gradient_1d.py
# coding: utf-8
import numpy as np
import matplotlib.pylab as plt
def numerical_diff(f, x):
h = 1e-4 #0.0001
return (f(x+h) - f(x-h))/(2*h)
def function_1(x):
return 0.01*x**2 + 0.1*x
def tangent_line(f, x):
d = numerical_diff(f, x)
print(d)
y = f(x) - d*x
return lambda t: d*t + y
if __name__ == "__main__":
x = np.arange(0.0, 20.0, 0.1)
y = function_1(x)
plt.xlabel('x')
plt.ylabel('f(x)')
tf = tangent_line(funtion_1, 5)
y2 = tf(x)
plt.plot(x, y)
plt.plot(x, y2)
plt.show()
gradient_2d.py
# coding: utf-8
# cf.http://d.hatena.ne.jp/white_wheels/20100327/p3
import numpy as np
import matplotlib.pylab as plt
from mpl_tookits.mplot3d import Axes3D
def _numerical_gradient_no_batch(f, x):
h = 1e-4 # 0.0001
grad = np.zeros_like(x)
for idx in range(x.size):
tmp_val = x[idx]
x[idx] = float(tmp_val) + h
fxh1 = f(x) # f(x+h)
x[idx] = tmp_val - h
fxh2 = f(x) # f(x-h)
grad[idx] = (fxh1 - fxh2) / (2*h)
x[idx] = tmp_val
return grad
def numerical_gradient(f, X):
if X.ndim == 1:
return _numerical_gradient_no_batch(f, X)
else:
grad = np.zeros_like(X)
for idx, x in enumerate(X):
grad[idx] = _numerical_gradient_no_batch(f, x)
return grad
def function_2(x):
if x.ndim == 1:
return np.sum(x**2)
else:
return np.sum(x**2, axis=1)
def tangent_line(f, x):
d = numerical_gradient(f, x)
print(d)
y = f(x) - d*x
return lambda t: d*t + y
if __name__ == '__main__':
x0 = np.arange(-2, 2.5, 0.25)
x1 = np.arange(-2, 2.5, 0.25)
X, Y = np.meshgrid(x0, x1)
X = X.flatten()
Y = Y.flatten()
grad = numerical_gradient(function2, np.array([X, Y]))
plt.figure()
plt.quiver(X, Y, -grad[0], -grad[1], angles='xy', color='#6666666')#,headwith=10,scale=40,color='#444444'
plt.xlim([-2, 2])
plt.ylim([-2, 2])
plt.xlabel('x0')
plt.ylabel('x1')
plt.grid()
plt.legend()
plt.draw()
plt.show()
gradient_method.py
# coding: utf-8
import numpy as np
import matplotlib.pylab as plt
from gradient_2d import numerical_gradient
def gradient_descent(f, init_x, lr=0.01, stemp_num=100):
x = init_x
x_history = []
for i in range(stem_num):
x_history.append( x.copy() )
grad = numerical_gradient(f, x)
x -= lr * grad
return x, np.array(x_history)
def function_2(x):
return x[0]**2 + x[1]**2
if __name__ == '__main__':
init_x = np.array([-3.0, 4.0])
lr = 0.1
step_num = 20
x, x_history = gradient_descent(function_2, init_x, lr=lr, step_num=step_num)
plt.plot([-5, 5], [0, 0], '--b')
plt.plot([0, 0], [-5, 5], '--b')
plt.plot(x_history[:, 0], x_history[:,1], 'o')
plt.xlim(-3.5, 3.5)
plt.ylim(-4.5, 4.5)
plt.xlabel('X0')
plt.ylabel('X1')
plt.show()
gradient_update_process_3d.py
# coding: utf-8
import numpy as np
from matplotlib import pyplot as plt
from mpl_tookits.mplot3d import Axes3D
ratio = 1 # 控制函数扁平率
def gradient_descent(f, init_x, lr=0.01, step_num=100):
x = init_x
x_collection = []
y_collection = []
z_collection = []
print(x)
x_collection.append(x[0])
y_collection.append(x[1])
z = ratio * x[0]**2 + x[1]**2
z_collection.append(z)
for i in range(step_num):
grad = numerical_gradient(f, x)
x -= lr * grad
x_collection.append(x[0])
y_collection.append(x[1])
z = ratio * x[0]**2 + x[1]**2
z_collection.append(z)
return [x_collection, y_collection, z_collection)
def function_2(x):
results = []
for item in x:
result = ratio * item[0]**2+item[1]**2
results.append(result)
return results
def function_3(x):
return ratio * x[0]**2 + x[1]**2
def _numerical_gradient_no_batch(f, x):
h = 1e-4 # 0.0001
grad = np.zeros_like(x)
for idx in range(x.size):
tmp_val = x[idx]
# f(x+h)
x[idx] = tmp_val + h
fxh1 = f(x)
x[idx] = tmp_val - h
fxh2 = f(x)
grad[idx] = (fxh1 - fxh2) / (2 * h)
x[idx] = tmp_val
return grad
def numerical_gradient(f, X):
if X.ndim == 1:
return _numerical_gradient_no_batch(f, X)
