《深度学习入门》学习代码

《深度学习入门》学习笔记

第三章 nn

调用训练好的sample_weight.pkl
one_hot 标签：[0 0 1 0 0 0 0 0 0 0]

# 神经网络识别 MNIST手写数字集
# coding: utf-8
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
import pickle
from dataset.mnist import load_mnist
from common.functions import sigmoid, softmax


def get_data():
    (x_train, t_train), (x_test, t_test) = load_mnist(normalize=True, flatten=True, one_hot_label=False)
    # normalize=True, 数据的值限定在0~1，正则化
    return x_test, t_test


def init_network():
    with open("sample_weight.pkl", 'rb') as f:
        network = pickle.load(f)
    return network


def predict(network, x):
    W1, W2, W3 = network['W1'], network['W2'], network['W3']
    b1, b2, b3 = network['b1'], network['b2'], network['b3']

    a1 = np.dot(x, W1) + b1
    z1 = sigmoid(a1)
    a2 = np.dot(z1, W2) + b2
    z2 = sigmoid(a2)
    a3 = np.dot(z2, W3) + b3
    y = softmax(a3)

    return y


# x, t = get_data()
# network = init_network()
# accuracy_cnt = 0
# for i in range(len(x)):
#     y = predict(network, x[i])
#     p= np.argmax(y) # 获取概率最高的元素的索引
#     if p == t[i]:
#         accuracy_cnt += 1
#     print("label = ", str(t[i]), "\tpredict = ", str(p))
#
# print("Accuracy:" + str(float(accuracy_cnt) / len(x)))

## 批处理
x, t = get_data()
network = init_network()

batch_size = 100 # 批数量
accuracy_cnt = 0

for i in range(0, len(x), batch_size):
    x_batch = x[i:i+batch_size]
    y_batch = predict(network, x_batch)
    p = np.argmax(y_batch, axis=1)
    accuracy_cnt += np.sum(p == t[i:i+batch_size])

print("Accuracy:" + str(float(accuracy_cnt) / len(x)))

运行结果：

Accuracy:0.9352

第四章 2_layer_nn

# 2_layer_nn
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
import matplotlib.pyplot as plt
from dataset.mnist import load_mnist
from common.functions import *
from common.gradient import numerical_gradient

class TwoLayerNet:

    def __init__(self, input_size, hidden_size, output_size, weight_init_std=0.01):
        # 初始化权重
        self.params = {}
        self.params['W1'] = weight_init_std * np.random.randn(input_size, hidden_size)
        self.params['b1'] = np.zeros(hidden_size)
        self.params['W2'] = weight_init_std * np.random.randn(hidden_size, output_size)
        self.params['b2'] = np.zeros(output_size)

    def predict(self, x):
        # 识别、推理
        # x 是图像数据
        W1, W2 = self.params['W1'], self.params['W2']
        b1, b2 = self.params['b1'], self.params['b2']

        a1 = np.dot(x, W1) + b1
        z1 = sigmoid(a1)
        a2 = np.dot(z1, W2) + b2
        y = softmax(a2)

        return y

    # x:输入数据, t:监督数据
    def loss(self, x, t):
        y = self.predict(x)

        return cross_entropy_error(y, t)

    def accuracy(self, x, t):
        y = self.predict(x)
        y = np.argmax(y, axis=1)
        t = np.argmax(t, axis=1)

        accuracy = np.sum(y == t) / float(x.shape[0])
        return accuracy

    # x:输入数据, t:监督数据
    def numerical_gradient(self, x, t):
        # 计算梯度
        loss_W = lambda W: self.loss(x, t)

        grads = {} # 字典变量
        grads['W1'] = numerical_gradient(loss_W, self.params['W1'])
        grads['b1'] = numerical_gradient(loss_W, self.params['b1'])
        grads['W2'] = numerical_gradient(loss_W, self.params['W2'])
        grads['b2'] = numerical_gradient(loss_W, self.params['b2'])

        return grads

    def gradient(self, x, t):
        # 计算梯度
        # numerical_gradient的高速版
        W1, W2 = self.params['W1'], self.params['W2']
        b1, b2 = self.params['b1'], self.params['b2']
        grads = {}

        batch_num = x.shape[0]

