目次

深層学習（前編・day 2）
- Section1　勾配消失問題
- Section2　学習率最適化手法
- Section3　過学習
- Section4　畳み込みニューラルネットワークの概念
- Section5　最新のCNN

Section1　勾配消失問題

活性化関数

シグモイド関数
- 大きな値では出力の変化が微小なため、勾配消失問題を引き起こす事があった
ReLU関数
- 勾配消失問題の回避とスパース化に貢献

初期値の設定方法

重み初期値設定
- Xavier
  - シグモイド関数
- He
  - RelU関数

バッチ正規化

ミニバッチ単位で、入力値のデータの偏りを抑制する手法

【考察】

【実装演習結果】

vanishing gradient

Sigmoid - gauss

import numpy as np
from common import layers
from collections import OrderedDict
from common import functions
from data.mnist import load_mnist
import matplotlib.pyplot as plt
# mnistをロード
(x_train, d_train), (x_test, d_test) = load_mnist(normalize=True, one_hot_label=True)
train_size = len(x_train)
print("データ読み込み完了")
# 重み初期値補正係数
wieght_init = 0.01
# 入力層サイズ
input_layer_size = 784
# 中間層サイズ
hidden_layer_1_size = 40
hidden_layer_2_size = 20
# 出力層サイズ
output_layer_size = 10
# 繰り返し数
iters_num = 2000
# ミニバッチサイズ
batch_size = 100
# 学習率
learning_rate = 0.1
# 描写頻度
plot_interval=10
# 初期設定
def init_network():
    network = {} 
    network['W1'] = wieght_init * np.random.randn(input_layer_size, hidden_layer_1_size)
    network['W2'] = wieght_init * np.random.randn(hidden_layer_1_size, hidden_layer_2_size)
    network['W3'] = wieght_init * np.random.randn(hidden_layer_2_size, output_layer_size)
    network['b1'] = np.zeros(hidden_layer_1_size)
    network['b2'] = np.zeros(hidden_layer_2_size)
    network['b3'] = np.zeros(output_layer_size)
    return network

# 順伝播
def forward(network, x):
    W1, W2, W3 = network['W1'], network['W2'], network['W3']
    b1, b2, b3 = network['b1'], network['b2'], network['b3']
    hidden_f = functions.sigmoid
    u1 =  np.dot(x, W1) + b1
    z1 = hidden_f(u1)
    u2 =  np.dot(z1, W2) + b2
    z2 = hidden_f(u2)
    u3 =  np.dot(z2, W3) + b3
    y = functions.softmax(u3)
    return z1, z2, y

# 誤差逆伝播
def backward(x, d, z1, z2, y):
    grad = {}
    W1, W2, W3 = network['W1'], network['W2'], network['W3']
    b1, b2, b3 = network['b1'], network['b2'], network['b3']
    hidden_d_f = functions.d_sigmoid
    last_d_f = functions.d_softmax_with_loss
    # 出力層でのデルタ
    delta3 = last_d_f(d, y)
    # b3の勾配
    grad['b3'] = np.sum(delta3, axis=0)
    # W3の勾配
    grad['W3'] = np.dot(z2.T, delta3)
    # 2層でのデルタ
    delta2 = np.dot(delta3, W3.T) * hidden_d_f(z2)
    # b2の勾配
    grad['b2'] = np.sum(delta2, axis=0)
    # W2の勾配
    grad['W2'] = np.dot(z1.T, delta2)
    # 1層でのデルタ
    delta1 = np.dot(delta2, W2.T) * hidden_d_f(z1)
    # b1の勾配
    grad['b1'] = np.sum(delta1, axis=0)
    # W1の勾配
    grad['W1'] = np.dot(x.T, delta1)
    return grad

# パラメータの初期化
network = init_network()
accuracies_train = []
accuracies_test = []
# 正答率
def accuracy(x, d):
    z1, z2, y = forward(network, x)
    y = np.argmax(y, axis=1)
    if d.ndim != 1 : d = np.argmax(d, axis=1)
    accuracy = np.sum(y == d) / float(x.shape[0])
    return accuracy
for i in range(iters_num):
    # ランダムにバッチを取得    
    batch_mask = np.random.choice(train_size, batch_size)
    # ミニバッチに対応する教師訓練画像データを取得    
    x_batch = x_train[batch_mask]
    # ミニバッチに対応する訓練正解ラベルデータを取得する
    d_batch = d_train[batch_mask]
    z1, z2, y = forward(network, x_batch)
    grad = backward(x_batch, d_batch, z1, z2, y)
    if (i+1)%plot_interval==0:
        accr_test = accuracy(x_test, d_test)
        accuracies_test.append(accr_test)
        accr_train = accuracy(x_batch, d_batch)
        accuracies_train.append(accr_train)
        print('Generation: ' + str(i+1) + '. 正答率(トレーニング) = ' + str(accr_train))
        print('                : ' + str(i+1) + '. 正答率(テスト) = ' + str(accr_test))
    # パラメータに勾配適用
    for key in ('W1', 'W2', 'W3', 'b1', 'b2', 'b3'):
        network[key]  -= learning_rate * grad[key]
lists = range(0, iters_num, plot_interval)
plt.plot(lists, accuracies_train, label="training set")
plt.plot(lists, accuracies_test,  label="test set")
plt.legend(loc="lower right")
plt.title("accuracy")
plt.xlabel("count")
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
# グラフの表示
plt.show()

ReLU - gauss

import numpy as np
from data.mnist import load_mnist
from PIL import Image
import pickle
from common import functions
import matplotlib.pyplot as plt

# mnistをロード
(x_train, d_train), (x_test, d_test) = load_mnist(normalize=True, one_hot_label=True)
train_size = len(x_train)
print("データ読み込み完了")
# 重み初期値補正係数
wieght_init = 0.01
# 入力層サイズ
input_layer_size = 784
# 中間層サイズ
hidden_layer_1_size = 40
hidden_layer_2_size = 20
# 出力層サイズ
output_layer_size = 10
# 繰り返し数
iters_num = 2000
# ミニバッチサイズ
batch_size = 100
# 学習率
learning_rate = 0.1
# 描写頻度
plot_interval=10
# 初期設定
def init_network():
    network = {} 
    network['W1'] = wieght_init * np.random.randn(input_layer_size, hidden_layer_1_size)
    network['W2'] = wieght_init * np.random.randn(hidden_layer_1_size, hidden_layer_2_size)
    network['W3'] = wieght_init * np.random.randn(hidden_layer_2_size, output_layer_size)    
    network['b1'] = np.zeros(hidden_layer_1_size)
    network['b2'] = np.zeros(hidden_layer_2_size)
    network['b3'] = np.zeros(output_layer_size)
    return network

