第五章.与学习相关技巧
5.4 正则化&超参数
在机器学习中，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，但不能很好的拟合不包含在训练数据中的其他数据状态。
1.发生过拟合的原因
- 模型拥有大量参数，表现力强。
- 训练数据少。
2.抑制过拟合的方法
1).权值衰减
-
通过在学习过程中对大的权重进行惩罚，来抑制过拟合。[很多过拟合发生原因是因为权重参数取值过大才发生的]
-
原理：
为损失函数加上权重的平方范数(L2范数)，用符号表示：
①.如果将权重记为W，L2范数的权值衰减就是 1/2λW2,然后将 1/2λW2加到损失函数上。[λ：控制正则化强度的超参数]
②.L2范数：各元素的平方和；L1范数：各元素的绝对值之和；L∞：各元素的绝对值中最大的哪一个。
-
对于所有权重，权值衰减方法都会为损失函数加上1/2λW2，因此在求权值梯度时，要在误差反向传播法的结果加上正则化项的导数λW。
-
示例：
过拟合现象应用权值衰减方法后的示意图：
-
代码实现：
import sys, os
sys.path.append(os.pardir)
import numpy as np
import matplotlib.pyplot as plt
from dataset.mnist import load_mnist
from collections import OrderedDict
# 加载数据
def get_data():
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True)
return (x_train, t_train), (x_test, t_test)
class Sigmoid:
def __init__(self):
self.out = None
# 正向传播
def forward(self, x):
out = 1 / (1 + np.exp(-x))
self.out = out
return out
# 反向传播
def backward(self, dout):
dx = dout * (1.0 - self.out) * self.out
return dx
class Relu:
def __init__(self):
self.mask = None
# 正向传播
def forward(self, x):
self.mask = (x <= 0)
out = x.copy()
out[self.mask] = 0
return out
# 反向传播
def backward(self, dout):
dout[self.mask] = 0
dx = dout
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 SoftmaxWithLoss:
def __init__(self):
self.loss = None # 损失
self.y = None # softmax的输出
self.t = None # 监督数据(one_hot vector)
# 输出层函数：softmax
def softmax(self, 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) # 溢出对策
return np.exp(x) / np.sum(np.exp(x))
# 交叉熵误差
def cross_entropy_error(self, y, t):
if y.ndim == 1:
t = t.reshape(1, t.size)
y = y.reshape(1, y.size)
# 监督数据是one-hot-vector的情况下，转换为正确解标签的索引
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
# 正向传播
def forward(self, x, t):
self.t = t
self.y = self.softmax(x)
self.loss = self.cross_entropy_error(self.y, self.t)
return self.loss
# 反向传播
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
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 SGD:
def __init__(self, lr):
self.lr = lr
def update(self, params, grads):
for key in params.keys():
params[key] -= self.lr * grads[key]
class MultiLayerNet:
# 全连接的多层神经网络
def __init__(self, input_size, hidden_size_list, output_size,
activation='relu', weight_init_std='relu', weight_decay_lambda=0):
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.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
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
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）
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）
# 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
(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]
# weight decay（权值衰减）的设定
# weight_decay_lambda = 0 # 不使用权值衰减的情况
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)
iter_num = 100000
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(iter_num):
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
# 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()
2).Dropout
-
如果网络的模型变得很复杂，只用权值衰减就难以应付了，这种情况下，我们就经常会使用Dropout方法。
-
原理：
- Dropout是一种在学习过程随机删除神经元的方法。
- 在训练时，随机选出隐藏层的神经元，然后进行删除，被删除的神经元不在进行信号的传递；
- 在测试时，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上训练时的删除比后在输出。
-
示例：
过拟合现象应用Dropout方法后的示意图：
-
代码实现：
import sys, os
sys.path.append(os.pardir)
import numpy as np
import matplotlib.pyplot as plt
from dataset.mnist import load_mnist
from collections import OrderedDict
# 加载数据
def get_data():
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True)
return (x_train, t_train), (x_test, t_test)
class Sigmoid:
def __init__(self):
self.out = None
# 正向传播
def forward(self, x):
out = 1 / (1 + np.exp(-x))
self.out = out
return out
# 反向传播
def backward(self, dout):
dx = dout * (1.0 - self.out) * self.out
return dx
class Relu:
def __init__(self):
self.mask = None
