import sys, os
sys.path.append(os.pardir) # 为了导入父目录的文件而进行的设定
import numpy as np
from collections import OrderedDict
from common.layers import *
from common.gradient import numerical_gradient
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
import sys, os
sys.path.append(os.pardir) # 为了导入父目录的文件而进行的设定
import numpy as np
from collections import OrderedDict
from common.layers import *
from common.gradient import numerical_gradient
class MultiLayerNetExtend:
"""扩展版的全连接的多层神经网络
具有Weiht Decay、Dropout、Batch Normalization的功能
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
use_dropout: 是否使用Dropout
dropout_ration : Dropout的比例
use_batchNorm: 是否使用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 = {}
# 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
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, 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
参数x是输入数据，t是教师标签
"""
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）
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, 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
common.layers:
from common.functions import *
from common.util import im2col, col2im
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
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
class Dropout:
"""
http://arxiv.org/abs/1207.0580
"""
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:
"""
http://arxiv.org/abs/1502.03167
"""
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 Convolution:
def __init__(self, W, b, stride=1, pad=0):
self.W = W
self.b = b
self.stride = stride
self.pad = pad
# 中间数据（backward时使用）
self.x = None
self.col = None
self.col_W = None
# 权重和偏置参数的梯度
self.dW = None
self.db = None
def forward(self, x):
FN, C, FH, FW = self.W.shape
N, C, H, W = x.shape
out_h = 1 + int((H + 2*self.pad - FH) / self.stride)
out_w = 1 + int((W + 2*self.pad - FW) / self.stride)
col = im2col(x, FH, FW, self.stride, self.pad)
col_W = self.W.reshape(FN, -1).T
out = np.dot(col, col_W) + self.b
out = out.reshape(N, out_h, out_w, -1).transpose(0, 3, 1, 2)
self.x = x
self.col = col
self.col_W = col_W
return out
def backward(self, dout):
FN, C, FH, FW = self.W.shape
dout = dout.transpose(0,2,3,1).reshape(-1, FN)
self.db = np.sum(dout, axis=0)
self.dW = np.dot(self.col.T, dout)
self.dW = self.dW.transpose(1, 0).reshape(FN, C, FH, FW)
dcol = np.dot(dout, self.col_W.T)
dx = col2im(dcol, self.x.shape, FH, FW, self.stride, self.pad)
return dx
class Pooling:
def __init__(self, pool_h, pool_w, stride=1, pad=0):
self.pool_h = pool_h
self.pool_w = pool_w
self.stride = stride
self.pad = pad
self.x = None
self.arg_max = None
def forward(self, x):
N, C, H, W = x.shape
out_h = int(1 + (H - self.pool_h) / self.stride)
out_w = int(1 + (W - self.pool_w) / self.stride)
col = im2col(x, self.pool_h, self.pool_w, self.stride, self.pad)
col = col.reshape(-1, self.pool_h*self.pool_w)
arg_max = np.argmax(col, axis=1)
out = np.max(col, axis=1)
out = out.reshape(N, out_h, out_w, C).transpose(0, 3, 1, 2)
self.x = x
self.arg_max = arg_max
return out
def backward(self, dout):
dout = dout.transpose(0, 2, 3, 1)
pool_size = self.pool_h * self.pool_w
dmax = np.zeros((dout.size, pool_size))
dmax[np.arange(self.arg_max.size), self.arg_max.flatten()] = dout.flatten()
dmax = dmax.reshape(dout.shape + (pool_size,))
dcol = dmax.reshape(dmax.shape[0] * dmax.shape[1] * dmax.shape[2], -1)
dx = col2im(dcol, self.x.shape, self.pool_h, self.pool_w, self.stride, self.pad)
return dx
functions.py
import numpy as np
def identity_function(x):
return x
def step_function(x):
return np.array(x > 0, dtype=np.int)
def sigmoid(x):
return 1 / (1 + np.exp(-x))
def sigmoid_grad(x):
return (1.0 - sigmoid(x)) * sigmoid(x)
def relu(x):
return np.maximum(0, x)
def relu_grad(x):
grad = np.zeros(x)
grad[x>=0] = 1
return grad
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) # 溢出对策
return np.exp(x) / np.sum(np.exp(x))
def mean_squared_error(y, t):
return 0.5 * np.sum((y-t)**2)
def cross_entropy_error(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
def softmax_loss(X, t):
y = softmax(X)
return cross_entropy_error(y, t)