Implementation method of Softmax regression function under Python

Softmax regression function is used to normalize the classification results. But it is different from the general normalization method according to proportion. It normalizes through logarithmic transformation, so that larger values ​​gain more during the normalization process.

Softmax formula

##Softmax implementation method 1

import numpy as np
def softmax(x):
 """Compute softmax values for each sets of scores in x."""
 pass # TODO: Compute and return softmax(x)
 x = np.array(x)
 x = np.exp(x)
 x.astype('float32')
 if x.ndim == 1:
  sumcol = sum(x)
  for i in range(x.size):
   x[i] = x[i]/float(sumcol)
 if x.ndim > 1:
  sumcol = x.sum(axis = 0)
  for row in x:
   for i in range(row.size):
    row[i] = row[i]/float(sumcol[i])
 return x
#测试结果
scores = [3.0,1.0, 0.2]
print softmax(scores)

The calculation results are as follows ：

[ 0.8360188 0.11314284 0.05083836]

Softmax implementation method 2

import numpy as np
def softmax(x):
 return np.exp(x)/np.sum(np.exp(x),axis=0)
 
#测试结果
scores = [3.0,1.0, 0.2]
print softmax(scores)

The above implementation method (recommended) of the Softmax regression function under Python is shared by the editor I’ve given you all the content, I hope it can give you a reference, and I hope you will support the PHP Chinese website.

For more related articles on how to implement the Softmax regression function under Python, please pay attention to the PHP Chinese website!