版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/Daycym/article/details/83863015
回顾
上面两篇博客，实现了CNN包含的层，下面我们只需要将他们组合起来，搭建进行手写数字识别的CNN
CNN实现
我们按上图CNN的网络结构进行实现，这里只包含一层卷积层
- 下面给出各层的实现代码，具体内容可参考之前的博客：
# im2col 图像数据的展开
def im2col(input_data, filter_h, filter_w, stride=1, pad=0):
N, C, H, W = input_data.shape
out_h = (H + 2*pad - filter_h)//stride + 1
out_w = (W + 2*pad - filter_w)//stride + 1
img = np.pad(input_data, [(0,0), (0,0), (pad, pad), (pad, pad)], 'constant')
col = np.zeros((N, C, filter_h, filter_w, out_h, out_w))
for y in range(filter_h):
y_max = y + stride*out_h
for x in range(filter_w):
x_max = x + stride*out_w
col[:, :, y, x, :, :] = img[:, :, y:y_max:stride, x:x_max:stride]
col = col.transpose(0, 4, 5, 1, 2, 3).reshape(N*out_h*out_w, -1)
return col
# col2im 逆变换
def col2im(col, input_shape, filter_h, filter_w, stride=1, pad=0):
N, C, H, W = input_shape
out_h = (H + 2*pad - filter_h)//stride + 1
out_w = (W + 2*pad - filter_w)//stride + 1
col = col.reshape(N, out_h, out_w, C, filter_h, filter_w).transpose(0, 3, 4, 5, 1, 2)
img = np.zeros((N, C, H + 2*pad + stride - 1, W + 2*pad + stride - 1))
for y in range(filter_h):
y_max = y + stride*out_h
for x in range(filter_w):
x_max = x + stride*out_w
img[:, :, y:y_max:stride, x:x_max:stride] += col[:, :, y, x, :, :]
return img[:, :, pad:H + pad, pad:W + pad]
# ReLU层
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
# Affine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
# 卷积层
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
# 池化层
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
- CNN实现
import numpy as np
from collections import OrderedDict
import pickle
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 SimpleConvNet:
"""简单的ConvNet
conv - relu - pool - affine - relu - affine - softmax
Parameters
----------
input_size : 输入大小（MNIST的情况下为784）
conv_param : 卷积层的超参数（字典）
filter_num : 滤波器（卷积核）的数量
filter_size : 滤波器的大小
pad : 填充
stride : 步幅
hidden_size : 隐藏层的神经元数量
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”
"""
# 初始化操作
def __init__(self, input_dim=(1, 28, 28),
conv_param={'filter_num':30, 'filter_size':5, 'pad':0, 'stride':1},
hidden_size=100, output_size=10, weight_init_std=0.01):
# 从conv_param字典中取出相应的value
filter_num = conv_param['filter_num']
filter_size = conv_param['filter_size']
filter_pad = conv_param['pad']
filter_stride = conv_param['stride']
input_size = input_dim[1]
# 计算卷积层的输出大小
conv_output_size = (input_size - filter_size + 2*filter_pad) / filter_stride + 1
# 计算池化层的输出大小
pool_output_size = int(filter_num * (conv_output_size/2) * (conv_output_size/2))
# 初始化权重
self.params = {}
self.params['W1'] = weight_init_std * np.random.randn(filter_num, input_dim[0], filter_size, filter_size)
self.params['b1'] = np.zeros(filter_num)
self.params['W2'] = weight_init_std * np.random.randn(pool_output_size, hidden_size)
self.params['b2'] = np.zeros(hidden_size)
self.params['W3'] = weight_init_std * np.random.randn(hidden_size, output_size)
self.params['b3'] = np.zeros(output_size)
# 生成层
self.layers = OrderedDict() # 有序字典
# 依次向有序字典中添加层
self.layers['Conv1'] = Convolution(self.params['W1'], self.params['b1'],conv_param['stride'], conv_param['pad'])
self.layers['Relu1'] = Relu()
self.layers['Pool1'] = Pooling(pool_h=2, pool_w=2, stride=2)
self.layers['Affine1'] = Affine(self.params['W2'], self.params['b2'])
self.layers['Relu2'] = Relu()
