# coding: utf-8
import sys, os
sys.path.append(os.pardir) # 부모 디렉터리의 파일을 가져올 수 있도록 설정
import numpy as np
from dataset.mnistPy2 import load_mnist
from two_layer_net05 import TwoLayerNet
# 데이터 읽기
(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)
# 각 가중치의 절대 오차의 평균을 구한다.
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 os
import sys
sys.path.append(os.pardir) # 부모 디렉터리의 파일을 가져올 수 있도록 설정
import numpy as np
import matplotlib.pyplot as plt
from dataset.mnistPy2 import load_mnist
from common.util import smooth_curve
from common.multi_layer_net import MultiLayerNet
from common.optimizer import SGD
# 0. MNIST 데이터 읽기==========
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True)
train_size = x_train.shape[0]
batch_size = 128
max_iterations = 2000
# 1. 실험용 설정==========
weight_init_types = {'std=0.01': 0.01, 'Xavier': 'sigmoid', 'He': 'relu'}
optimizer = SGD(lr=0.01)
networks = {}
train_loss = {}
for key, weight_type in weight_init_types.items():
networks[key] = MultiLayerNet(input_size=784,
hidden_size_list=[100, 100, 100, 100],
output_size=10,
weight_init_std=weight_type)
train_loss[key] = []
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) # 부모 디렉터리의 파일을 가져올 수 있도록 설정
import numpy as np
import matplotlib.pyplot as plt
from dataset.mnistPy2 import load_mnist
from deep_convnet import DeepConvNet
from common.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()
# 매개변수 보관
network.save_params("deep_convnet_paramsPy2.pkl")
print("Saved Network Parameters!")
# coding: utf-8
import sys, os
sys.path.append(os.pardir) # 부모 디렉터리의 파일을 가져올 수 있도록 설정
import numpy as np
from dataset.mnistPy2 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) # 형상을 원래 이미지의 크기로 변형
print(img.shape) # (28, 28)
img_show(img)