# 順伝播
def forward(network, x):
    W1, W2, W3 = network['W1'], network['W2'], network['W3']
    b1, b2, b3 = network['b1'], network['b2'], network['b3']
    ###########  変更箇所  ##############
    hidden_f = functions.relu
    #################################
    u1 =  np.dot(x, W1) + b1
    z1 = hidden_f(u1)
    u2 =  np.dot(z1, W2) + b2
    z2 = hidden_f(u2)
    u3 =  np.dot(z2, W3) + b3
    y = functions.softmax(u3)
    return z1, z2, y

# 誤差逆伝播
def backward(x, d, z1, z2, y):
    grad = {}
    W1, W2, W3 = network['W1'], network['W2'], network['W3']
    b1, b2, b3 = network['b1'], network['b2'], network['b3']
    ###########  変更箇所  ##############
    hidden_d_f = functions.d_relu
    #################################
    # 出力層でのデルタ
    delta3 = functions.d_softmax_with_loss(d, y)
    # b3の勾配
    grad['b3'] = np.sum(delta3, axis=0)
    # W3の勾配
    grad['W3'] = np.dot(z2.T, delta3)
    # 2層でのデルタ
    delta2 = np.dot(delta3, W3.T) * hidden_d_f(z2)
    # b2の勾配
    grad['b2'] = np.sum(delta2, axis=0)
    # W2の勾配
    grad['W2'] = np.dot(z1.T, delta2)
    # 1層でのデルタ
    delta1 = np.dot(delta2, W2.T) * hidden_d_f(z1)
    # b1の勾配
    grad['b1'] = np.sum(delta1, axis=0)
    # W1の勾配
    grad['W1'] = np.dot(x.T, delta1)
    return grad

# パラメータの初期化
network = init_network()
accuracies_train = []
accuracies_test = []
# 正答率
def accuracy(x, d):
    z1, z2, y = forward(network, x)
    y = np.argmax(y, axis=1)
    if d.ndim != 1 : d = np.argmax(d, axis=1)
    accuracy = np.sum(y == d) / float(x.shape[0])
    return accuracy

for i in range(iters_num):
    # ランダムにバッチを取得    
    batch_mask = np.random.choice(train_size, batch_size)
    # ミニバッチに対応する教師訓練画像データを取得    
    x_batch = x_train[batch_mask]
    # ミニバッチに対応する訓練正解ラベルデータを取得する
    d_batch = d_train[batch_mask]
    z1, z2, y = forward(network, x_batch)
    grad = backward(x_batch, d_batch, z1, z2, y)
    if (i+1)%plot_interval==0:
        accr_test = accuracy(x_test, d_test)
        accuracies_test.append(accr_test)
        accr_train = accuracy(x_batch, d_batch)
        accuracies_train.append(accr_train)
        print('Generation: ' + str(i+1) + '. 正答率(トレーニング) = ' + str(accr_train))
        print('                : ' + str(i+1) + '. 正答率(テスト) = ' + str(accr_test))
    # パラメータに勾配適用
    for key in ('W1', 'W2', 'W3', 'b1', 'b2', 'b3'):
        network[key]  -= learning_rate * grad[key]
lists = range(0, iters_num, plot_interval)
plt.plot(lists, accuracies_train, label="training set")
plt.plot(lists, accuracies_test,  label="test set")
plt.legend(loc="lower right")
plt.title("accuracy")
plt.xlabel("count")
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
# グラフの表示
plt.show()

Sigmoid - Xavier

import numpy as np
from data.mnist import load_mnist
from PIL import Image
import pickle
from common import functions
import matplotlib.pyplot as plt

# mnistをロード
(x_train, d_train), (x_test, d_test) = load_mnist(normalize=True, one_hot_label=True)
train_size = len(x_train)
print("データ読み込み完了")
# 入力層サイズ
input_layer_size = 784
# 中間層サイズ
hidden_layer_1_size = 40
hidden_layer_2_size = 20
# 出力層サイズ
output_layer_size = 10
# 繰り返し数
iters_num = 2000
# ミニバッチサイズ
batch_size = 100
# 学習率
learning_rate = 0.1
# 描写頻度
plot_interval=10
# 初期設定
def init_network():
    network = {} 
    ###########  変更箇所  ##############
    # Xavierの初期値
    network['W1'] = np.random.randn(input_layer_size, hidden_layer_1_size) / (np.sqrt(input_layer_size))
    network['W2'] = np.random.randn(hidden_layer_1_size, hidden_layer_2_size) / (np.sqrt(hidden_layer_1_size))
    network['W3'] = np.random.randn(hidden_layer_2_size, output_layer_size) / (np.sqrt(hidden_layer_2_size))
    #################################
    network['b1'] = np.zeros(hidden_layer_1_size)
    network['b2'] = np.zeros(hidden_layer_2_size)
    network['b3'] = np.zeros(output_layer_size)
    return network

# 順伝播
def forward(network, x):
    W1, W2, W3 = network['W1'], network['W2'], network['W3']
    b1, b2, b3 = network['b1'], network['b2'], network['b3']
    hidden_f = functions.sigmoid
    u1 =  np.dot(x, W1) + b1
    z1 = hidden_f(u1)
    u2 =  np.dot(z1, W2) + b2
    z2 = hidden_f(u2)
    u3 =  np.dot(z2, W3) + b3
    y = functions.softmax(u3)
    return z1, z2, y

# 誤差逆伝播
def backward(x, d, z1, z2, y):
    grad = {}
    W1, W2, W3 = network['W1'], network['W2'], network['W3']
    b1, b2, b3 = network['b1'], network['b2'], network['b3']
    hidden_d_f = functions.d_sigmoid
    # 出力層でのデルタ
    delta3 = functions.d_softmax_with_loss(d, y)
    # b3の勾配
    grad['b3'] = np.sum(delta3, axis=0)
    # W3の勾配
    grad['W3'] = np.dot(z2.T, delta3)
    # 2層でのデルタ
    delta2 = np.dot(delta3, W3.T) * hidden_d_f(z2)
    # b2の勾配
    grad['b2'] = np.sum(delta2, axis=0)
    # W2の勾配
    grad['W2'] = np.dot(z1.T, delta2)
    # 1層でのデルタ
    delta1 = np.dot(delta2, W2.T) * hidden_d_f(z1)
    # b1の勾配
    grad['b1'] = np.sum(delta1, axis=0)
    # W1の勾配
    grad['W1'] = np.dot(x.T, delta1)
    return grad

