开发后如何部署神经网络？

Question

I found a simple tutorial for a neural network. Now I would like to deploy it. I wish to make it a desktop application. I can find out how to make a .exe from it. But my question is this.

According to the code, for the training purpose we have to input all inputs and the outputs when predicting. But when we deploy it we have to give only the inputs and neural network predict the output. So according to the I can't figure out what changes I should make.

import numpy as np
def nonlin(x,deriv=False):
   if(deriv==True):
      return x*(1-x)

X = np.array([[0,0,1],
             [0,1,1],
             [1,0,1],
             [1,1,1]])

y = np.array([[0],
              [1],
              [1],
              [0]])

np.random.seed(1)
syn0 = 2*np.random.random((3,4)) - 1
syn1 = 2*np.random.random((4,1)) - 1


for j in xrange(60000):
   l0 = X
   l1 = nonlin(np.dot(l0,syn0))
   l2 = nonlin(np.dot(l1,syn1))
   l2_error = y - l2

   l2_delta = l2_error*nonlin(l2,deriv=True)
   l1_error = l2_delta.dot(syn1.T)

   l1_delta = l1_error * nonlin(l1,deriv=True)

   syn1 += l1.T.dot(l2_delta)
   syn0 += l0.T.dot(l1_delta)                

As I understand in when we deploy this there cant be an array as y with values (which contains the out put values).

Answer 1

Build your model using a framework such as Keras, so that you can save it. Then create a desktop application using Tkinter and load the model when needed to make a prediction.