# 正向传播
def forward(self, x):
self.mask = (x <= 0)
out = x.copy()
out[self.mask] = 0
return out
# 反向传播
def backward(self, dout):
dout[self.mask] = 0
dx = dout
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 SoftmaxWithLoss:
def __init__(self):
self.loss = None # 损失
self.y = None # softmax的输出
self.t = None # 监督数据(one_hot vector)
# 输出层函数：softmax
def softmax(self, 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) # 溢出对策
return np.exp(x) / np.sum(np.exp(x))
# 交叉熵误差
def cross_entropy_error(self, y, t):
if y.ndim == 1:
t = t.reshape(1, t.size)
y = y.reshape(1, y.size)
# 监督数据是one-hot-vector的情况下，转换为正确解标签的索引
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
# 正向传播
def forward(self, x, t):
self.t = t
self.y = self.softmax(x)
self.loss = self.cross_entropy_error(self.y, self.t)
return self.loss
# 反向传播
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
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 SGD:
def __init__(self, lr):
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] = self.beta1*self.m[key] + (1-self.beta1)*grads[key]
# self.v[key] = self.beta2*self.v[key] + (1-self.beta2)*(grads[key]**2)
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)
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:
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
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
class MultiLayerNetExtend:
# 扩展版的全连接的多层神经网络
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):
# 设定权重的初始值
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, 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):
# 求损失函数
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):
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):
# 求梯度（数值微分）
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:
"""进行神经网络的训练的类
"""
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))
(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()
3.集成学习
- 机器学习中经常使用集成学习，所谓集成学习，就是让多个模型单独进行训练，推理时再取多个模型输出数据的均值。[用神经网络的语境来说：比如，准备5个结构相同的网络，分别进行学习，测试时，以这5个网络的输出均值作为最后的答案]
4.超参数
1).数据集的分类
①.训练数据：用于参数(权重和偏置)的学习
②.验证数据：用于超参数的性能评估
③.测试数据：确认泛化能力，要在最后使用。
2).超参数最优化的步骤
这里介绍的超参数最优化方法是实践性方法，，如果需要更精炼的方法，可以使用贝叶斯最优化。
-
步骤1：
设定超参数的范围。 -
步骤2：
从设定的超参数范围中随机取样。 -
步骤3：
使用步骤1中的采样到的超参数的值进行学习，通过验证数据评估识别精度（但要将epoch设置的很小）。 -
步骤4：
重复步骤1和步骤2，根据他们的识别精度结果，缩小超参数范围。
2).超参数最优化的实现
· 示例中:权值衰减的初始范围：10-8-10-4，学习率的初始范围是10-6-10-2
# 指定搜索的超参数的范围===============
weight_decay = 10 ** np.random.uniform(-8, -4)
lr = 10 ** np.random.uniform(-6, -2)
· 完整的代码：
import sys, os
sys.path.append(os.pardir)
import numpy as np
import matplotlib.pyplot as plt
from dataset.mnist import load_mnist
from collections import OrderedDict
# 加载数据
def get_data():
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True)
return (x_train, t_train), (x_test, t_test)
def shuffle_dataset(x, t):
"""打乱数据集
Parameters
----------
x : 训练数据
t : 监督数据
Return
-------
x, t : 打乱的训练数据和监督数据
"""
permutation = np.random.permutation(x.shape[0]) # 随机排列函数
x = x[permutation, :] if x.ndim == 2 else x[permutation, :, :, :]
t = t[permutation]
return x, t
class Sigmoid:
def __init__(self):
self.out = None
# 正向传播
def forward(self, x):
out = 1 / (1 + np.exp(-x))
self.out = out
return out
# 反向传播
def backward(self, dout):
dx = dout * (1.0 - self.out) * self.out
return dx
class Relu:
def __init__(self):
self.mask = None
# 正向传播
def forward(self, x):
self.mask = (x <= 0)
out = x.copy()
out[self.mask] = 0
return out
# 反向传播
def backward(self, dout):
dout[self.mask] = 0
dx = dout
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 SoftmaxWithLoss:
def __init__(self):
self.loss = None # 损失
self.y = None # softmax的输出
self.t = None # 监督数据(one_hot vector)
# 输出层函数：softmax
def softmax(self, 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) # 溢出对策
return np.exp(x) / np.sum(np.exp(x))