        # forward
        a1 = np.dot(x, W1) + b1
        z1 = sigmoid(a1)
        a2 = np.dot(z1, W2) + b2
        y = softmax(a2)

        # backward
        dy = (y - t) / batch_num
        grads['W2'] = np.dot(z1.T, dy)
        grads['b2'] = np.sum(dy, axis=0)

        da1 = np.dot(dy, W2.T)
        dz1 = sigmoid_grad(a1) * da1
        grads['W1'] = np.dot(x.T, dz1)
        grads['b1'] = np.sum(dz1, axis=0)

        return grads

def train():
    # 读入数据
    (x_train, t_train), (x_test, t_test) = load_mnist(normalize=True, one_hot_label=True)
    train_loss_list = []
    train_acc_list = []
    test_acc_list = []

    # 超参数
    iters_num = 50000  # 适当设定循环的次数
    train_size = x_train.shape[0]
    batch_size = 100
    learning_rate = 0.1
    network = TwoLayerNet(input_size=784, hidden_size=50, output_size=10)

    iter_per_epoch = max(train_size / batch_size, 1)

    for i in range(iters_num):
        batch_mask = np.random.choice(train_size, batch_size)
        x_batch = x_train[batch_mask]
        t_batch = t_train[batch_mask]

        # 计算梯度
        # grad = network.numerical_gradient(x_batch, t_batch)
        grad = network.gradient(x_batch, t_batch)

        # 更新参数
        for key in ('W1', 'b1', 'W2', 'b2'):
            network.params[key] -= learning_rate * grad[key]

        # 记录学习过程
        loss = network.loss(x_batch, t_batch)
        train_loss_list.append(loss)

        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("train acc, test acc | " + str(train_acc) + ", " + str(test_acc))

    # 绘制图形
    markers = {'train': 'o', 'test': 's'}
    x = np.arange(len(train_acc_list))
    plt.plot(x, train_acc_list, label='train acc')
    plt.plot(x, test_acc_list, label='test acc', linestyle='--')
    plt.xlabel("epochs")
    plt.ylabel("accuracy")
    plt.ylim(0, 1.0)
    plt.legend(loc='lower right')
    plt.show()

train()

结果：

train acc, test acc | 0.10218333333333333, 0.101
train acc, test acc | 0.7928333333333333, 0.7966
train acc, test acc | 0.87415, 0.8808
train acc, test acc | 0.8976833333333334, 0.9031
train acc, test acc | 0.9083666666666667, 0.9113
train acc, test acc | 0.91435, 0.9167
train acc, test acc | 0.9186166666666666, 0.9209
train acc, test acc |0.9231, 0.9253
train acc, test acc | 0.9273666666666667, 0.9291
train acc, test acc | 0.9316166666666666, 0.933
。。。。
train acc, test acc | 0.9474166666666667, 0.9466

第五章 2_layer_nn

与上一个类似

# coding: utf-8
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 common.layers import *
from common.gradient import numerical_gradient
from collections import OrderedDict
from dataset.mnist import load_mnist

class TwoLayerNet:

    def __init__(self, input_size, hidden_size, output_size, weight_init_std=0.01):
        # 初始化权重
        self.params = {}
        self.params['W1'] = weight_init_std * np.random.randn(input_size, hidden_size)
        self.params['b1'] = np.zeros(hidden_size)
        self.params['W2'] = weight_init_std * np.random.randn(hidden_size, output_size)
        self.params['b2'] = np.zeros(output_size)

        # 生成层
        self.layers = OrderedDict()
        self.layers['Affine1'] = Affine(self.params['W1'], self.params['b1'])
        self.layers['Relu1'] = Relu()
        self.layers['Affine2'] = Affine(self.params['W2'], self.params['b2'])

        self.lastLayer = SoftmaxWithLoss()

    def predict(self, x):
        for layer in self.layers.values():
            x = layer.forward(x)

        return x

    # x:输入数据, t:监督数据
    def loss(self, x, t):
        y = self.predict(x)
        return self.lastLayer.forward(y, t)

    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

    # x:输入数据, t:监督数据
    def numerical_gradient(self, x, t):
        loss_W = lambda W: self.loss(x, t)

        grads = {}
        grads['W1'] = numerical_gradient(loss_W, self.params['W1'])
        grads['b1'] = numerical_gradient(loss_W, self.params['b1'])
        grads['W2'] = numerical_gradient(loss_W, self.params['W2'])
        grads['b2'] = numerical_gradient(loss_W, self.params['b2'])

        return grads

    def gradient(self, x, t):
        # forward
        self.loss(x, t)

