第六章.卷积神经网络(CNN)—CNN的实现(搭建手写数字识别的CNN)

第六章.卷积神经网络(CNN)

6.2 CNN的实现(搭建手写数字识别的CNN)

1.网络构成

2.代码实现

import pickle
import matplotlib.pyplot as plt
import numpy as np
import sys, ossys.path.append(os.pardir)from dataset.mnist import load_mnist
from collections import OrderedDict# 从图像到矩阵
def im2col(input_data, filter_h, filter_w, stride=1, pad=0):N, C, H, W = input_data.shapeout_h = (H + 2 * pad - filter_h) // stride + 1out_w = (W + 2 * pad - filter_w) // stride + 1img = 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_hfor x in range(filter_w):x_max = x + stride * out_wcol[:, :, 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# 从矩阵到图像
def col2im(col, input_shape, filter_h, filter_w, stride=1, pad=0):N, C, H, W = input_shapeout_h = (H + 2 * pad - filter_h) // stride + 1out_w = (W + 2 * pad - filter_w) // stride + 1col = 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_hfor x in range(filter_w):x_max = x + stride * out_wimg[:, :, y:y_max:stride, x:x_max:stride] += col[:, :, y, x, :, :]return img[:, :, pad:H + pad, pad:W + pad]class SGD:def __init__(self, lr=0.01):self.lr = lrdef 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 = lrself.momentum = momentumself.v = Nonedef 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 = lrself.momentum = momentumself.v = Nonedef 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.momentumself.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 = lrself.h = Nonedef 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 = lrself.decay_rate = decay_rateself.h = Nonedef 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_rateself.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 = lrself.beta1 = beta1self.beta2 = beta2self.iter = 0self.m = Noneself.v = Nonedef 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 += 1lr_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)# unbias_m += (1 - self.beta1) * (grads[key] - self.m[key]) # correct bias# unbisa_b += (1 - self.beta2) * (grads[key]*grads[key] - self.v[key]) # correct bias# params[key] += self.lr * unbias_m / (np.sqrt(unbisa_b) + 1e-7)# 激活函数Relu
class Relu:def __init__(self):self.mask = Nonedef forward(self, x):self.mask = (x <= 0)out = x.copy()out[self.mask] = 0return outdef backward(self, dout):dout[self.mask] = 0dx = doutreturn dx# 卷积层
class Convolution:def __init__(self, W, b, stride=1, pad=0):self.W = Wself.b = bself.stride = strideself.pad = pad# 中间数据（backward时使用）self.x = Noneself.col = Noneself.col_W = None# 权重和偏置参数的梯度self.dW = Noneself.db = None# 正向传播def forward(self, x):FN, C, FH, FW = self.W.shapeN, C, H, W = x.shapeout_h = int((H + 2 * self.pad - FH) / self.stride) + 1out_w = int((W + 2 * self.pad - FW) / self.stride) + 1col = im2col(x, FH, FW, self.stride, self.pad)col_W = self.W.reshape(FN, -1).Tout = np.dot(col, col_W) + self.bout = out.reshape(N, out_h, out_w, -1).transpose(0, 3, 1, 2)self.x = xself.col = colself.col_W = col_Wreturn out# 反向传播def backward(self, dout):FN, C, FH, FW = self.W.shapedout = 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_hself.pool_w = pool_wself.stride = strideself.pad = padself.x = Noneself.arg_max = None# 正向传播def forward(self, x):N, C, H, W = x.shapeout_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 = xself.arg_max = arg_maxreturn out# 反向传播def backward(self, dout):dout = dout.transpose(0, 2, 3, 1)pool_size = self.pool_h * self.pool_wdmax = 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# Affine层
class Affine:def __init__(self, W, b):self.W = Wself.b = bself.x = Noneself.original_x_shape = None# 权重和偏置参数的导数self.dW = Noneself.db = Nonedef forward(self, x):# 对应张量self.original_x_shape = x.shape  # 例如：x.shape=(209, 64, 64, 3)x = x.reshape(x.shape[0], -1)  # x=(209, 64*64*3)self.x = xout = np.dot(self.x, self.W) + self.breturn outdef 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# 输出层