# パラメータの初期化
network = init_network()
accuracies_train = []
accuracies_test = []
# 正答率
def accuracy(x, d):
    z1, z2, y = forward(network, x)
    y = np.argmax(y, axis=1)
    if d.ndim != 1 : d = np.argmax(d, axis=1)
    accuracy = np.sum(y == d) / float(x.shape[0])
    return accuracy

for i in range(iters_num):
    # ランダムにバッチを取得    
    batch_mask = np.random.choice(train_size, batch_size)
    # ミニバッチに対応する教師訓練画像データを取得    
    x_batch = x_train[batch_mask]
    # ミニバッチに対応する訓練正解ラベルデータを取得する
    d_batch = d_train[batch_mask]
    z1, z2, y = forward(network, x_batch)
    grad = backward(x_batch, d_batch, z1, z2, y)
    if (i+1)%plot_interval==0:
        accr_test = accuracy(x_test, d_test)
        accuracies_test.append(accr_test)
        accr_train = accuracy(x_batch, d_batch)
        accuracies_train.append(accr_train)
        print('Generation: ' + str(i+1) + '. 正答率(トレーニング) = ' + str(accr_train))
        print('                : ' + str(i+1) + '. 正答率(テスト) = ' + str(accr_test))
        
    # パラメータに勾配適用
    for key in ('W1', 'W2', 'W3', 'b1', 'b2', 'b3'):
        network[key]  -= learning_rate * grad[key]
lists = range(0, iters_num, plot_interval)
plt.plot(lists, accuracies_train, label="training set")
plt.plot(lists, accuracies_test,  label="test set")
plt.legend(loc="lower right")
plt.title("accuracy")
plt.xlabel("count")
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
# グラフの表示
plt.show()

ReLU - He

import numpy as np
from data.mnist import load_mnist
from PIL import Image
import pickle
from common import functions
import matplotlib.pyplot as plt

# mnistをロード
(x_train, d_train), (x_test, d_test) = load_mnist(normalize=True, one_hot_label=True)
train_size = len(x_train)
print("データ読み込み完了")
# 重み初期値補正係数
wieght_init = 0.01
# 入力層サイズ
input_layer_size = 784
# 中間層サイズ
hidden_layer_1_size = 40
hidden_layer_2_size = 20
# 出力層サイズ
output_layer_size = 10
# 繰り返し数
iters_num = 2000
# ミニバッチサイズ
batch_size = 100
# 学習率
learning_rate = 0.1
# 描写頻度
plot_interval=10
# 初期設定
def init_network():
    network = {} 
    ###########  変更箇所  ##############
    # Heの初期値
    network['W1'] = np.random.randn(input_layer_size, hidden_layer_1_size) / np.sqrt(input_layer_size) * np.sqrt(2)
    network['W2'] = np.random.randn(hidden_layer_1_size, hidden_layer_2_size) / np.sqrt(hidden_layer_1_size) * np.sqrt(2)
    network['W3'] = np.random.randn(hidden_layer_2_size, output_layer_size) / np.sqrt(hidden_layer_2_size) * np.sqrt(2)
    #################################
    network['b1'] = np.zeros(hidden_layer_1_size)
    network['b2'] = np.zeros(hidden_layer_2_size)
    network['b3'] = np.zeros(output_layer_size)
    return network

# 順伝播
def forward(network, x):
    W1, W2, W3 = network['W1'], network['W2'], network['W3']
    b1, b2, b3 = network['b1'], network['b2'], network['b3']
    ###########  変更箇所  ##############
    hidden_f = functions.relu
    #################################
    u1 =  np.dot(x, W1) + b1
    z1 = hidden_f(u1)
    u2 =  np.dot(z1, W2) + b2
    z2 = hidden_f(u2)
    u3 =  np.dot(z2, W3) + b3
    y = functions.softmax(u3)
    return z1, z2, y

# 誤差逆伝播
def backward(x, d, z1, z2, y):
    grad = {}
    W1, W2, W3 = network['W1'], network['W2'], network['W3']
    b1, b2, b3 = network['b1'], network['b2'], network['b3']
    ###########  変更箇所  ##############
    hidden_d_f = functions.d_relu
    #################################
    # 出力層でのデルタ
    delta3 = functions.d_softmax_with_loss(d, y)
    # b3の勾配
    grad['b3'] = np.sum(delta3, axis=0)
    # W3の勾配
    grad['W3'] = np.dot(z2.T, delta3)
    # 2層でのデルタ
    delta2 = np.dot(delta3, W3.T) * hidden_d_f(z2)
    # b2の勾配
    grad['b2'] = np.sum(delta2, axis=0)
    # W2の勾配
    grad['W2'] = np.dot(z1.T, delta2)
    # 1層でのデルタ
    delta1 = np.dot(delta2, W2.T) * hidden_d_f(z1)
    # b1の勾配
    grad['b1'] = np.sum(delta1, axis=0)
    # W1の勾配
    grad['W1'] = np.dot(x.T, delta1)
    return grad

# パラメータの初期化
network = init_network()
accuracies_train = []
accuracies_test = []
# 正答率
def accuracy(x, d):
    z1, z2, y = forward(network, x)
    y = np.argmax(y, axis=1)
    if d.ndim != 1 : d = np.argmax(d, axis=1)
    accuracy = np.sum(y == d) / float(x.shape[0])
    return accuracy

for i in range(iters_num):
    # ランダムにバッチを取得    
    batch_mask = np.random.choice(train_size, batch_size)
    # ミニバッチに対応する教師訓練画像データを取得    
    x_batch = x_train[batch_mask]
    # ミニバッチに対応する訓練正解ラベルデータを取得する
    d_batch = d_train[batch_mask]
    z1, z2, y = forward(network, x_batch)
    grad = backward(x_batch, d_batch, z1, z2, y)
    if (i+1)%plot_interval==0:
        accr_test = accuracy(x_test, d_test)
        accuracies_test.append(accr_test)
        accr_train = accuracy(x_batch, d_batch)
        accuracies_train.append(accr_train)
        print('Generation: ' + str(i+1) + '. 正答率(トレーニング) = ' + str(accr_train))
        print('                : ' + str(i+1) + '. 正答率(テスト) = ' + str(accr_test))
    # パラメータに勾配適用
    for key in ('W1', 'W2', 'W3', 'b1', 'b2', 'b3'):
        network[key]  -= learning_rate * grad[key]
lists = range(0, iters_num, plot_interval)
plt.plot(lists, accuracies_train, label="training set")
plt.plot(lists, accuracies_test,  label="test set")
plt.legend(loc="lower right")
plt.title("accuracy")
plt.xlabel("count")
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
# グラフの表示
plt.show()

【確認テスト】

Q.連鎖律の原理を使い、dz/dxを求めよ。

A.

