# 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 DeepLearning.dataset.mnist import load_mnist
from DeepLearning.ch07.simple_convnet import SimpleConvNet
from DeepLearning.common.trainer import Trainer
# データの読み込み
(x_train, t_train), (x_test, t_test) = load_mnist(flatten=False)
# 処理に時間のかかる場合はデータを削減
#x_train, t_train = x_train[:5000], t_train[:5000]
#x_test, t_test = x_test[:1000], t_test[:1000]
max_epochs = 20
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)
trainer = Trainer(network,
x_train,
# 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 DeepLearning.dataset.mnist import load_mnist
from DeepLearning.common.multi_layer_net_extend import MultiLayerNetExtend
from DeepLearning.common.trainer import Trainer
(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[:300]
t_train = t_train[:300]
# Dropuoutの有無、割り合いの設定 ========================
use_dropout = True # Dropoutなしのときの場合はFalseに
dropout_ratio = 0.2
# ====================================================
network = MultiLayerNetExtend(input_size=784,
hidden_size_list=[100, 100, 100, 100, 100, 100],
output_size=10,
use_dropout=use_dropout,
dropout_ration=dropout_ratio)
trainer = Trainer(network,
x_train,
t_train,
x_test,
def get_data():
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True, flatten=True, one_hot_label=False)
return x_test, t_test
# 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
from DeepLearning.dataset.mnist import load_mnist
from DeepLearning.ch05.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)
x_batch = x_train[:3]
t_batch = t_train[:3]
grad_numerical = network.numerical_gradient(x_batch, t_batch)
grad_backprop = network.gradient(x_batch, t_batch)
for key in grad_numerical.keys():
diff = np.average( np.abs(grad_backprop[key] - grad_numerical[key]) )
print(key + ":" + str(diff))
# 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
from DeepLearning.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 = {0}'.format(label)) # 5
print('t_train[0].shape = {0}'.format(img.shape)) # (784,)
img = img.reshape(28, 28) # 形状を元の画像サイズに変形
print('t_train[0].reshape(28, 28) = {0}'.format(img.shape)) # (28, 28)
img_show(img)
print('t_tain[20].label = {0}'.format(t_train[20]))
img = x_train[20]
img = img.reshape(28, 28)
img_show(img)