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：softmaxdef softmax(self, x):if x.ndim == 2:x = x.Tx = x - np.max(x, axis=0)y = np.exp(x) / np.sum(np.exp(x), axis=0)return y.Tx = 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 = tself.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_sizeelse:dx = self.y.copy()dx[np.arange(batch_size), self.t] -= 1dx = dx / batch_sizereturn dxclass 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 = networkself.verbose = verboseself.x_train = x_trainself.t_train = t_trainself.x_test = x_testself.t_test = t_testself.epochs = epochsself.batch_size = mini_batch_sizeself.evaluate_sample_num_per_epoch = evaluate_sample_num_per_epoch# optimzeroptimizer_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 = 0self.current_epoch = 0self.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 += 1x_train_sample, t_train_sample = self.x_train, self.t_trainx_test_sample, t_test_sample = self.x_test, self.t_testif not self.evaluate_sample_num_per_epoch is None:t = self.evaluate_sample_num_per_epochx_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 += 1def 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))# 手写数字识别CNN的实现类: conv - relu - pool - affine - relu - affine - softmax
class SimpleConvNet: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_int_std=0.01):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]conv_output_size = (input_size + 2 * filter_pad - filter_size) / filter_stride + 1pool_output_size = int(filter_num * (conv_output_size / 2) * (conv_output_size / 2))# 初始化权重self.params = {}self.params['W1'] = weight_int_std * np.random.randn(filter_num, input_dim[0], filter_size, filter_size)self.params['b1'] = np.zeros(filter_num)self.params['W2'] = weight_int_std * np.random.randn(pool_output_size, hidden_size)self.params['b2'] = np.zeros(hidden_size)self.params['W3'] = weight_int_std * np.random.randn(hidden_size, output_size)self.params['b3'] = np.zeros(output_size)# 生成层self.layers = OrderedDict()self.layers['Conv1'] = Convolution(self.params['W1'], self.params['b1'], filter_stride, filter_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'])self.last_layer = SoftmaxWithLoss()# 推理函数def predict(self, x):for layer in self.layers.values():x = layer.forward(x)return x# 损失函数def loss(self, x, t):y = self.predict(x)return self.last_layer.forward(y, t)# 识别精度def accuracy(self, x, t, batch_size=100):if t.ndim != 1: t = np.argmax(t, axis=1)acc = 0.0for 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]def numerical_gradient(f, x):h = 1e-4  # 0.0001grad = np.zeros_like(x)it = np.nditer(x, flags=['multi_index'], op_flags=['readwrite'])while not it.finished:idx = it.multi_indextmp_val = x[idx]x[idx] = float(tmp_val) + hfxh1 = f(x)  # f(x+h)x[idx] = tmp_val - hfxh2 = f(x)  # f(x-h)grad[idx] = (fxh1 - fxh2) / (2 * h)x[idx] = tmp_val  # 还原值it.iternext()return grad# 数值微分def numerical_gradient(self, x, t):loss_w = lambda w: self.loss(x, t)grads = {}for idx in (1, 2, 3):grads['W' + str(idx)] = self.numerical_gradient(loss_w, self.params['W' + str(idx)])grads['b' + str(idx)] = self.numerical_gradient(loss_w, self.params['b' + str(idx)])return grads# 误差反向传播法求梯度def gradient(self, x, t):self.loss(x, t)dout = 1dout = 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'].dbgrads['W2'], grads['b2'] = self.layers['Affine1'].dW, self.layers['Affine1'].dbgrads['W3'], grads['b3'] = self.layers['Affine2'].dW, self.layers['Affine2'].dbreturn grads# 保存参数def save_param(self, file_name='params.pkl'):params = {}for key, val in self.params.items():params[key] = valwith open(file_name, 'wb') as f:pickle.dump(params, f)# 加载参数def load_param(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] = valfor 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)]#加载数据
(x_train,t_train),(x_test,t_test)=load_mnist(flatten=False)#较少数据
x_train,t_train=x_train[:5000],t_train[:5000]
x_test,t_test=x_test[:1000],t_test[:1000]max_epoch=20
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_int_std=0.01)trainer=Trainer(network, x_train, t_train, x_test, t_test,epochs=max_epoch, 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_param("params.pkl")
print("Save Network Parameters!")#绘制图像
x=np.arange(max_epoch)
plt.plot(x,trainer.train_acc_list,marker='o',label='train',markevery=2)
plt.plot(x,trainer.test_acc_list,marker='s',label='test',markevery=2)
plt.xlabel("epochs")
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
plt.legend(loc='lower right')
plt.show()

3.结果展示

4.CNN的代表性网络

1).LeNet

• 传统的CNN & LeNet的差异：

  ①.激活函数不同：LeNet使用sigmoid函数，传统的CNN网络使用的是Relu函数

  ②.原始的LeNet中使用子采样缩小中间数据的大小，传统的CNN网络主要使用Max池化。

2).AlexNet

• LeNet & AlexNet的差异：

  ①.激活函数不同：LeNet使用sigmoid函数，AlexNet使用Relu函数

  ②.使用进行局部正则化的LRN(Local Response Normalization)层

  ③.使用Dropout