Q.シグモイド関数を微分した時、入力値が0の時に最大値をとる。その値として正しいものを選択肢から選べ。
(1) 0.15 (2) 0.25 (3) 0.35 (4) 0.45
A.(2)

Q.重みの初期値に0に設定すると、どのような問題が発生するか。簡潔に説明せよ。
A.全ての値が同じ値で伝わるためパラメータのチューニングが行われなくなる。

Q.一般的に考えられるバッチ正規化の効果を2点挙げよ。
A.

計算の高速化
勾配消失が起こりづらくなる

【演習問題】

Section2　学習率最適化手法

モメンタム(Momentum)

局所的最適解にはならず、大域的最適解となる。
谷間に着いてからも最も低い位置（最適値）に行くまでの時間が早い。

AdaGrad

勾配の緩やかな斜面に対して、最適値に近づける、

RMSProp

局所的最適解にはならず、大域的最適解となる。
ハイパーパラメータの調整が必要な場合が少ない。

Adam

モメンタムとRMSPropの双方のメリットを持つ。

【考察】

【実装演習結果】

optimizer

SGD

import sys, os
sys.path.append(os.pardir)  # 親ディレクトリのファイルをインポートするための設定
import numpy as np
from collections import OrderedDict
from common import layers
from data.mnist import load_mnist
import matplotlib.pyplot as plt
from multi_layer_net import MultiLayerNet
# データの読み込み
(x_train, d_train), (x_test, d_test) = load_mnist(normalize=True, one_hot_label=True)
print("データ読み込み完了")
# batch_normalizationの設定 ================================
# use_batchnorm = True
use_batchnorm = False
# ====================================================
network = MultiLayerNet(input_size=784, hidden_size_list=[40, 20], output_size=10, activation='sigmoid', weight_init_std=0.01,
                       use_batchnorm=use_batchnorm)
iters_num = 1000
train_size = x_train.shape[0]
batch_size = 100
learning_rate = 0.01
train_loss_list = []
accuracies_train = []
accuracies_test = []
plot_interval=10
for i in range(iters_num):
    batch_mask = np.random.choice(train_size, batch_size)
    x_batch = x_train[batch_mask]
    d_batch = d_train[batch_mask]
    # 勾配
    grad = network.gradient(x_batch, d_batch)
    for key in ('W1', 'W2', 'W3', 'b1', 'b2', 'b3'):
        network.params[key] -= learning_rate * grad[key]
        loss = network.loss(x_batch, d_batch)
        train_loss_list.append(loss)
    if (i + 1) % plot_interval == 0:
        accr_test = network.accuracy(x_test, d_test)
        accuracies_test.append(accr_test)        
        accr_train = network.accuracy(x_batch, d_batch)
        accuracies_train.append(accr_train)
        print('Generation: ' + str(i+1) + '. 正答率(トレーニング) = ' + str(accr_train))
        print('                : ' + str(i+1) + '. 正答率(テスト) = ' + str(accr_test))
lists = range(0, iters_num, plot_interval)
plt.plot(lists, accuracies_train, label="training set")
plt.plot(lists, accuracies_test,  label="test set")
plt.legend(loc="lower right")
plt.title("accuracy")
plt.xlabel("count")
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
# グラフの表示
plt.show()

Momentum

# データの読み込み
(x_train, d_train), (x_test, d_test) = load_mnist(normalize=True, one_hot_label=True)
print("データ読み込み完了")
# batch_normalizationの設定 ================================
# use_batchnorm = True
use_batchnorm = False
# ====================================================
network = MultiLayerNet(input_size=784, hidden_size_list=[40, 20], output_size=10, activation='sigmoid', weight_init_std=0.01,
                       use_batchnorm=use_batchnorm)
iters_num = 1000
train_size = x_train.shape[0]
batch_size = 100
learning_rate = 0.01
# 慣性
momentum = 0.9
train_loss_list = []
accuracies_train = []
accuracies_test = []
plot_interval=10
for i in range(iters_num):
    batch_mask = np.random.choice(train_size, batch_size)
    x_batch = x_train[batch_mask]
    d_batch = d_train[batch_mask]
    # 勾配
    grad = network.gradient(x_batch, d_batch)
    if i == 0:
        v = {}
    for key in ('W1', 'W2', 'W3', 'b1', 'b2', 'b3'):
        if i == 0:
            v[key] = np.zeros_like(network.params[key])
        v[key] = momentum * v[key] - learning_rate * grad[key]
        network.params[key] += v[key]
        loss = network.loss(x_batch, d_batch)
        train_loss_list.append(loss)
    if (i + 1) % plot_interval == 0:
        accr_test = network.accuracy(x_test, d_test)
        accuracies_test.append(accr_test)        
        accr_train = network.accuracy(x_batch, d_batch)
        accuracies_train.append(accr_train)
        print('Generation: ' + str(i+1) + '. 正答率(トレーニング) = ' + str(accr_train))
        print('                : ' + str(i+1) + '. 正答率(テスト) = ' + str(accr_test))
lists = range(0, iters_num, plot_interval)
plt.plot(lists, accuracies_train, label="training set")
plt.plot(lists, accuracies_test,  label="test set")
plt.legend(loc="lower right")
plt.title("accuracy")
plt.xlabel("count")
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
# グラフの表示
plt.show()

MomentumをもとにAdaGradを作ってみよう

θ = 1e-4 とする

# AdaGradを作ってみよう
# データの読み込み
(x_train, d_train), (x_test, d_test) = load_mnist(normalize=True, one_hot_label=True)
print("データ読み込み完了")
# batch_normalizationの設定 ================================
# use_batchnorm = True
use_batchnorm = False
# ====================================================
network = MultiLayerNet(input_size=784, hidden_size_list=[40, 20], output_size=10, activation='sigmoid', weight_init_std=0.01,
                       use_batchnorm=use_batchnorm)
iters_num = 1000
# iters_num = 500 # 処理を短縮
train_size = x_train.shape[0]
batch_size = 100
learning_rate = 0.01
# AdaGradでは不必要
# =============================
momentum = 0.9 
# =============================
train_loss_list = []
accuracies_train = []
accuracies_test = []
plot_interval=10
for i in range(iters_num):
    batch_mask = np.random.choice(train_size, batch_size)
    x_batch = x_train[batch_mask]
    d_batch = d_train[batch_mask]
    # 勾配
    grad = network.gradient(x_batch, d_batch)
    if i == 0:
        h = {}
    for key in ('W1', 'W2', 'W3', 'b1', 'b2', 'b3'):    
        # 変更しよう  
        # ===========================================
        if i == 0:
            h[key] = np.zeros_like(network.params[key])        
        h[key] = momentum * h[key] - learning_rate * grad[key]
        network.params[key] += h[key]