        # backward
        dout = 1
        dout = self.lastLayer.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['Affine1'].dW, self.layers['Affine1'].db
        grads['W2'], grads['b2'] = self.layers['Affine2'].dW, self.layers['Affine2'].db

        return grads

def train():
    # 读入数据
    (x_train, t_train), (x_test, t_test) = load_mnist(normalize=True, one_hot_label=True)

    network = TwoLayerNet(input_size=784, hidden_size=50, output_size=10)

    # iters_num = 10000
    iters_num = 100
    train_size = x_train.shape[0]
    batch_size = 100
    learning_rate = 0.1

    train_loss_list = []
    train_acc_list = []
    test_acc_list = []

    iter_per_epoch = max(train_size / batch_size, 1)

    for i in range(iters_num):
        batch_mask = np.random.choice(train_size, batch_size)
        x_batch = x_train[batch_mask]
        t_batch = t_train[batch_mask]

        # 梯度
        # grad = network.numerical_gradient(x_batch, t_batch)
        grad = network.gradient(x_batch, t_batch)

        # 更新
        for key in ('W1', 'b1', 'W2', 'b2'):
            network.params[key] -= learning_rate * grad[key]

        loss = network.loss(x_batch, t_batch)
        train_loss_list.append(loss)

        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("train acc, test acc | " + str(train_acc) + ", " + str(test_acc))

    y = network.predict(x_test[0:9])
    y = np.argmax(y, axis=1)
    print("预测值： ", y)
    print("真实值： ",np.argmax(t_test[0:9], axis=1))


train()

train acc, test acc | 0.9786666666666667, 0.9701
预测值： [7 2 1 0 4 1 4 9 6]
真实值： [7 2 1 0 4 1 4 9 5]

第六章 optimizer

基于MNIST数据集的更新方法的比较,SGD、Momentum、
AdaGrad、Adam

# coding: utf-8
import os
import sys

sys.path.append(os.pardir)  # 为了导入父目录的文件而进行的设定
import matplotlib.pyplot as plt
from dataset.mnist import load_mnist
from common.util import smooth_curve
from common.multi_layer_net import MultiLayerNet
from common.optimizer import *

# 0:读入MNIST数据==========
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True)

train_size = x_train.shape[0]
batch_size = 128
max_iterations = 2000

# 1:进行实验的设置==========
optimizers = {}
optimizers['SGD'] = SGD()
optimizers['Momentum'] = Momentum()
optimizers['AdaGrad'] = AdaGrad()
optimizers['Adam'] = Adam()
# optimizers['RMSprop'] = RMSprop()

networks = {}
train_loss = {}
for key in optimizers.keys():
    networks[key] = MultiLayerNet(
        input_size=784, hidden_size_list=[100, 100, 100, 100],
        output_size=10)
    train_loss[key] = []

# 2:开始训练==========
for i in range(max_iterations):
    batch_mask = np.random.choice(train_size, batch_size)
    x_batch = x_train[batch_mask]
    t_batch = t_train[batch_mask]

    for key in optimizers.keys():
        grads = networks[key].gradient(x_batch, t_batch)
        optimizers[key].update(networks[key].params, grads)

        loss = networks[key].loss(x_batch, t_batch)
        train_loss[key].append(loss)

    if i % 100 == 0:
        print("===========" + "iteration:" + str(i) + "===========")
        for key in optimizers.keys():
            loss = networks[key].loss(x_batch, t_batch)
            print(key + ":" + str(loss))

# 3.绘制图形==========
markers = {"SGD": "o", "Momentum": "x", "AdaGrad": "s", "Adam": "D"}
x = np.arange(max_iterations)
for key in optimizers.keys():
    plt.plot(x, smooth_curve(train_loss[key]), marker=markers[key], markevery=100, label=key)
plt.xlabel("iterations")
plt.ylabel("loss")
plt.ylim(0, 1)
plt.legend()
plt.show()

