# coding: utf-8
import os
import sys
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
import matplotlib.pyplot as plt
from mnistlist.dataset.mnist import load_mnist
from mnistlist.common.optimizer import SGD
from mnistlist.common.multi_layer_net import MultiLayerNet
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True)
# 過学習を再現するために、学習データを削減
x_train = x_train[:10]
t_train = t_train[:10]
# weight decay（荷重減衰）の設定 =======================
#weight_decay_lambda = 0 # weight decayを使用しない場合
weight_decay_lambda = 0.1
# ====================================================
network = MultiLayerNet(input_size=784, hidden_size_list=[100, 100, 100, 100, 100, 100], output_size=10,
weight_decay_lambda=weight_decay_lambda)
optimizer = SGD(lr=0.01)
max_epochs = 201
train_size = x_train.shape[0]
batch_size = 100
train_loss_list = []
# coding: utf-8
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
import matplotlib.pyplot as plt
from mnistlist.dataset.mnist import load_mnist
from mnistlist.ch04.two_layer_net import TwoLayerNet
# データの読み込み
(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 # 繰り返しの回数を適宜設定する
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]
# 勾配の計算