        # ===========================================
        loss = network.loss(x_batch, d_batch)
        train_loss_list.append(loss)
    if (i + 1) % plot_interval == 0:
        accr_test = network.accuracy(x_test, d_test)
        accuracies_test.append(accr_test)        
        accr_train = network.accuracy(x_batch, d_batch)
        accuracies_train.append(accr_train)
        print('Generation: ' + str(i+1) + '. 正答率(トレーニング) = ' + str(accr_train))
        print('                : ' + str(i+1) + '. 正答率(テスト) = ' + str(accr_test))
lists = range(0, iters_num, plot_interval)
plt.plot(lists, accuracies_train, label="training set")
plt.plot(lists, accuracies_test,  label="test set")
plt.legend(loc="lower right")
plt.title("accuracy")
plt.xlabel("count")
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
# グラフの表示
plt.show()

RSMprop

# データの読み込み
(x_train, d_train), (x_test, d_test) = load_mnist(normalize=True, one_hot_label=True)
print("データ読み込み完了")
# batch_normalizationの設定 ================================
# use_batchnorm = True
use_batchnorm = False
# ====================================================
network = MultiLayerNet(input_size=784, hidden_size_list=[40, 20], output_size=10, activation='sigmoid', weight_init_std=0.01,
                       use_batchnorm=use_batchnorm)
iters_num = 1000
train_size = x_train.shape[0]
batch_size = 100
learning_rate = 0.01
decay_rate = 0.99
train_loss_list = []
accuracies_train = []
accuracies_test = []
plot_interval=10
for i in range(iters_num):
    batch_mask = np.random.choice(train_size, batch_size)
    x_batch = x_train[batch_mask]
    d_batch = d_train[batch_mask]
    # 勾配
    grad = network.gradient(x_batch, d_batch)
    if i == 0:
        h = {}
    for key in ('W1', 'W2', 'W3', 'b1', 'b2', 'b3'):
        if i == 0:
            h[key] = np.zeros_like(network.params[key])
        h[key] *= decay_rate
        h[key] += (1 - decay_rate) * np.square(grad[key])
        network.params[key] -= learning_rate * grad[key] / (np.sqrt(h[key]) + 1e-7)
        loss = network.loss(x_batch, d_batch)
        train_loss_list.append(loss)                
    if (i + 1) % plot_interval == 0:
        accr_test = network.accuracy(x_test, d_test)
        accuracies_test.append(accr_test)        
        accr_train = network.accuracy(x_batch, d_batch)
        accuracies_train.append(accr_train)
        print('Generation: ' + str(i+1) + '. 正答率(トレーニング) = ' + str(accr_train))
        print('                : ' + str(i+1) + '. 正答率(テスト) = ' + str(accr_test))
lists = range(0, iters_num, plot_interval)
plt.plot(lists, accuracies_train, label="training set")
plt.plot(lists, accuracies_test,  label="test set")
plt.legend(loc="lower right")
plt.title("accuracy")
plt.xlabel("count")
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
# グラフの表示
plt.show()

Adam

# データの読み込み
(x_train, d_train), (x_test, d_test) = load_mnist(normalize=True, one_hot_label=True)
print("データ読み込み完了")
# batch_normalizationの設定 ================================
# use_batchnorm = True
use_batchnorm = False
# ====================================================
network = MultiLayerNet(input_size=784, hidden_size_list=[40, 20], output_size=10, activation='sigmoid', weight_init_std=0.01,
                       use_batchnorm=use_batchnorm)
iters_num = 1000
train_size = x_train.shape[0]
batch_size = 100
learning_rate = 0.01
beta1 = 0.9
beta2 = 0.999
train_loss_list = []
accuracies_train = []
accuracies_test = []
plot_interval=10
for i in range(iters_num):
    batch_mask = np.random.choice(train_size, batch_size)
    x_batch = x_train[batch_mask]
    d_batch = d_train[batch_mask]
    # 勾配
    grad = network.gradient(x_batch, d_batch)
    if i == 0:
        m = {}
        v = {}
    learning_rate_t  = learning_rate * np.sqrt(1.0 - beta2 ** (i + 1)) / (1.0 - beta1 ** (i + 1))    
    for key in ('W1', 'W2', 'W3', 'b1', 'b2', 'b3'):
        if i == 0:
            m[key] = np.zeros_like(network.params[key])
            v[key] = np.zeros_like(network.params[key])
        m[key] += (1 - beta1) * (grad[key] - m[key])
        v[key] += (1 - beta2) * (grad[key] ** 2 - v[key])            
        network.params[key] -= learning_rate_t * m[key] / (np.sqrt(v[key]) + 1e-7)
    if (i + 1) % plot_interval == 0:
        accr_test = network.accuracy(x_test, d_test)
        accuracies_test.append(accr_test)        
        accr_train = network.accuracy(x_batch, d_batch)
        accuracies_train.append(accr_train)
        loss = network.loss(x_batch, d_batch)
        train_loss_list.append(loss)        
        print('Generation: ' + str(i+1) + '. 正答率(トレーニング) = ' + str(accr_train))
        print('                : ' + str(i+1) + '. 正答率(テスト) = ' + str(accr_test))
lists = range(0, iters_num, plot_interval)
plt.plot(lists, accuracies_train, label="training set")
plt.plot(lists, accuracies_test,  label="test set")
plt.legend(loc="lower right")
plt.title("accuracy")
plt.xlabel("count")
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
# グラフの表示
plt.show()

【確認テスト】

Q.モメンタム・AdaGrad・RMSPropの特徴をそれぞれ簡潔に説明せよ。
A.

