Python Softmax中出现了大量错误
下面是一个小代码,我正在尝试计算softmax。它适用于单个阵列。但如果有更大的数字,如1000等,它就会爆炸Python Softmax中出现了大量错误,python,numpy,deep-learning,Python,Numpy,Deep Learning,下面是一个小代码,我正在尝试计算softmax。它适用于单个阵列。但如果有更大的数字,如1000等,它就会爆炸 import numpy as np def softmax(x): print (x.shape) softmax1 = np.exp(x)/np.sum(np.exp(x)) return softmax1 def test_softmax(): print "Running your code" #print softmax(np.array([1,2]))
import numpy as np
def softmax(x):
print (x.shape)
softmax1 = np.exp(x)/np.sum(np.exp(x))
return softmax1
def test_softmax():
print "Running your code"
#print softmax(np.array([1,2]))
test1 = softmax(np.array([1,2]))
ans1 = np.array([0.26894142, 0.73105858])
assert np.allclose(test1, ans1, rtol=1e-05, atol=1e-06)
print ("Softmax values %s" % test1)
test2 = softmax(np.array([[1001,1002],[3,4]]))
print test2
ans2 = np.array([
[0.26894142, 0.73105858],
[0.26894142, 0.73105858]])
assert np.allclose(test2, ans2, rtol=1e-05, atol=1e-06)
if __name__ == "__main__":
test_softmax()
我犯了一个错误
RuntimeWarning:exp中遇到溢出
运行代码
softmax 1=np.exp(x)/np.sum(np.exp(x))softmax的典型实现首先去掉最大值以解决此问题:
def softmax(x, axis=-1):
# save typing...
kw = dict(axis=axis, keepdims=True)
# make every value 0 or below, as exp(0) won't overflow
xrel = x - x.max(**kw)
# if you wanted better handling of small exponents, you could do something like this
# to try and make the values as large as possible without overflowing, The 0.9
# is a fudge factor to try and ignore rounding errors
#
# xrel += np.log(np.finfo(float).max / x.shape[axis]) * 0.9
exp_xrel = np.exp(xrel)
return exp_xrel / exp_xrel.sum(**kw)
在代数上,这是完全相同的,但这确保了传递到
exp
的最大值是1
谢谢你的回复。我看到这些值与预期的一样,除了现在的测试用例,其中code
np.array([[10011002],[3,4]])。其中输出看起来像[[0.26894142 0.73105858][0.0.]]而不是[[0.26894142,0.73105858],[0.26894142,0.73105858]]。啊,没有意识到您想要的是列型softmax而不是数组型softmax。更新您可能对和感兴趣