def get_data():
"""
获取数据
"""
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True,
flatten=True,
one_hot_label=False)
return x_test, t_test
import sys, os
sys.path.append(os.pardir)
import numpy as np
from dataset.minist 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)
print(img.shape)
img = img.reshape(28, 28)
print(img.shape)
img_show(img)
# coding: utf-8
import os
import sys
sys.path.append(os.pardir) # 为了导入父目录的文件而进行的设定
import numpy as np + self.weight_decay_lambda * self.params['W' + str(idx)]
grads['b' + str(idx)] = self.layers['Affine' + str(idx)].d
import matplotlib.pyplot as plt
from dataset.minist import load_mnist
from commom.multi_layer_net_extend import MultiLayerNetExtend
from commom.trainer import Trainer
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True)
# 为了再现过拟合，减少学习数据
x_train = x_train[:300]
t_train = t_train[:300]
# 设定是否使用Dropuout，以及比例 ========================
use_dropout = True # 不使用Dropout的情况下为False
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, t_test,
epochs=301, mini_batch_size=100,
optimizer='sgd', optimizer_param={'lr': 0.01}, verbose=True)
trainer.train()
train_acc_list, test_acc_list = trainer.train_acc_list, trainer.test_acc_list
# TODO: load mnist data
import sys
import os
sys.path.append(os.pardir)
from dataset.minist import load_mnist
(x_train, t_train), (x_test, t_test) = load_mnist(flatten=True, normalize=False,one_hot_label=True)
# print(x_train.shape)
# print(t_train.shape)
# print(x_test.shape)
# print(t_test.shape)
# TODO: show the first img
import numpy as np
from PIL import Image
def img_show(img):
pil_img = Image.fromarray(np.uint8(img))
pil_img.show()
img = x_train[0]
label = t_train[0]
print(label)
print(img.shape)
img = img.reshape(28, 28) # 还原成原来的尺寸
print(img.shape)
# coding: utf-8
import sys, os
sys.path.append(os.pardir) # 为了导入父目录而进行的设定
import numpy as np
import matplotlib.pyplot as plt
from dataset.minist import load_mnist
from ch08.deep_convnet import DeepConvNet
from commom.trainer import Trainer
(x_train, t_train), (x_test, t_test) = load_mnist(flatten=False)
network = DeepConvNet()
trainer = Trainer(network,
x_train,
t_train,
x_test,
t_test,
epochs=20,
mini_batch_size=100,
optimizer='Adam',
optimizer_param={'lr': 0.001},
evaluate_sample_num_per_epoch=1000)
trainer.train()
# 保存参数
network.save_params("deep_convnet_params.pkl")
print("Saved Network Parameters!")
import sys, os
sys.path.append(os.pardir)
import numpy as np
from dataset.minist import load_mnist
from ch05.two_layer_net import TwoLayerNet
(x_train, t_train), (x_test, y_test) = load_mnist(normalize=True,
one_hot_label=True)
network = TwoLayerNet(input_size=784, hidden_size=50, output_size=10)
if __name__ == '__main__':
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))
def get_data():
(x_train, t_train), (x_test, t_test) = load_mnist(flatten=True,
normalize=True)
return x_test, t_test