モメンタム：谷間に落ちてから収束までのスピードが早い
AdaGrad：緩やかな斜面に対して最適値に近づきやすい
RMSProp：パラメータの調整が少ない

【演習問題】

Section3　過学習

訓練データには適合できるが、未知のデータには適合できていない状態
モデルの自由度が高いと過学習しやすくなる

正則化(Regularization)
- 過学習しないようにペナルティを課す方法
- 多層NNは正則化を施しても過学習してしまう
Weight decay(荷重減衰)
　- L1、L2正則化
Dropout
- 学習するたびに無効にするノードを変更

【考察】

【実装演習結果】

overfiting

import numpy as np
from collections import OrderedDict
from common import layers
from data.mnist import load_mnist
import matplotlib.pyplot as plt
from multi_layer_net import MultiLayerNet
from common import optimizer
(x_train, d_train), (x_test, d_test) = load_mnist(normalize=True)
print("データ読み込み完了")
# 過学習を再現するために、学習データを削減
x_train = x_train[:300]
d_train = d_train[:300]
network = MultiLayerNet(input_size=784, hidden_size_list=[100, 100, 100, 100, 100, 100], output_size=10)
optimizer = optimizer.SGD(learning_rate=0.01)
iters_num = 1000
train_size = x_train.shape[0]
batch_size = 100
train_loss_list = []
accuracies_train = []
accuracies_test = []
plot_interval=10
for i in range(iters_num):
    batch_mask = np.random.choice(train_size, batch_size)
    x_batch = x_train[batch_mask]
    d_batch = d_train[batch_mask]
    grad = network.gradient(x_batch, d_batch)
    optimizer.update(network.params, grad)
    loss = network.loss(x_batch, d_batch)
    train_loss_list.append(loss)
    if (i+1) % plot_interval == 0:
        accr_train = network.accuracy(x_train, d_train)
        accr_test = network.accuracy(x_test, d_test)
        accuracies_train.append(accr_train)
        accuracies_test.append(accr_test)
        print('Generation: ' + str(i+1) + '. 正答率(トレーニング) = ' + str(accr_train))
        print('                : ' + str(i+1) + '. 正答率(テスト) = ' + str(accr_test))        
lists = range(0, iters_num, plot_interval)
plt.plot(lists, accuracies_train, label="training set")
plt.plot(lists, accuracies_test,  label="test set")
plt.legend(loc="lower right")
plt.title("accuracy")
plt.xlabel("count")
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
# グラフの表示
plt.show()

weight decay

L2

from common import optimizer
(x_train, d_train), (x_test, d_test) = load_mnist(normalize=True)
print("データ読み込み完了")
# 過学習を再現するために、学習データを削減
x_train = x_train[:300]
d_train = d_train[:300]
network = MultiLayerNet(input_size=784, hidden_size_list=[100, 100, 100, 100, 100, 100], output_size=10)
iters_num = 1000
train_size = x_train.shape[0]
batch_size = 100
learning_rate=0.01
train_loss_list = []
accuracies_train = []
accuracies_test = []
plot_interval=10
hidden_layer_num = network.hidden_layer_num
# 正則化強度設定 ======================================
weight_decay_lambda = 0.1
# =================================================
for i in range(iters_num):
    batch_mask = np.random.choice(train_size, batch_size)
    x_batch = x_train[batch_mask]
    d_batch = d_train[batch_mask]
    grad = network.gradient(x_batch, d_batch)
    weight_decay = 0
    for idx in range(1, hidden_layer_num+1):
        grad['W' + str(idx)] = network.layers['Affine' + str(idx)].dW + weight_decay_lambda * network.params['W' + str(idx)]
        grad['b' + str(idx)] = network.layers['Affine' + str(idx)].db
        network.params['W' + str(idx)] -= learning_rate * grad['W' + str(idx)]
        network.params['b' + str(idx)] -= learning_rate * grad['b' + str(idx)]        
        weight_decay += 0.5 * weight_decay_lambda * np.sqrt(np.sum(network.params['W' + str(idx)] ** 2))
    loss = network.loss(x_batch, d_batch) + weight_decay
    train_loss_list.append(loss)          
    if (i+1) % plot_interval == 0:
        accr_train = network.accuracy(x_train, d_train)
        accr_test = network.accuracy(x_test, d_test)
        accuracies_train.append(accr_train)
        accuracies_test.append(accr_test)  
        print('Generation: ' + str(i+1) + '. 正答率(トレーニング) = ' + str(accr_train))
        print('                : ' + str(i+1) + '. 正答率(テスト) = ' + str(accr_test))               
lists = range(0, iters_num, plot_interval)
plt.plot(lists, accuracies_train, label="training set")
plt.plot(lists, accuracies_test,  label="test set")
plt.legend(loc="lower right")
plt.title("accuracy")
plt.xlabel("count")
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
# グラフの表示
plt.show()

L1

(x_train, d_train), (x_test, d_test) = load_mnist(normalize=True)
print("データ読み込み完了")
# 過学習を再現するために、学習データを削減
x_train = x_train[:300]
d_train = d_train[:300]
network = MultiLayerNet(input_size=784, hidden_size_list=[100, 100, 100, 100, 100, 100], output_size=10)
iters_num = 1000
train_size = x_train.shape[0]
batch_size = 100
learning_rate=0.1
train_loss_list = []
accuracies_train = []
accuracies_test = []
plot_interval=10
hidden_layer_num = network.hidden_layer_num
# 正則化強度設定 ======================================
weight_decay_lambda = 0.005
# =================================================
for i in range(iters_num):
    batch_mask = np.random.choice(train_size, batch_size)
    x_batch = x_train[batch_mask]
    d_batch = d_train[batch_mask]
    grad = network.gradient(x_batch, d_batch)
    weight_decay = 0
    for idx in range(1, hidden_layer_num+1):
        grad['W' + str(idx)] = network.layers['Affine' + str(idx)].dW + weight_decay_lambda * np.sign(network.params['W' + str(idx)])
        grad['b' + str(idx)] = network.layers['Affine' + str(idx)].db
        network.params['W' + str(idx)] -= learning_rate * grad['W' + str(idx)]
        network.params['b' + str(idx)] -= learning_rate * grad['b' + str(idx)]        
        weight_decay += weight_decay_lambda * np.sum(np.abs(network.params['W' + str(idx)]))
    loss = network.loss(x_batch, d_batch) + weight_decay
    train_loss_list.append(loss)        
    if (i+1) % plot_interval == 0:
        accr_train = network.accuracy(x_train, d_train)
        accr_test = network.accuracy(x_test, d_test)
        accuracies_train.append(accr_train)
        accuracies_test.append(accr_test)
        print('Generation: ' + str(i+1) + '. 正答率(トレーニング) = ' + str(accr_train))
        print('                : ' + str(i+1) + '. 正答率(テスト) = ' + str(accr_test))                      
lists = range(0, iters_num, plot_interval)
plt.plot(lists, accuracies_train, label="training set")
plt.plot(lists, accuracies_test,  label="test set")
plt.legend(loc="lower right")
plt.title("accuracy")
plt.xlabel("count")
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
# グラフの表示
plt.show()

