準備

Googleドライブのマウント

from google.colab import drive
drive.mount('/content/drive')

Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount("/content/drive", force_remount=True).

sys.pathの設定

以下では，Googleドライブのマイドライブ直下にDNN_codeフォルダを置くことを仮定しています．必要に応じて，パスを変更してください．

import sys
sys.path.append('/content/drive/My Drive/DNN_code_colab_lesson_1_2')
sys.path.append('/content/drive/My Drive/DNN_code_colab_lesson_1_2/lesson_2')

optimizer

SGD

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()

データ読み込み完了

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 = 0.3
# 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()

データ読み込み完了

AdaGrad

# 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 = 0.1

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.full_like(network.params[key], 1e-4)
        else:
            h[key] += np.square(grad[key])
        network.params[key] -= learning_rate * grad[key] / (np.sqrt(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()

データ読み込み完了

RMSprop

# 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()
#【コメント】学習速い！
#【コメント】trainとtestに差があるのが気になる

データ読み込み完了

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)                
        
        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()
#【コメント】学習速い！
#【コメント】trainとtestに差はない

データ読み込み完了

---

[try] 活性化関数と重みの初期化方法を変更して違いを見てみよう

初期状態ではsigmoid - gauss
activationはReLU、weight_init_stdは別の数値や'Xavier'・'He'に変更可能

# 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='relu', weight_init_std="He",
                       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)                
        
        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()
#【コメント】最初からそこそこのacc。Heの効果？うまくいきすぎのような？

データ読み込み完了

[try] バッチ正規化をして変化を見てみよう

use_batchnormをTrueにしよう

---

# 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 = True
# ====================================================

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)                
        
        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()
#【コメント】学習速く安定しているような傾向

データ読み込み完了