class MultiLayerNetExtend:
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 = {}
# 初始化权重
self.__init_weight(weight_init_std)
# 生成层
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()
def __init_weight(self, weight_init_std):
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]) # 使用ReLU的情况下推荐的初始值
elif str(weight_init_std).lower() in ('sigmoid', 'xavier'):
scale = np.sqrt(1.0 / all_size_list[idx - 1]) # 使用sigmoid的情况下推荐的初始值
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):
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):
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):
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)
# 设定
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
class Trainer:
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
# optimzer
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))
class Dropout:
def __init__(self, droput_ratio=0.5):
self.droput_ratio = droput_ratio
self.mask = None
def forward(self, x, train_flg=True):
if train_flg:
self.mask = np.random.rand(*x.shape) > self.droput_ratio
return x * self.mask
else:
return x * (1.0 - self.droput_ratio)
def backward(self, dout):
return dout * self.mask
class BatchNormalization:
def __init__(self, gamma, beta, momentum=0.9, running_mean=None, running_var=None):
self.gamma = gamma
self.beta = beta
self.momentum = momentum
self.input_shape = None # Conv层的情况下为4维，全连接层的情况下为2维
# 测试时使用的平均值和方差
self.running_mean = running_mean
self.running_var = running_var
# backward时使用的中间数据
self.batch_size = None
self.xc = None
self.std = None
self.dgamma = None
self.dbeta = None
def forward(self, x, train_flg=True):
self.input_shape = x.shape
if x.ndim != 2:
N, C, H, W = x.shape
x = x.reshape(N, -1)
out = self.__forward(x, train_flg)
return out.reshape(*self.input_shape)
def __forward(self, x, train_flg):
if self.running_mean is None:
N, D = x.shape
self.running_mean = np.zeros(D)
self.running_var = np.zeros(D)
if train_flg:
mu = x.mean(axis=0)
xc = x - mu
var = np.mean(xc ** 2, axis=0)
std = np.sqrt(var + 10e-7)
xn = xc / std
self.batch_size = x.shape[0]
self.xc = xc
self.xn = xn
self.std = std
self.running_mean = self.momentum * self.running_mean + (1 - self.momentum) * mu
self.running_var = self.momentum * self.running_var + (1 - self.momentum) * var
else:
xc = x - self.running_mean
xn = xc / ((np.sqrt(self.running_var + 10e-7)))
out = self.gamma * xn + self.beta
return out
def backward(self, dout):
if dout.ndim != 2:
N, C, H, W = dout.shape
dout = dout.reshape(N, -1)
dx = self.__backward(dout)
dx = dx.reshape(*self.input_shape)
return dx
def __backward(self, dout):
dbeta = dout.sum(axis=0)
dgamma = np.sum(self.xn * dout, axis=0)
dxn = self.gamma * dout
dxc = dxn / self.std
dstd = -np.sum((dxn * self.xc) / (self.std * self.std), axis=0)
dvar = 0.5 * dstd / self.std
dxc += (2.0 / self.batch_size) * self.xc * dvar
dmu = np.sum(dxc, axis=0)
dx = dxc - dmu / self.batch_size
self.dgamma = dgamma
self.dbeta = dbeta
return dx
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True)
# 为了再现过拟合，减少学习数据
x_train = x_train[:300]
t_train = t_train[:300]
# 设定是否使用Dropuout，以及比例 ========================
use_dropout = True # 不使用Dropout的情况下为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
# 绘制图形==========
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()
