Python Code Numpy Arrays Creation Problem

Asked

Viewed 157 times

1

I’m having trouble in the following code. I don’t understand what is wrong. I believe it is in the function sigmoid where she appears not to be receiving values float.

import numpy as np

# sigmoid function
def nonlin(x,deriv=False):
    if(deriv==True):
        return x*(1-x)
    return 1/(1+np.exp(-x))

# Valores de Entradas
X = np.array([[488457.495,6673006.568,68.624],[488458.287,6673008.192,68.621],
              [488459.073,6673009.798,68.618], [488456.712,6673004.978,66.558]],dtype=object)# Entrada_Estação_Total_Aba_8_Reg_01

# saidas          
y = np.array([[488457.500,6673006.571,68.624],[488458.281,6673008.199,68.617],
              [488459.071,6673009.807,68.615],[488456.722,6673004.980,66.566]],dtype=object).T#Registro_C1_Nuvem_Aba_*_REG_1

# seed random numbers to make calculation
# deterministic (just a good practice)
np.random.seed(1)

# initialize weights randomly with mean 0
syn0 = 2*np.random.random((3,1)) - 1

for iter in range(10000):

    # forward propagation
    l0 = X
    l1 = nonlin(np.dot(l0,syn0))

    # how much did we miss?
    l1_error = (y - l1)

    # multiply how much we missed by the 
    # slope of the sigmoid at the values in l1
    l1_delta = l1_error * nonlin(l1,True)

    # update weights
    syn0 += np.dot(l0.T,l1_delta)

print("\n")  
print ("Saidas depois do treinamento:")
print("\n")     
print (l1)
print("\n")         
print("Pesos_Ajustados: ")
print("\n") 
print(np.around(syn0,decimals=3))

The following error message appears:

Traceback (most recent call last):
  File "G:\Perceptron_PE_TLS\Perceptron_TLS_Ajustado2.py", line 34, in <module>
    l1 = nonlin(np.dot(l0,syn0))
  File "G:\Perceptron_PE_TLS\Perceptron_TLS_Ajustado2.py", line 7, in nonlin
    return 1/(1+np.exp(-x))
AttributeError: 'float' object has no attribute 'exp'
python-3.x numpy

1 answer

1


Apparently there is a problem with changing values of an array created by numpy. The solution to this "Valueerror: Setting an array element with a Sequence" problem is to add to the end of the array the attribute "dtype=Object": 

pesos = np.array([0.0, 0.0], dtype=object)

More detailed explanation here

Browser other questions tagged python-3.x numpy

You are not signed in. Login or sign up in order to post.