结果

# coding: utf-8
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
import matplotlib.pyplot as plt
from collections import OrderedDict
from common.optimizer import *


def f(x, y):
    return x ** 2 / 20.0 + y ** 2


def df(x, y):
    return x / 10.0, 2.0 * y


init_pos = (-7.0, 2.0)
params = {}
params['x'], params['y'] = init_pos[0], init_pos[1]
grads = {}
grads['x'], grads['y'] = 0, 0

optimizers = OrderedDict()
optimizers["SGD"] = SGD(lr=0.95)
optimizers["Momentum"] = Momentum(lr=0.1)
optimizers["AdaGrad"] = AdaGrad(lr=1.5)
optimizers["Adam"] = Adam(lr=0.3)

idx = 1

for key in optimizers:
    optimizer = optimizers[key]
    x_history = []
    y_history = []
    params['x'], params['y'] = init_pos[0], init_pos[1]

    for i in range(30):
        x_history.append(params['x'])
        y_history.append(params['y'])

        grads['x'], grads['y'] = df(params['x'], params['y'])
        optimizer.update(params, grads)

    x = np.arange(-10, 10, 0.01)
    y = np.arange(-5, 5, 0.01)

    X, Y = np.meshgrid(x, y)
    Z = f(X, Y)

    # for simple contour line
    mask = Z > 7
    Z[mask] = 0

    # plot
    plt.subplot(2, 2, idx)
    idx += 1
    plt.plot(x_history, y_history, 'o-', color="red")
    plt.contour(X, Y, Z)
    plt.ylim(-10, 10)
    plt.xlim(-10, 10)
    plt.plot(0, 0, '+')
    # colorbar()
    # spring()
    plt.title(key)
    plt.xlabel("x")
    plt.ylabel("y")

plt.show()

结果

第七章 简单的ConvNet

# coding: utf-8
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 pickle
import numpy as np
from collections import OrderedDict
from common.layers import *
from common.functions import *
from common.gradient import numerical_gradient
import matplotlib.pyplot as plt
from dataset.mnist import load_mnist
from common.trainer import Trainer

class ConvNet:

    """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）
    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”
    """

    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):
        # 取出卷积层超参数
        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 - filter_size + 2 * filter_pad) / filter_stride + 1
        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()
        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'])

        self.last_layer = SoftmaxWithLoss()

    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
        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)

    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]

    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 (1, 2, 3):
            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 = {}
        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

    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)

    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)]

def train():
    # 读入数据
    (x_train, t_train), (x_test, t_test) = 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

    network = ConvNet(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)

    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("Saved Network Parameters!")

    # 绘制图形
    markers = {'train': 'o', 'test': 's'}
    x = np.arange(max_epochs)
    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()

    y = network.predict(x_test[0:9])
    y = np.argmax(y, axis=1)
    print("预测值： ", y)
    print("真实值： ", np.argmax(t_test[0:9], axis=1))

train()

结果

train loss:0.07818116457244638

第八章 DeepConvNet

# coding: utf-8 书P236
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 pickle
import numpy as np
from collections import OrderedDict
from common.layers import *
from dataset.mnist import load_mnist
from common.trainer import Trainer

class DeepConvNet:
    """识别率为99%以上的高精度的ConvNet

    网络结构如下所示
        conv - relu - conv- relu - pool -
        conv - relu - conv- relu - pool -
        conv - relu - conv- relu - pool -
        affine - relu - dropout - affine - dropout - softmax
    """
    def __init__(self, input_dim=(1, 28, 28),
                 conv_param_1 = {'filter_num':16, 'filter_size':3, 'pad':1, 'stride':1},
                 conv_param_2 = {'filter_num':16, 'filter_size':3, 'pad':1, 'stride':1},
                 conv_param_3 = {'filter_num':32, 'filter_size':3, 'pad':1, 'stride':1},
                 conv_param_4 = {'filter_num':32, 'filter_size':3, 'pad':2, 'stride':1},
                 conv_param_5 = {'filter_num':64, 'filter_size':3, 'pad':1, 'stride':1},
                 conv_param_6 = {'filter_num':64, 'filter_size':3, 'pad':1, 'stride':1},
                 hidden_size=50, output_size=10):
        # 初始化权重===========
        # 各层的神经元平均与前一层的几个神经元有连接（TODO:自动计算）
        pre_node_nums = np.array([1*3*3, 16*3*3, 16*3*3, 32*3*3, 32*3*3, 64*3*3, 64*4*4, hidden_size])
        wight_init_scales = np.sqrt(2.0 / pre_node_nums)  # 使用ReLU的情况下推荐的初始值
        