Dropout

class Dropout:
    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

from common import optimizer
(x_train, d_train), (x_test, d_test) = load_mnist(normalize=True)
print("データ読み込み完了")
# 過学習を再現するために、学習データを削減
x_train = x_train[:300]
d_train = d_train[:300]
# ドロップアウト設定 ======================================
use_dropout = True
dropout_ratio = 0.15
# ====================================================
network = MultiLayerNet(input_size=784, hidden_size_list=[100, 100, 100, 100, 100, 100], output_size=10,
                        weight_decay_lambda=weight_decay_lambda, use_dropout = use_dropout, dropout_ratio = dropout_ratio)
optimizer = optimizer.SGD(learning_rate=0.01)
# optimizer = optimizer.Momentum(learning_rate=0.01, momentum=0.9)
# optimizer = optimizer.AdaGrad(learning_rate=0.01)
# optimizer = optimizer.Adam()
iters_num = 1000
train_size = x_train.shape[0]
batch_size = 100
train_loss_list = []
accuracies_train = []
accuracies_test = []
plot_interval=10
for i in range(iters_num):
    batch_mask = np.random.choice(train_size, batch_size)
    x_batch = x_train[batch_mask]
    d_batch = d_train[batch_mask]
    grad = network.gradient(x_batch, d_batch)
    optimizer.update(network.params, grad)
    loss = network.loss(x_batch, d_batch)
    train_loss_list.append(loss)    
    if (i+1) % plot_interval == 0:
        accr_train = network.accuracy(x_train, d_train)
        accr_test = network.accuracy(x_test, d_test)
        accuracies_train.append(accr_train)
        accuracies_test.append(accr_test)
        print('Generation: ' + str(i+1) + '. 正答率(トレーニング) = ' + str(accr_train))
        print('                : ' + str(i+1) + '. 正答率(テスト) = ' + str(accr_test))        
lists = range(0, iters_num, plot_interval)
plt.plot(lists, accuracies_train, label="training set")
plt.plot(lists, accuracies_test,  label="test set")
plt.legend(loc="lower right")
plt.title("accuracy")
plt.xlabel("count")
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
# グラフの表示
plt.show()

Dropout + L1

from common import optimizer
(x_train, d_train), (x_test, d_test) = load_mnist(normalize=True)
print("データ読み込み完了")
# 過学習を再現するために、学習データを削減
x_train = x_train[:300]
d_train = d_train[:300]
# ドロップアウト設定 ======================================
use_dropout = True
dropout_ratio = 0.08
# ====================================================
network = MultiLayerNet(input_size=784, hidden_size_list=[100, 100, 100, 100, 100, 100], output_size=10,
                        use_dropout = use_dropout, dropout_ratio = dropout_ratio)
iters_num = 1000
train_size = x_train.shape[0]
batch_size = 100
learning_rate=0.01
train_loss_list = []
accuracies_train = []
accuracies_test = []
hidden_layer_num = network.hidden_layer_num
plot_interval=10
# 正則化強度設定 ======================================
weight_decay_lambda=0.004
# =================================================
for i in range(iters_num):
    batch_mask = np.random.choice(train_size, batch_size)
    x_batch = x_train[batch_mask]
    d_batch = d_train[batch_mask]
    grad = network.gradient(x_batch, d_batch)
    weight_decay = 0
    for idx in range(1, hidden_layer_num+1):
        grad['W' + str(idx)] = network.layers['Affine' + str(idx)].dW + weight_decay_lambda * np.sign(network.params['W' + str(idx)])
        grad['b' + str(idx)] = network.layers['Affine' + str(idx)].db
        network.params['W' + str(idx)] -= learning_rate * grad['W' + str(idx)]
        network.params['b' + str(idx)] -= learning_rate * grad['b' + str(idx)]        
        weight_decay += weight_decay_lambda * np.sum(np.abs(network.params['W' + str(idx)]))
    loss = network.loss(x_batch, d_batch) + weight_decay
    train_loss_list.append(loss)        
    if (i+1) % plot_interval == 0:
        accr_train = network.accuracy(x_train, d_train)
        accr_test = network.accuracy(x_test, d_test)
        accuracies_train.append(accr_train)
        accuracies_test.append(accr_test)
        print('Generation: ' + str(i+1) + '. 正答率(トレーニング) = ' + str(accr_train))
        print('                : ' + str(i+1) + '. 正答率(テスト) = ' + str(accr_test))               
lists = range(0, iters_num, plot_interval)
plt.plot(lists, accuracies_train, label="training set")
plt.plot(lists, accuracies_test,  label="test set")
plt.legend(loc="lower right")
plt.title("accuracy")
plt.xlabel("count")
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
# グラフの表示
plt.show()

【確認テスト】

Q.下図について、L1正則化を表しているグラフはどちらか答えよ。
A.Lasso推定量がL1正則化

【演習問題】

Section4　畳み込みニューラルネットワークの概念

畳み込み層
- バイアス
- パディング
- ストライド
- チャンネル
プーリング層

【考察】

【実装演習結果】

simple convolution network

image to column

import pickle
import numpy as np
from collections import OrderedDict
from common import layers
from common import optimizer
from data.mnist import load_mnist
import matplotlib.pyplot as plt

# 画像データを２次元配列に変換
'''
input_data: 入力値
filter_h: フィルターの高さ
filter_w: フィルターの横幅
stride: ストライド
pad: パディング
'''
def im2col(input_data, filter_h, filter_w, stride=1, pad=0):
    # N: number, C: channel, H: height, W: width
    N, C, H, W = input_data.shape
    # 切り捨て除算
    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) # (N, C, filter_h, filter_w, out_h, out_w) -> (N, filter_w, out_h, out_w, C, filter_h)    
    
    col = col.reshape(N * out_h * out_w, -1)
    return col

# im2colの処理確認
input_data = np.random.rand(2, 1, 4, 4)*100//1 # number, channel, height, widthを表す
print('========== input_data ===========\n', input_data)
print('==============================')
filter_h = 3
filter_w = 3
stride = 1
pad = 0
col = im2col(input_data, filter_h=filter_h, filter_w=filter_w, stride=stride, pad=pad)
print('============= col ==============\n', col)
print('==============================')

column to image

# ２次元配列を画像データに変換
def col2im(col, input_shape, filter_h, filter_w, stride=1, pad=0):
    # N: number, C: channel, H: height, W: width
    N, C, H, W = input_shape
    # 切り捨て除算    
    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) # (N, filter_h, filter_w, out_h, out_w, C)

