Question

我按如下方式设置了numpy.seterr：

np.seterr(invalid='raise', over ='raise', under='raise')

我收到以下错误：

    c = beta[j,i] + oneminusbeta[j,i]
FloatingPointError: overflow encountered in double_scalars

我已经检查了beta[j,i]和oneminusbeta[j,i]在崩溃时的情况，这些是他们的值：

beta: -131.340389182 
oneminusbeta: 0.0

请注意，此行添加（beta[j,i] + oneminusbeta[j,i]）已在循环中运行了数千行（执行图像分类），此时此处崩溃。我怎么处理这个？是否有必要更改numpy数组的类型？这就是我初始化它们的方式：

beta = np.empty([m,n])
oneminusbeta = np.empty([m,n])

是否可以在添加之前投射各个值？而不是改变整个数组声明？或者这甚至是一个严重的问题？简单地关闭numpy.seterr配置并让计算继续进行而不会引发错误是否安全？

修改

有人在下面建议，我也怀疑，添加的值不应该导致溢出。那我怎样才能找出真正发生溢出的地方？

这是我的代码：

epthreshold = 709 
enthreshold = -708

f.write("weights["+str(i)+", " + str(j)+"] = math.exp(beta: " +str(beta[j,i])+ " + oneminusbeta: " + str(oneminusbeta[j,i])+")\n"  )
c = beta[j,i] + oneminusbeta[j,i]
weights[i,j] = math.exp(np.clip(c, enthreshold, epthreshold))

当我检查我的日志文件时，这就是我得到的行：

weights[5550, 13] = math.exp(beta: -131.340389182 + oneminusbeta: 0.0)

编辑2

以下是我的其余代码，其中变量n，m和H已初始化为整数值：

import numba
import numpy as np
import statsmodels.api as sm

weights = np.empty([n,m])
for curr_n in range(n):
    for curr_m in range(m):
        weights[curr_n,curr_m] = 1.0/(n)

beta = np.empty([m,n])
oneminusbeta = np.empty([m,n])
for curr_class in range(m):
    for curr_sample in range(n):
        beta[curr_class,curr_sample] = 1./m

epthreshold = 709 # positive exponential threshold
enthreshold = -708

for h in range(H):
    print "Boosting round %d ... " % h
    z = np.empty([n,m]) 
    for j in range(m):    # computing working responses and weights, Step 2(a)(i)
        for i in range(no_samples): 
            i_class =  y[i] #get the correct class for the current sample
            if h == 0:
                z[i,j] = (int(j==i_class) - beta[j,i])/((beta[j,i])*(1. - beta[j,i]))
                weights[i,j] = beta[j,i]*(1. - beta[j,i])
            else:
                if j == i_class:
                    z[i,j] = math.exp(np.clip(-beta[j,i],enthreshold, epthreshold))
                else:
                    z[i,j] = -math.exp(np.clip(oneminusbeta[j,i], enthreshold, epthreshold))                            

                f.write("weights["+str(i)+", " + str(j)+"] = math.exp(beta: " +str(beta[j,i])+ " + oneminusbeta: " + str(oneminusbeta[j,i])+")\n"  )
                c = beta[j,i] + oneminusbeta[j,i]
                weights[i,j] = math.exp(np.clip(c, enthreshold, epthreshold))


    g_h = np.zeros([1,1])
    j = 0
    # Calculating regression coefficients per class
    # building the parameters per j class
    for y1_w in zip(z.T, weights.T):
        y1, w = y1_w 
        temp_g = sm.WLS(y1, X, w).fit()  # Step 2(a)(ii)
        if np.allclose(g_h,0):
               g_h = temp_g.params
        else:
                g_h = np.c_[g_h, temp_g.params] 
        j = j + 1

    if np.allclose(g,0):
        g = g_h
    else:            
        g = g + g_h # Step(2)(a)(iii)

    # now set g(x), function coefficients according to new formula, step (2)(b)
    sum_g = g.sum(axis=1)
    for j in range(m): 
        diff = (g[:,j] - ((1./m) * sum_g))
        g[:,j] = ((m-1.)/m) * diff 
        g_per_round[h,:,j] = g[:,j]
    #Now computing beta, Step 2(c)...."
    Q = 0.
    e = 0.
    for j in range(m):
        # Calculating beta and oneminusbeta for class j
        aj = 0.0
        for i in range(no_samples):
            i_class = y[i]
            X1 = X[i].reshape(1, no_features)
            g1 = g[:,j].reshape(no_features, 1)
            gc =  g[:,i_class].reshape(no_features, 1)
            dot = 1. + float(np.dot(X1, g1)) - float(np.dot(X1,gc))
            aj = dot
            sum_e = 0.
            a_q = []
            a_q.append(0.)
            for j2 in range(m): # calculating sum of e's except for all j except where j=i_class
                if j2 != i_class: # g based on j2, not necessarily g1?
                    g2 = g[:,j2].reshape(no_features, 1)
                    dot1 = 1. + float(np.dot(X1, g2)) - float(np.dot(X1,gc))
                    e2 = math.exp(np.clip(dot1,enthreshold, epthreshold))
                    sum_e = sum_e + e2
                    a_q.append(dot1)

            if (int(j==i_class) == 1):
                a_q_arr = np.array(a_q)                        
                alpha = np.array(a_q_arr[1:])  
                Q = mylogsumexp(f,a_q_arr, 1, 0)
                sumalpha = mylogsumexp(f,alpha, 1, 0)
                beta[j,i] = -Q
                oneminusbeta[j,i] = sumalpha - Q
            else:
                alpha = a_q
                alpha = np.array(alpha[1:])
                a_q_arr = np.array(a_q)
                Q = mylogsumexp(f,a_q_arr, 0, aj)
                sumalpha = log(math.exp(np.clip(Q, enthreshold, epthreshold)) - math.exp(np.clip(aj, enthreshold, epthreshold)))

                beta[j,i] = aj - Q
                oneminusbeta[j,i] = sumalpha - Q

，函数mylogsumexp为：

def mylogsumexp(f, a, is_class, maxaj, axis=None, b=None):
    np.seterr(over="raise", under="raise", invalid="raise")
    threshold = -sys.float_info.max    
    maxthreshold = sys.float_info.max
    epthreshold = 709 # positive exponential threshold
    enthreshold = -708

    a = asarray(a)

    if axis is None:
        a = a.ravel()
    else:
        a = rollaxis(a, axis)

    if is_class == 1:
        a_max = a.max(axis=0)
    else:
        a_max = maxaj 

    #bnone = " none "
    if b is not None:
        a_max = maxaj
        b = asarray(b)
        if axis is None:
            b = b.ravel()
        else:
            b = rollaxis(b, axis)
        a = np.clip(a - a_max, enthreshold, epthreshold)
        midout = np.sum(np.exp(a), axis=0)
        midout = 1.0 + np.clip(midout - math.exp(a_max), threshold, maxthreshold)
        out = np.log(midout)

    else:
        a = np.clip(a - a_max, enthreshold, epthreshold)
        out = np.log(np.sum(np.exp(a)))

    out += a_max
    if out == float("inf"):
        out = maxthreshold
    if out == float("-inf"):
        out = threshold
    return out

FloatingPointError：double_scalars中遇到溢出

修改

编辑2

0 个答案: