python_study/fromScratch_example_ch6_batch_norm_test.py at master · 2changhyeon/python_study · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
# -*- coding: utf-8 -*-
"""
Created on Fri May 28 18:46:02 2021

@author: 이창현
"""

import sys, os
sys.path.append(os.pardir)  # 부모 디렉터리의 파일을 가져올 수 있도록 설정
import numpy as np
import matplotlib.pyplot as plt
from dataset.mnist import load_mnist
from common.multi_layer_net_extend import MultiLayerNetExtend
from common.optimizer import SGD, Adam

(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True)

# 학습 데이터를 줄임
x_train = x_train[:1000]
t_train = t_train[:1000]

max_epochs = 20
train_size = x_train.shape[0]
batch_size = 100
learning_rate = 0.01


def __train(weight_init_std):
    bn_network = MultiLayerNetExtend(input_size=784, hidden_size_list=[100, 100, 100, 100, 100], output_size=10,
                                    weight_init_std=weight_init_std, use_batchnorm=True)
    network = MultiLayerNetExtend(input_size=784, hidden_size_list=[100, 100, 100, 100, 100], output_size=10,
                                weight_init_std=weight_init_std)
    optimizer = SGD(lr=learning_rate)

    train_acc_list = []
    bn_train_acc_list = []

    iter_per_epoch = max(train_size / batch_size, 1)
    epoch_cnt = 0

    for i in range(1000000000):
        batch_mask = np.random.choice(train_size, batch_size)
        x_batch = x_train[batch_mask]
        t_batch = t_train[batch_mask]

        for _network in (bn_network, network):
            grads = _network.gradient(x_batch, t_batch)
            optimizer.update(_network.params, grads)

        if i % iter_per_epoch == 0:
            train_acc = network.accuracy(x_train, t_train)
            bn_train_acc = bn_network.accuracy(x_train, t_train)
            train_acc_list.append(train_acc)
            bn_train_acc_list.append(bn_train_acc)

            print("epoch:" + str(epoch_cnt) + " | " + str(train_acc) + " - " + str(bn_train_acc))

            epoch_cnt += 1
            if epoch_cnt >= max_epochs:
                break

    return train_acc_list, bn_train_acc_list


# 그래프 그리기==========
weight_scale_list = np.logspace(0, -4, num=16)
x = np.arange(max_epochs)

for i, w in enumerate(weight_scale_list):
    print( "============== " + str(i+1) + "/16" + " ==============")
    train_acc_list, bn_train_acc_list = __train(w)

    plt.subplot(4,4,i+1)
    plt.title("W:" + str(w))
    if i == 15:
        plt.plot(x, bn_train_acc_list, label='Batch Normalization', markevery=2)
        plt.plot(x, train_acc_list, linestyle = "--", label='Normal(without BatchNorm)', markevery=2)
    else:
        plt.plot(x, bn_train_acc_list, markevery=2)
        plt.plot(x, train_acc_list, linestyle="--", markevery=2)

    plt.ylim(0, 1.0)
    if i % 4:
        plt.yticks([])
    else:
        plt.ylabel("accuracy")
    if i < 12:
        plt.xticks([])
    else:
        plt.xlabel("epochs")
    plt.legend(loc='lower right')

plt.show()