import numpy as np
from matplotlib import pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
# https://blog.csdn.net/weixin_39228381/article/details/108511882
def func(x, y):
return x * x / 20 + y * y
def paint_loss_func():
x = np.linspace(-50, 50, 100) # x的绘制范围是-50到50,从改区间均匀取100个数
y = np.linspace(-50, 50, 100) # y的绘制范围是-50到50,从改区间均匀取100个数
X, Y = np.meshgrid(x, y)
Z = func(X, Y)
fig = plt.figure() # figsize=(10, 10))
ax = Axes3D(fig)
plt.xlabel('x')
plt.ylabel('y')
ax.plot_surface(X, Y, Z, rstride=1, cstride=1, cmap='rainbow')
plt.show()
paint_loss_func()
运行结果:
特征:有全局最小值、是一个向x轴方向延伸的“碗”状函数
特征:Y轴方向梯度大,X轴方向梯度小;很多位置的梯度并没有指向最小位置(0,0)
# coding: utf-8
import numpy as np
import matplotlib.pyplot as plt
from collections import OrderedDict
class SGD:
"""随机梯度下降法(Stochastic Gradient Descent)"""
def __init__(self, lr=0.01):
self.lr = lr
def update(self, params, grads):
for key in params.keys():
params[key] -= self.lr * grads[key]
class Momentum:
"""Momentum SGD"""
def __init__(self, lr=0.01, momentum=0.9):
self.lr = lr
self.momentum = momentum
self.v = None
def update(self, params, grads):
if self.v is None:
self.v = {}
for key, val in params.items():
self.v[key] = np.zeros_like(val)
for key in params.keys():
self.v[key] = self.momentum * self.v[key] - self.lr * grads[key]
params[key] += self.v[key]
class Nesterov:
"""Nesterov's Accelerated Gradient (http://arxiv.org/abs/1212.0901)"""
def __init__(self, lr=0.01, momentum=0.9):
self.lr = lr
self.momentum = momentum
self.v = None
def update(self, params, grads):
if self.v is None:
self.v = {}
for key, val in params.items():
self.v[key] = np.zeros_like(val)
for key in params.keys():
self.v[key] *= self.momentum
self.v[key] -= self.lr * grads[key]
params[key] += self.momentum * self.momentum * self.v[key]
params[key] -= (1 + self.momentum) * self.lr * grads[key]
class AdaGrad:
"""AdaGrad"""
def __init__(self, lr=0.01):
self.lr = lr
self.h = None
def update(self, params, grads):
if self.h is None:
self.h = {}
for key, val in params.items():
self.h[key] = np.zeros_like(val)
for key in params.keys():
self.h[key] += grads[key] * grads[key]
params[key] -= self.lr * grads[key] / (np.sqrt(self.h[key]) + 1e-7)
class RMSprop:
"""RMSprop"""
def __init__(self, lr=0.01, decay_rate=0.99):
self.lr = lr
self.decay_rate = decay_rate
self.h = None
def update(self, params, grads):
if self.h is None:
self.h = {}
for key, val in params.items():
self.h[key] = np.zeros_like(val)
for key in params.keys():
self.h[key] *= self.decay_rate
self.h[key] += (1 - self.decay_rate) * grads[key] * grads[key]
params[key] -= self.lr * grads[key] / (np.sqrt(self.h[key]) + 1e-7)
class Adam:
"""Adam (http://arxiv.org/abs/1412.6980v8)"""
def __init__(self, lr=0.001, beta1=0.9, beta2=0.999):
self.lr = lr
self.beta1 = beta1
self.beta2 = beta2
self.iter = 0
self.m = None
self.v = None
def update(self, params, grads):
if self.m is None:
self.m, self.v = {}, {}
for key, val in params.items():
self.m[key] = np.zeros_like(val)
self.v[key] = np.zeros_like(val)
self.iter += 1
lr_t = self.lr * np.sqrt(1.0 - self.beta2 ** self.iter) / (1.0 - self.beta1 ** self.iter)
for key in params.keys():
self.m[key] += (1 - self.beta1) * (grads[key] - self.m[key])
self.v[key] += (1 - self.beta2) * (grads[key] ** 2 - self.v[key])
params[key] -= lr_t * self.m[key] / (np.sqrt(self.v[key]) + 1e-7)
def f(x, y):
return x ** 2 / 20.0 + y ** 2
def df(x, y):
return x / 10.0, 2.0 * y
init_pos = (-7.0, 2.0)
params = {}
params['x'], params['y'] = init_pos[0], init_pos[1]
grads = {}
grads['x'], grads['y'] = 0, 0
optimizers = OrderedDict()
optimizers["SGD"] = SGD(lr=0.95)
optimizers["Momentum"] = Momentum(lr=0.1)
optimizers["AdaGrad"] = AdaGrad(lr=1.5)
optimizers["Adam"] = Adam(lr=0.3)
idx = 1
for key in optimizers:
optimizer = optimizers[key]
x_history = []
y_history = []
params['x'], params['y'] = init_pos[0], init_pos[1]
for i in range(30):
x_history.append(params['x'])
y_history.append(params['y'])
grads['x'], grads['y'] = df(params['x'], params['y'])
optimizer.update(params, grads)
x = np.arange(-10, 10, 0.01)
y = np.arange(-5, 5, 0.01)
X, Y = np.meshgrid(x, y)
Z = f(X, Y)
# for simple contour line
mask = Z > 7
Z[mask] = 0
# plot
plt.subplot(2, 2, idx)
idx += 1
plt.plot(x_history, y_history, 'o-', color="red")
plt.contour(X, Y, Z) # 绘制等高线
plt.ylim(-10, 10)
plt.xlim(-10, 10)
plt.plot(0, 0, '+')
plt.title(key)
plt.xlabel("x")
plt.ylabel("y")
plt.subplots_adjust(wspace=0, hspace=0) # 调整子图间距
plt.show()
收敛效果排序依次为AdaGrad、Adam、Momentum、SGD。
是因为图像的变化并不均匀,所以y方向变化很大时,x方向变化很小,只能迂回往复地寻找,效率很低。
SGD
SGD是深度学习中最常见的优化方法之一,虽然是最常使用的优化方法,但是却有不少常见的问题。
learning rate不易确定,如果选择过小的话,收敛速度会很慢,如果太大,loss function就会在极小值处不停的震荡甚至偏离。每个参数的learning rate都是相同的,如果数据是稀疏的,则希望出现频率低的特征进行大一点的更新。深度神经网络之所以比较难训练,并不是因为容易进入局部最小,而是因为学习过程容易进入马鞍面中,在这种区域中,所有方向的梯度值几乎都是0。
Momentum(动量)
Momentum借助了物理中的动量的概念,即前几次的梯度也会参与计算。为了表示动量,引入一个新的变量V,V是之前的梯度的累加,但是在每个回合都会有一定的衰减。它的特点是当前后梯度方向不一致时,能够加速学习,前后梯度方向一致时,能够抑制震荡。
Adagrad
在上述的优化算法中,参数的步长都是相的,那么能否为不同的常数设置不同的步长呢,对于梯度大的参数设置小的步长,对于梯度小的参数,设置大的步长。类比于在缓坡上面,我们可以大步长的前进,在陡坡上面,这需要小步长的前进。adagrad则是参考了这个思路。