    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]

img = col2im(col, input_shape=input_data.shape, filter_h=filter_h, filter_w=filter_w, stride=stride, pad=pad)
print(img)

convolution class

class Convolution:
    # W: フィルター, b: バイアス
    def __init__(self, W, b, stride=1, pad=0):
        self.W = W
        self.b = b
        self.stride = stride
        self.pad = pad
        
        # 中間データ（backward時に使用）
        self.x = None   
        self.col = None
        self.col_W = None
        
        # フィルター・バイアスパラメータの勾配
        self.dW = None
        self.db = None

    def forward(self, x):
        # FN: filter_number, C: channel, FH: filter_height, FW: filter_width
        FN, C, FH, FW = self.W.shape
        N, C, H, W = x.shape
        # 出力値のheight, width
        out_h = 1 + int((H + 2 * self.pad - FH) / self.stride)
        out_w = 1 + int((W + 2 * self.pad - FW) / self.stride)
        
        # xを行列に変換
        col = im2col(x, FH, FW, self.stride, self.pad)
        # フィルターをxに合わせた行列に変換
        col_W = self.W.reshape(FN, -1).T

        out = np.dot(col, col_W) + self.b
        # 計算のために変えた形式を戻す
        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)
        # dcolを画像データに変換
        dx = col2im(dcol, self.x.shape, FH, FW, self.stride, self.pad)

        return dx

pooling class

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)
        
        # xを行列に変換
        col = im2col(x, self.pool_h, self.pool_w, self.stride, self.pad)
        # プーリングのサイズに合わせてリサイズ
        col = col.reshape(-1, self.pool_h*self.pool_w)
        
        #maxプーリング
        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

simple convolution network class

class SimpleConvNet:
    # conv - relu - pool - affine - relu - affine - softmax
    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):
        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))

        # 重みの初期化
        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)

        # レイヤの生成
        self.layers = OrderedDict()
        self.layers['Conv1'] = layers.Convolution(self.params['W1'], self.params['b1'], conv_param['stride'], conv_param['pad'])
        self.layers['Relu1'] = layers.Relu()
        self.layers['Pool1'] = layers.Pooling(pool_h=2, pool_w=2, stride=2)
        self.layers['Affine1'] = layers.Affine(self.params['W2'], self.params['b2'])
        self.layers['Relu2'] = layers.Relu()
        self.layers['Affine2'] = layers.Affine(self.params['W3'], self.params['b3'])

        self.last_layer = layers.SoftmaxWithLoss()

    def predict(self, x):
        for key in self.layers.keys():
            x = self.layers[key].forward(x)
        return x
        
    def loss(self, x, d):
        y = self.predict(x)
        return self.last_layer.forward(y, d)

    def accuracy(self, x, d, batch_size=100):
        if d.ndim != 1 : d = np.argmax(d, axis=1)
        
        acc = 0.0
        
        for i in range(int(x.shape[0] / batch_size)):
            tx = x[i*batch_size:(i+1)*batch_size]
            td = d[i*batch_size:(i+1)*batch_size]
            y = self.predict(tx)
            y = np.argmax(y, axis=1)
            acc += np.sum(y == td) 
        
        return acc / x.shape[0]

    def gradient(self, x, d):
        # forward
        self.loss(x, d)
        
        # backward
        dout = 1
        dout = self.last_layer.backward(dout)
        layers = list(self.layers.values())
        
        layers.reverse()
        for layer in layers:
            dout = layer.backward(dout)

        # 設定
        grad = {}
        grad['W1'], grad['b1'] = self.layers['Conv1'].dW, self.layers['Conv1'].db
        grad['W2'], grad['b2'] = self.layers['Affine1'].dW, self.layers['Affine1'].db
        grad['W3'], grad['b3'] = self.layers['Affine2'].dW, self.layers['Affine2'].db

        return grad

from common import optimizer
# データの読み込み
(x_train, d_train), (x_test, d_test) = load_mnist(flatten=False)
print("データ読み込み完了")
# 処理に時間のかかる場合はデータを削減 
x_train, d_train = x_train[:5000], d_train[:5000]
x_test, d_test = x_test[:1000], d_test[:1000]
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)
optimizer = optimizer.Adam()
iters_num = 1000
train_size = x_train.shape[0]
batch_size = 100
train_loss_list = []
accuracies_train = []
accuracies_test = []
plot_interval=10
for i in range(iters_num):
    batch_mask = np.random.choice(train_size, batch_size)
    x_batch = x_train[batch_mask]
    d_batch = d_train[batch_mask]
    grad = network.gradient(x_batch, d_batch)
    optimizer.update(network.params, grad)
    loss = network.loss(x_batch, d_batch)
    train_loss_list.append(loss)
    if (i+1) % plot_interval == 0:
        accr_train = network.accuracy(x_train, d_train)
        accr_test = network.accuracy(x_test, d_test)
        accuracies_train.append(accr_train)
        accuracies_test.append(accr_test)
        print('Generation: ' + str(i+1) + '. 正答率(トレーニング) = ' + str(accr_train))
        print('                : ' + str(i+1) + '. 正答率(テスト) = ' + str(accr_test))               
lists = range(0, iters_num, plot_interval)
plt.plot(lists, accuracies_train, label="training set")
plt.plot(lists, accuracies_test,  label="test set")
plt.legend(loc="lower right")
plt.title("accuracy")
plt.xlabel("count")
plt.ylabel("accuracy")
plt.ylim(0, 1.0)
# グラフの表示
plt.show()

【確認テスト】

Q.サイズ6x6の入力画像を、サイズ2x2のファイタで畳み込んだ時の出力画像のサイズを答えよ。なおストライドとパディングは1とする。
A.以下の式により、出力画像のサイズは7×7

【演習問題】

Section5　最新のCNN

AlexNet
- モデルの構造
  - 5層の畳み込み層およびプーリング層など、それに続く3層の全結合層から構成
- 過学習を防ぐ施策
  - サイズ4096の全結合層の出力にドロップアウトを使用

【考察】

【実装演習結果】

【確認テスト】

【演習問題】