我正在使用 python 解决 SGD 手动实现的分配问题。我被困在 dw 导数函数上。
import numpy as np
import pandas as pd
from sklearn.datasets import make_classification
X, y = make_classification(n_samples=50000, n_features=15, n_informative=10, n_redundant
=5,n_classes=2, weights=[0.7], class_sep=0.7, random_state=15)
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=15)
def initialize_weights(dim):
w=np.zeros_like(dim)
b=0
return w,b
dim=X_train[0]
w,b = initialize_weights(dim)
print('w =',(w))
print('b =',str(b))
import math
def sigmoid(z):
''' In this function, we will return sigmoid of z'''
# compute sigmoid(z) and return
test_neg_int = -z
sig_z=1/(1+(math.exp(test_neg_int )))
return sig_z
import math
def logloss(y_true,y_pred):
'''In this function, we will compute log loss '''
n=len(y_true)
loss= -(1.0/n)*sum([y_true[i]*math.log(y_pred[i],10)+ (1.0-y_true[i])*math.log(1.0-y_pred[i],10)
for i in range(len(y_true))])
return loss
def gradient_dw(x,y,w,b,alpha,N):
'''In this function, we will compute the gardient w.r.to w '''
for n in range(0,len(x)):
dw=[]
# y=0, x= 15 array values, w= 15 array values of 0, b=0, alpha=0.0001, n=len(X_train)=37500
lambda_val = 0.01
d = x[n]*((y-alpha*((w.T)*x[n]+b)) - ((lambda_val*w)/N))
dw.append(d)
print (dw)
def grader_dw(x,y,w,b,alpha,N):
grad_dw=gradient_dw(x,y,w,b,alpha,N)
assert(np.sum(grad_dw)==2.613689585)
return True
grad_x=np.array([-2.07864835, 3.31604252, -0.79104357, -3.87045546, -1.14783286,
-2.81434437, -0.86771071, -0.04073287, 0.84827878, 1.99451725,
3.67152472, 0.01451875, 2.01062888, 0.07373904, -5.54586092])
grad_y=0
grad_w,grad_b=initialize_weights(grad_x)
alpha=0.0001
N=len(X_train)
grader_dw(grad_x,grad_y,grad_w,grad_b,alpha,N)
结果我得到
[array([-0., -0., -0., -0., -0., -0., -0., -0., -0., -0., -0., -0., -0.,
-0., -0.])]
---------------------------------------------------------------------------
AssertionError Traceback (most recent call last)
<ipython-input-168-a3ed60706dc2> in <module>
10 alpha=0.0001
11 N=len(X_train)
---> 12 grader_dw(grad_x,grad_y,grad_w,grad_b,alpha,N)
<ipython-input-168-a3ed60706dc2> in grader_dw(x, y, w, b, alpha, N)
1 def grader_dw(x,y,w,b,alpha,N):
2 grad_dw=gradient_dw(x,y,w,b,alpha,N)
----> 3 assert(np.sum(grad_dw)==2.613689585)
4 return True
5 grad_x=np.array([-2.07864835, 3.31604252, -0.79104357, -3.87045546, -1.14783286,
AssertionError:
预期结果:
True
您能否告诉我我对 gradient_dw 函数的理解是否错误?我正在尝试应用这个公式:
dw(t) = xn * (yn − σ * (((w(t))Transpose) * xn + b(t))) − (λ * w(t)) / N)
我正在尝试在 gradient_dw 函数中计算梯度 wrt 'w',以便稍后在主代码中使用它。我不明白的是 w 是一个 0s 和 y=0 的数组,所以当我们应用 dw(t) 公式并返回 dw 时,我们很可能会得到一个 0s 的数组,但是为什么它说“断言(np.sum(grad_dw)==2.613689585)" 。我们怎么可能得到 2.613689585?