self.layers['Affine2'] = Affine(self.params['W3'], self.params['b3'])
# 最后一层添加到变量last_layer中
self.last_layer = SoftmaxWithLoss()
# 推理
def predict(self, x):
# 从头开始一次调用已经添加的层，并进行正向传播运算，并将结果传递给下一层
for layer in self.layers.values():
x = layer.forward(x)
return x
# 求损失
def loss(self, x, t):
"""求损失函数
参数x是输入数据、t是教师标签
"""
y = self.predict(x)
return self.last_layer.forward(y, t)
# 计算准确率
def accuracy(self, x, t, batch_size=100):
if t.ndim != 1 : t = np.argmax(t, axis=1)
acc = 0.0
for i in range(int(x.shape[0] / batch_size)):
tx = x[i*batch_size:(i+1)*batch_size]
tt = t[i*batch_size:(i+1)*batch_size]
y = self.predict(tx)
y = np.argmax(y, axis=1)
acc += np.sum(y == tt)
return acc / x.shape[0]
# 计算梯度
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 = {}
grads['W1'], grads['b1'] = self.layers['Conv1'].dW, self.layers['Conv1'].db
grads['W2'], grads['b2'] = self.layers['Affine1'].dW, self.layers['Affine1'].db
grads['W3'], grads['b3'] = self.layers['Affine2'].dW, self.layers['Affine2'].db
return grads
# 保存模型
def save_params(self, file_name="params.pkl"):
params = {}
for key, val in self.params.items():
params[key] = val
with open(file_name, 'wb') as f:
pickle.dump(params, f)
# 加载模型
def load_params(self, file_name="params.pkl"):
with open(file_name, 'rb') as f:
params = pickle.load(f)
for key, val in params.items():
self.params[key] = val
for i, key in enumerate(['Conv1', 'Affine1', 'Affine2']):
self.layers[key].W = self.params['W' + str(i+1)]
self.layers[key].b = self.params['b' + str(i+1)]
CNN的训练
- 优化方法点击查看
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]
class Momentum:
"""Momentum SGD"""
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:
"""Nesterov's Accelerated Gradient (http://arxiv.org/abs/1212.0901)"""
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:
"""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:
"""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:
"""Adam (http://arxiv.org/abs/1412.6980v8)"""
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)
- 训练实现类
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
# 优化方法字典
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):
# 随机选择数据
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]
# 求梯度
grads = self.network.gradient(x_batch, t_batch)
# 更新参数
self.optimizer.update(self.network.params, grads)
# 求损失
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]
# 计算训练准确率
train_acc = self.network.accuracy(x_train_sample, t_train_sample)
# 测试准确率
test_acc = self.network.accuracy(x_test_sample, t_test_sample)
# 添加到列表中
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))
测试
import mnist
# 读入数据
(x_train, t_train), (x_test, t_test) = mnist.load_mnist(flatten=False)
# 处理花费时间较长的情况下减少数据
x_train, t_train = x_train[:5000], t_train[:5000]
x_test, t_test = x_test[:1000], t_test[:1000]
max_epochs = 20
# 构建CNN网络
network = SimpleConvNet(input_dim=(1,28,28),
conv_param = {'filter_num': 30, 'filter_size': 5, 'pad': 0, 'stride': 1},
hidden_size=100, output_size=10, weight_init_std=0.01)
# 训练，选择的Adam优化
trainer = Trainer(network, x_train, t_train, x_test, t_test,
epochs=max_epochs, mini_batch_size=100,
optimizer='Adam', optimizer_param={'lr': 0.001},
evaluate_sample_num_per_epoch=1000)
trainer.train()
# 保存参数
network.save_params("params.pkl")
print("保存模型成功！")
总结
- 由于处理花费时间较长，我只选择了部分数据，有兴趣的可以使用全部数据，将测试代码中的减少数据注释掉
- 本代码实现了多种优化方法，可以选择不同的优化方法进行比较