def main():
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True,
flatten=True,
one_hot_label=True)
# print(batch_verify(x_test, t_test, init_network()))
# print(verify(x_test, t_test, init_network()))
print(test_cross_entropy_error(x_test, t_test, init_network()))
def __init__(self):
(self.x_train, self.t_train), (x_test, t_test) = load_mnist(
normalize=True, one_hot_label=True)
self.iter_num = 10000 # 学习次数
self.learn_rate = 0.3 # 学习率
self.batch_size = 100 # 批处理数量
self.train_size = self.x_train.shape[0] # 总训练数量
self.network = TwoLayerNet_Pro( # 初始化2层网络
input_size=784, hidden_size=50, output_size=10)
# self.network = TwoLayerNet_Pro2( # 初始化3层网络
# input_size=784, hidden_size1=100, hidden_size2=50, output_size=10)
# self.network = TwoLayerNet_Pro2( # 初始化4层网络
# input_size=784, hidden_size1=200, hidden_size2=100, hidden_size3=50, output_size=10)
self.train_loss = list()
self.acc_list = list()
import numpy as np
from source.ch_05.layer_net import TwoLayerNet
from source.dataset.mnist import load_mnist
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True,
one_hot_label=True)
iters_num = 10000
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)
network = TwoLayerNet(input_size=784, hidden_size=50, output_size=10)
for i in range(iters_num):
# print("Loop number: " + str(i))
batch_mask = np.random.choice(train_size, batch_size)
x_batch = x_train[batch_mask]
t_batch = t_train[batch_mask]
grads = network.gradient(x_batch, t_batch)
for key in ("W1", "W2", "b1", "b2"):
network.params[key] -= learning_rate * grads[key]
# 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
from source.dataset.mnist import load_mnist
from PIL import Image
def img_show(img):
pil_img = Image.fromarray(np.uint8(img))
pil_img.show()
(x_train, t_train), (x_test, t_test) = load_mnist(flatten=True,
normalize=False)
img = x_train[0]
label = t_train[0]
print(label) # 5
print(img.shape) # (784,)
img = img.reshape(28, 28) # 形状を元の画像サイズに変形
print(img.shape) # (28, 28)
img_show(img)