观察结果：通过Droput，训练数据和测试数据的识别精度的差距变小了，而且，训练数据也没有达到100%的识别精度，这样的神经网络表现力强也没有出现过拟合现象。
四，集成学习：
所谓集成学习就是将多个模型单独进行学习，推理处理时，在取多个模型的输出平均值。用神经网络的来举例就是，准备n个结构相同的网络，分别进行学习，测试时，以这n个网络的输出的平均值作为最终答案。
（上一个实验代码分别使用SGD，Momentum，AdaGrad，Adom不同的激活函数模拟出不同的结构相似的神经网络模型，为集成学习创造条件）
通过实验，有效的集成学习可以使神经网络的识别精度提高几个百分点。集成学习与Droput结合，通过学习过程中随机删除神经元，从而每一次都让不同的模型学习进行学习。并且在推理处理时，通过对神经元乘以 删除比例（Droput_rate=0.5），可以取得平均值提高精度。
也可以理解为Droput将集成学习的效果模拟地通过一个网络实现了。
MNIST数据集的导入代码：
代码需要在一个命名为命名为dataset的文件夹下命名为mnist，并且与实验代码在同一个文件夹；
# coding: utf-8
try:
import urllib.request
except ImportError:
raise ImportError('You should use Python 3.x')
import os.path
import gzip
import pickle
import os
import numpy as np
url_base = 'http://yann.lecun.com/exdb/mnist/'
key_file = {
'train_img':'train-images-idx3-ubyte.gz',
'train_label':'train-labels-idx1-ubyte.gz',
'test_img':'t10k-images-idx3-ubyte.gz',
'test_label':'t10k-labels-idx1-ubyte.gz'
}
dataset_dir = os.path.dirname(os.path.abspath(__file__))
save_file = dataset_dir + "/mnist.pkl"
train_num = 60000
test_num = 10000
img_dim = (1, 28, 28)
img_size = 784
def _download(file_name):
file_path = dataset_dir + "/" + file_name
if os.path.exists(file_path):
return
print("Downloading " + file_name + " ... ")
urllib.request.urlretrieve(url_base + file_name, file_path)
print("Done")
def download_mnist():
for v in key_file.values():
_download(v)
def _load_label(file_name):
file_path = dataset_dir + "/" + file_name
print("Converting " + file_name + " to NumPy Array ...")
with gzip.open(file_path, 'rb') as f:
labels = np.frombuffer(f.read(), np.uint8, offset=8)
print("Done")
return labels
def _load_img(file_name):
file_path = dataset_dir + "/" + file_name
print("Converting " + file_name + " to NumPy Array ...")
with gzip.open(file_path, 'rb') as f:
data = np.frombuffer(f.read(), np.uint8, offset=16)
data = data.reshape(-1, img_size)
print("Done")
return data
def _convert_numpy():
dataset = {}
dataset['train_img'] = _load_img(key_file['train_img'])
dataset['train_label'] = _load_label(key_file['train_label'])
dataset['test_img'] = _load_img(key_file['test_img'])
dataset['test_label'] = _load_label(key_file['test_label'])
return dataset
def init_mnist():
download_mnist()
dataset = _convert_numpy()
print("Creating pickle file ...")
with open(save_file, 'wb') as f:
pickle.dump(dataset, f, -1)
print("Done!")
def _change_one_hot_label(X):
T = np.zeros((X.size, 10))
for idx, row in enumerate(T):
row[X[idx]] = 1
return T
def load_mnist(normalize=True, flatten=True, one_hot_label=False):
"""读入MNIST数据集
Parameters
----------
normalize : 将图像的像素值正规化为0.0~1.0
one_hot_label :
one_hot_label为True的情况下，标签作为one-hot数组返回
one-hot数组是指[0,0,1,0,0,0,0,0,0,0]这样的数组
flatten : 是否将图像展开为一维数组
Returns
-------
(训练图像, 训练标签), (测试图像, 测试标签)
"""
if not os.path.exists(save_file):
init_mnist()
with open(save_file, 'rb') as f:
dataset = pickle.load(f)
if normalize:
for key in ('train_img', 'test_img'):
dataset[key] = dataset[key].astype(np.float32)
dataset[key] /= 255.0
if one_hot_label:
dataset['train_label'] = _change_one_hot_label(dataset['train_label'])
dataset['test_label'] = _change_one_hot_label(dataset['test_label'])
if not flatten:
for key in ('train_img', 'test_img'):
dataset[key] = dataset[key].reshape(-1, 1, 28, 28)
return (dataset['train_img'], dataset['train_label']), (dataset['test_img'], dataset['test_label'])
if __name__ == '__main__':
init_mnist()