import numpy as np
class MulLayer:
def __init__(self):
self.x = None
self.y = None
def forward(self, x, y):
self.x = x
self.y = y
out = x * y
return out
def backward(self, dout):
dx = dout * self.y
dy = dout * self.x
return dx, dy
# coding: utf-8
import numpy as np
from mymodule.layer_naive import *
apple = 100
apple_num = 2
tax = 1.1
mul_apple_layer = MulLayer()
mul_tax_layer = MulLayer()
# forward
apple_price = mul_apple_layer.forward(apple, apple_num)
price = mul_tax_layer.forward(apple_price, tax)
# backward
dprice = 1
dapple_price, dtax = mul_tax_layer.backward(dprice)
dapple, dapple_num = mul_apple_layer.backward(dapple_price)
print("price:", int(price))
print("dApple:", dapple)
print("dApple_num:", int(dapple_num))
print("dTax:", dtax)
price: 220 dApple: 2.2 dApple_num: 110 dTax: 200
import numpy as np
class AddLayer:
def __init__(self):
pass
def forward(self, x, y):
out = x + y
return out
def backward(self, dout):
dx = dout * 1
dy = dout * 1
return dx, dy
# coding: utf-8
import numpy as np
from mymodule.layer_naive import *
apple = 100
apple_num = 2
orange = 150
orange_num = 3
tax = 1.1
# layer
mul_apple_layer = MulLayer()
mul_orange_layer = MulLayer()
add_apple_orange_layer = AddLayer()
mul_tax_layer = MulLayer()
# forward
apple_price = mul_apple_layer.forward(apple, apple_num) # (1)
orange_price = mul_orange_layer.forward(orange, orange_num) # (2)
all_price = add_apple_orange_layer.forward(apple_price, orange_price) # (3)
price = mul_tax_layer.forward(all_price, tax) # (4)
# backward
dprice = 1
dall_price, dtax = mul_tax_layer.backward(dprice) # (4)
dapple_price, dorange_price = add_apple_orange_layer.backward(dall_price) # (3)
dorange, dorange_num = mul_orange_layer.backward(dorange_price) # (2)
dapple, dapple_num = mul_apple_layer.backward(dapple_price) # (1)
print("price:", int(price))
print("dApple:", dapple)
print("dApple_num:", int(dapple_num))
print("dOrange:", dorange)
print("dOrange_num:", int(dorange_num))
print("dTax:", dtax)
price: 715 dApple: 2.2 dApple_num: 110 dOrange: 3.3000000000000003 dOrange_num: 165 dTax: 650
import numpy as np
x = np.array([[1.0, -0.5], [-2.0, 3.0]])
mask = (x <= 0)
print(mask)
[[False True] [ True False]]
import numpy as np
class Relu:
def __init__(self):
self.mask = None
def forward(self, x):
self.mask = (x <= 0)
out = x.copy()
out[self.mask] = 0
return out
def backward(self, dout):
dout[self.mask] = 0
dx = dout
return dx
import numpy as np
class Sigmoid:
def __init__(self):
self.out = None
def forward(self, x):
out = sigmoid(x)
self.out = out
return out
def backward(self, dout):
dx = dout * (1.0 - self.out) * self.out
return dx
import numpy as np
class Affine:
def __init__(self, W, b):
self.W =W
self.b = b
self.x = None
self.original_x_shape = None
# 重み・バイアスパラメータの微分
self.dW = None
self.db = None
def forward(self, x):
# テンソル対応
self.original_x_shape = x.shape
x = x.reshape(x.shape[0], -1)
self.x = x
out = np.dot(self.x, self.W) + self.b
return out
def backward(self, dout):
dx = np.dot(dout, self.W.T)
self.dW = np.dot(self.x.T, dout)
self.db = np.sum(dout, axis=0)
dx = dx.reshape(*self.original_x_shape) # 入力データの形状に戻す(テンソル対応)
return dx
class SoftmaxWithLoss:
def __init__(self):
self.loss = None
self.y = None # softmaxの出力
self.t = None # 教師データ
def forward(self, x, t):
self.t = t
self.y = softmax(x)
self.loss = cross_entropy_error(self.y, self.t)
return self.loss
def backward(self, dout=1):