        self.params = {}
        pre_channel_num = input_dim[0]
        for idx, conv_param in enumerate([conv_param_1, conv_param_2, conv_param_3, conv_param_4, conv_param_5, conv_param_6]):
            self.params['W' + str(idx+1)] = wight_init_scales[idx] * np.random.randn(conv_param['filter_num'], pre_channel_num, conv_param['filter_size'], conv_param['filter_size'])
            self.params['b' + str(idx+1)] = np.zeros(conv_param['filter_num'])
            pre_channel_num = conv_param['filter_num']
        self.params['W7'] = wight_init_scales[6] * np.random.randn(64*4*4, hidden_size)
        self.params['b7'] = np.zeros(hidden_size)
        self.params['W8'] = wight_init_scales[7] * np.random.randn(hidden_size, output_size)
        self.params['b8'] = np.zeros(output_size)

        # 生成层===========
        self.layers = []
        self.layers.append(Convolution(self.params['W1'], self.params['b1'], 
                           conv_param_1['stride'], conv_param_1['pad']))
        self.layers.append(Relu())
        self.layers.append(Convolution(self.params['W2'], self.params['b2'], 
                           conv_param_2['stride'], conv_param_2['pad']))
        self.layers.append(Relu())
        self.layers.append(Pooling(pool_h=2, pool_w=2, stride=2))
        self.layers.append(Convolution(self.params['W3'], self.params['b3'], 
                           conv_param_3['stride'], conv_param_3['pad']))
        self.layers.append(Relu())
        self.layers.append(Convolution(self.params['W4'], self.params['b4'],
                           conv_param_4['stride'], conv_param_4['pad']))
        self.layers.append(Relu())
        self.layers.append(Pooling(pool_h=2, pool_w=2, stride=2))
        self.layers.append(Convolution(self.params['W5'], self.params['b5'],
                           conv_param_5['stride'], conv_param_5['pad']))
        self.layers.append(Relu())
        self.layers.append(Convolution(self.params['W6'], self.params['b6'],
                           conv_param_6['stride'], conv_param_6['pad']))
        self.layers.append(Relu())
        self.layers.append(Pooling(pool_h=2, pool_w=2, stride=2))
        self.layers.append(Affine(self.params['W7'], self.params['b7']))
        self.layers.append(Relu())
        self.layers.append(Dropout(0.5))
        self.layers.append(Affine(self.params['W8'], self.params['b8']))
        self.layers.append(Dropout(0.5))
        
        self.last_layer = SoftmaxWithLoss()

    def predict(self, x, train_flg=False):
        for layer in self.layers:
            if isinstance(layer, Dropout):
                x = layer.forward(x, train_flg)
            else:
                x = layer.forward(x)
        return x

    def loss(self, x, t):
        y = self.predict(x, train_flg=True)
        return self.last_layer.forward(y, t)

    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, train_flg=False)
            y = np.argmax(y, axis=1)
            acc += np.sum(y == tt)

        return acc / x.shape[0]

    def gradient(self, x, t):
        # forward
        self.loss(x, t)

        # backward
        dout = 1
        dout = self.last_layer.backward(dout)

        tmp_layers = self.layers.copy()
        tmp_layers.reverse()
        for layer in tmp_layers:
            dout = layer.backward(dout)

        # 设定
        grads = {}
        for i, layer_idx in enumerate((0, 2, 5, 7, 10, 12, 15, 18)):
            grads['W' + str(i+1)] = self.layers[layer_idx].dW
            grads['b' + str(i+1)] = self.layers[layer_idx].db

        return grads

    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)

    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, layer_idx in enumerate((0, 2, 5, 7, 10, 12, 15, 18)):
            self.layers[layer_idx].W = self.params['W' + str(i+1)]
            self.layers[layer_idx].b = self.params['b' + str(i+1)]

def train():
    (x_train, t_train), (x_test, t_test) = 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]

    network = DeepConvNet()
    trainer = Trainer(network, x_train, t_train, x_test, t_test,
                      epochs=20, 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("deep_convnet_params.pkl")
    print("Saved Network Parameters!")

train()