# 一个简单的卷积神经网络——layers.py

# coding： utf-8
import numpy as np
from functions import *
from util import im2col, col2im

# ------------------------------激活函数relu层-------------------------------------------------
class Relu:
def __init__(self):

def forward(self, x):
out = x.copy()

return out

def backward(self, dout):
dx = dout

return dx

# --------------------------------sigmoid激活函数层---------------------------------------------
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

# -------------------------------Affine全连接层------------------------------------------------------
class Affine:
def __init__(self, W, b):
self.W = W
self.b = b

self.x = None
self.original_x_shape = None

# 权重和偏置的导数
self.dW = None
self.db = None

def forward(self, x):
# 对应张量
self.original_x_shape = x.shape
"""将输入数据展开的方法"""
x = x.reshape(x.shape[0], -1) # reshape指定-1之后，自动计算-1维度上的元素个数，以便多维数组的元素个数前后一致
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

# ---------------------------------Softmax_with_Loss层--------------------------------------------------------
class SoftmaxWithLoss:
def __init__(self):
self.loss = None
self.y = None # softmax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

# ------------------------------Dropout层---------------------------------------------------------------------
class Dropout:
"""随机删除神经元
正向传播时，传递了信号的神经元，反向传播时按照原样传递信号
没有传递信号的神经元，反向传播时停止

机器学习中，常常采用！集成学习！：
多个模型单独进行学习，推理时再取多个模型的输出的平均值

droput作用：防止过拟合
droput原理：训练时去除一些神经元，在测试的时候用全部的神经元，这样可以使得模型泛化能力更强，因为它不会太依赖某些局部的特征
"""
def __init__(self, dropout_ratio=0.5):
self.dropout_ratio = dropout_ratio

def forward(self, x, train_flg=True):
if train_flg:
else:
return x * (1.0 - self.dropout_ratio)

def backward(self, dout):

# ---------------------------------Batch Normalization层（正则化）------------------------------------------
class BatchNormalization:
"""
思路：强制性调整激活值的分布，适当的初始值，带来更加适当的激活值分布，保证训练正常进行
作用：防止过拟合
增大学习率
不多余依赖初始值
位置：Affine、convolution层后面
原理：与数据白化原理类似，对数据的均值方差进行调整，加速训练收敛
"""

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

# ------------------------------------卷积层convolution--------------------------------------------------
class Convolution:
def __init__(self, W, b, stride=1, pad=0):
self.W = W
self.b = b
self.stride = stride

# 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

# --------------------------------池化层pooling------------------------------------------------------
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.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
10-02 617

03-20 9330
12-21 556
05-08 1205
05-10 1097
04-23 1047
12-13 4426
01-23 4万+
04-16 20万+
01-16 9281
10-19 1116