batch_size = self.t.shape[0]
if self.t.size == self.y.size: # 教師データがone-hot-vectorの場合
dx = (self.y - self.t) / batch_size
else:
dx = self.y.copy()
dx[np.arange(batch_size), self.t] -= 1
dx = dx / batch_size
return dx
# 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 mymodule.layers import *
from mymodule.gradient import numerical_gradient
from collections import OrderedDict
class TwoLayerNet:
def __init__(self, input_size, hidden_size, output_size, weight_init_std = 0.01):
# 重みの初期化
self.params = {}
self.params['W1'] = weight_init_std * np.random.randn(input_size, hidden_size)
self.params['b1'] = np.zeros(hidden_size)
self.params['W2'] = weight_init_std * np.random.randn(hidden_size, output_size)
self.params['b2'] = np.zeros(output_size)
# レイヤの生成
self.layers = OrderedDict()
self.layers['Affine1'] = Affine(self.params['W1'], self.params['b1'])
self.layers['Relu1'] = Relu()
self.layers['Affine2'] = Affine(self.params['W2'], self.params['b2'])
self.lastLayer = SoftmaxWithLoss()
def predict(self, x):
for layer in self.layers.values():
x = layer.forward(x)
return x
# x:入力データ, t:教師データ
def loss(self, x, t):
y = self.predict(x)
return self.lastLayer.forward(y, t)
def accuracy(self, x, t):
y = self.predict(x)
y = np.argmax(y, axis=1)
if t.ndim != 1 : t = np.argmax(t, axis=1)
accuracy = np.sum(y == t) / float(x.shape[0])
return accuracy
# x:入力データ, t:教師データ
def numerical_gradient(self, x, t):
loss_W = lambda W: self.loss(x, t)
grads = {}
grads['W1'] = numerical_gradient(loss_W, self.params['W1'])
grads['b1'] = numerical_gradient(loss_W, self.params['b1'])
grads['W2'] = numerical_gradient(loss_W, self.params['W2'])
grads['b2'] = numerical_gradient(loss_W, self.params['b2'])
return grads
def gradient(self, x, t):
# forward
self.loss(x, t)
# backward
dout = 1
dout = self.lastLayer.backward(dout)
layers = list(self.layers.values())
layers.reverse()
for layer in layers:
dout = layer.backward(dout)
# 設定
grads = {}
grads['W1'], grads['b1'] = self.layers['Affine1'].dW, self.layers['Affine1'].db
grads['W2'], grads['b2'] = self.layers['Affine2'].dW, self.layers['Affine2'].db
return grads
# 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 mymodule.mnist import load_mnist
from mymodule.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))
W1:2.65339253248e-13 b1:7.42792047488e-13 W2:8.93400580132e-13 b2:1.20348178645e-10
# coding: utf-8
import sys, os
sys.path.append(os.pardir)
import numpy as np
from dataset.mnist import load_mnist
from mymodule.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
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
#grad = network.numerical_gradient(x_batch, t_batch)
grad = network.gradient(x_batch, t_batch)
# 更新
for key in ('W1', 'b1', 'W2', 'b2'):
network.params[key] -= learning_rate * grad[key]
loss = network.loss(x_batch, t_batch)
train_loss_list.append(loss)
if i % iter_per_epoch == 0:
train_acc = network.accuracy(x_train, t_train)
test_acc = network.accuracy(x_test, t_test)
train_acc_list.append(train_acc)
test_acc_list.append(test_acc)
print(train_acc, test_acc)
0.06215 0.0625 0.902966666667 0.9061 0.921516666667 0.9251 0.934316666667 0.9365 0.94705 0.9473 0.952183333333 0.9506 0.956283333333 0.9543 0.961233333333 0.9567 0.964783333333 0.9606 0.966466666667 0.9612 0.970933333333 0.964 0.9713 0.9669 0.97195 0.965 0.974666666667 0.9663 0.976066666667 0.9687 0.9772 0.9691 0.97815 0.9685