# 交叉熵误差
def cross_entropy_error(self, y, t):
if y.ndim == 1:
t = t.reshape(1, t.size)
y = y.reshape(1, y.size)
# 监督数据是one-hot-vector的情况下，转换为正确解标签的索引
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
# 正向传播
def forward(self, x, t):
self.t = t
self.y = self.softmax(x)
self.loss = self.cross_entropy_error(self.y, self.t)
return self.loss
# 反向传播
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
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 SGD:
def __init__(self, lr):
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] = self.beta1*self.m[key] + (1-self.beta1)*grads[key]
# self.v[key] = self.beta2*self.v[key] + (1-self.beta2)*(grads[key]**2)
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)
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:
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
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
class MultiLayerNet:
"""全连接的多层神经网络
Parameters
----------
input_size : 输入大小（MNIST的情况下为784）
hidden_size_list : 隐藏层的神经元数量的列表（e.g. [100, 100, 100]）
output_size : 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_size, hidden_size_list, output_size,
activation='relu', weight_init_std='relu', weight_decay_lambda=0):
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.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 : 教师标签
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 : 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
"""
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 Trainer:
"""进行神经网络的训练的类
"""
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))
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True)
# 为了实现高速化，减少训练数据
x_train = x_train[:500]
t_train = t_train[:500]
# 分割验证数据
validation_rate = 0.20
validation_num = int(x_train.shape[0] * validation_rate)
x_train, t_train = shuffle_dataset(x_train, t_train)
x_val = x_train[:validation_num]
t_val = t_train[:validation_num]
x_train = x_train[validation_num:]
t_train = t_train[validation_num:]
def __train(lr, weight_decay, epocs=50):
network = MultiLayerNet(input_size=784, hidden_size_list=[100, 100, 100, 100, 100, 100],
output_size=10, weight_decay_lambda=weight_decay)
trainer = Trainer(network, x_train, t_train, x_val, t_val,
epochs=epocs, mini_batch_size=100,
optimizer='sgd', optimizer_param={'lr': lr}, verbose=False)
trainer.train()
return trainer.test_acc_list, trainer.train_acc_list
# 超参数的随机搜索======================================
optimization_trial = 100
results_val = {}
results_train = {}
for _ in range(optimization_trial):
# 指定搜索的超参数的范围===============
weight_decay = 10 ** np.random.uniform(-8, -4)
lr = 10 ** np.random.uniform(-6, -2)
# ================================================
val_acc_list, train_acc_list = __train(lr, weight_decay)
print("val acc:" + str(val_acc_list[-1]) + " | lr:" + str(lr) + ", weight decay:" + str(weight_decay))
key = "lr:" + str(lr) + ", weight decay:" + str(weight_decay)
results_val[key] = val_acc_list
results_train[key] = train_acc_list
# 绘制图形========================================================
print("=========== Hyper-Parameter Optimization Result ===========")
graph_draw_num = 20
col_num = 5
row_num = int(np.ceil(graph_draw_num / col_num))
i = 0
for key, val_acc_list in sorted(results_val.items(), key=lambda x: x[1][-1], reverse=True):
print("Best-" + str(i + 1) + "(val acc:" + str(val_acc_list[-1]) + ") | " + key)
plt.subplot(row_num, col_num, i + 1)
plt.title("Best-" + str(i + 1))
plt.ylim(0.0, 1.0)
if i % 5: plt.yticks([])
plt.xticks([])
x = np.arange(len(val_acc_list))
plt.plot(x, val_acc_list)
plt.plot(x, results_train[key], "--")
i += 1
if i >= graph_draw_num:
break
plt.show()
3).结果展示
识别精度从高到低的顺序排列了验证数据学习的变化。[实线是验证数据的识别精度，虚线是训练数据的识别精度]
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