else:
grad = np.zeros_like(X)
for idx, x in enumerate(X):
grad[idx] = _numerical_gradient_no_batch(f, x)
return grad
if __name__ == '__main__':
fig = plt.figure()
ax1 = plt.axes(projection='3d')
xx = np.arange(-440,440,0.5)
yy = np.arange(-140,140,0.5)
X, Y = np.meshgrid(xx, yy)
Z = ratio*X**2+Y**2
xy = gradient_descent(function_3,np.array([-400.0,-130.0]),lr=0.05,step_num=500)
ax1.plot_surface(X,Y,Z,alpha=0.3,cmap='winter')#绘制函数曲面
ax1.contour(X,Y,Z,zdir='z', offset=-20,cmap="rainbow")#绘制x-y平面等高线
ax1.scatter3D(xy[0],xy[1],zd,color='red',s=35) #绘制三维散点图
ax1.scatter(xy[0],xy[1]) #绘制x-y平面散点图
gradient_simplenet.py
# coding: utf-8
import sys, os
sys.path.append(os.pardir) # 为了导入父目录中的文件而进行的设定
import numpy as np
from common.functions import softmax, cross_entropy_error
from common.gradient import numerical_gradient
class simpleNet:
def __init__(self):
self.W = np.random.randn(2, 3)
def predict(self, x):
return np.dot(x, self.W)
def loss(self, x, t):
z = self.predict(x)
y = softmax(z)
loss = cross_entropy_error(y, t)
return loss
if __name__ == '__main__':
x = np.array([0.6, 0.9])
t = np.array([0, 0, 1])
net = simpleNet()
f = lambda w: net.loss(x, t)
dW = numerical_gradient(f, net.W)
print(dW)
two_layer_net.py
# coding: utf-8
import sys, os
sys.path.append(os.pardir) # 为了导入父目录的文件而进行的设定
from common.functions import *
from common.gradient import numerical_gradient
class TwoLayerNet:
def __init__(self, input_size, hidden_size, output_size, weight_init_std=0.0):
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)
def predict(self, x):
W1, W2 = self.params['W1'], self.params['W2']
b1, b2 = self.params['b1'], self.params['b2']
a1 = np.dot(x, W1) + b1
z1 = sigmoid(a1)
a2 = np.dot(z1, W2) + b2
y = softmax(a2)
return y
def loss(self, x, t):
y = self.predict(x)
return cross_entropy_error(y, t)
def accuracy(self, x, t):
y = self.predict(x)
y = np.argmax(y, axis=1)
t = np.argmax(t, axis=1)
accuracy = np.sum(y == t) / float(x.shape[0])
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):
W1, W2 = self.params['W1'], self.params['W2']
b1, b2 = self.params['b1'], self.params['b2']
grads = {}
batch_num = x.shape[0]
# forward
a1 = np.dot(x, W1) + b1
z1 = sigmoid(a1)
a2 = np.dot(z1, W2) + b2
y = softmax(a2)
# backward
dy = (y - t) / batch_num
grads['W2'] = np.dot(x.T, dy)
grads['b2'] = np.sum(dy, axis=0)
da1 = np.dot(dy, W2.T)
dz1 = sigmoid_grad(a1) * da1
grads['W1'] = np.dot(x.T, dz1)
grads['b1'] = np.sum(dz1, axis=0)
return grads
train_nueralnet.py
# coding: utf-8
import sys, os
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
import matplotlib.pyplot as plt
from dataset.mnist import load_mnist
from two_layer_net import TwoLayerNet
(x_train, t_train), (x_test, t_test) = load_mnist(normalize=True, one_hot_label=True)
network = TwoLayerNet(input_size=748, hidden_size=50, output_size=10)
iters_num = 1000000
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]
#grad = network.numerical_gradient(x_batch, t_batch)
grad = network.gradient(x_batch, t_batch)
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)
test_acc_list.append(test_acc)
train_acc_list.append(train_acc)
print('train acc, test acc | ', + str(train_acc) +','+str(test_acc))
markers = {'train':'o','test':'s'}
x = np.arange(len(train_acc_list))
plt.plot(x, train_acc_list, label='train_acc')
plt.plot(x, test_acc_list, label='test_acc', linestyle='--')
plt.xlabel('epochs')
plt.ylabel('accuracy')
plt.ylim(0, 1.0)
plt.legend(loc='lower right')
plt.show()
本章所学内容
- 机器学习中使用的数据集分为训练数据和测试数据
- 神经网路用训练数据进行学习,并用测试数据评价学习到的模型的泛化能力
- 神经网路的学习以损失函数为指标,更新权重参数,以使损失函数的值减小
- 利用某个给定的微小值的差分求导数的过程称为数值微分
- 利用数值微分,可以计算权重参数的梯度
- 数值微分虽然费时间,但是实现起来很简单,下一章中要实现的稍微复杂一些的误差反向传播法可以高效地计算梯度