莫烦theano学习自修第十天【保存神经网络及加载神经网络】

1. 为何保存神经网络

保存神经网络指的是保存神经网络的权重W及偏置b，权重W，和偏置b本身是一个列表，将这两个列表的值写到列表或者字典的数据结构中，使用pickle的数据结构将列表或者字典写入到文件中，保存神经网络只须保存权重W和偏置b，神经网络的结构下次再次定义为一样的，只需从文件中加载权重W和偏置b参数即可，无需重新训练神经网络

2. 代码实现：

from __future__ import print_function
import numpy as np
import theano
import theano.tensor as T
import pickle

def compute_accuracy(y_target, y_predict):
    correct_prediction = np.equal(y_predict, y_target)
    accuracy = np.sum(correct_prediction)/len(correct_prediction)
    return accuracy

rng = np.random

# set random seed
np.random.seed(100)

N = 400
feats = 784

# generate a dataset: D = (input_values, target_class)
D = (rng.randn(N, feats), rng.randint(size=N, low=0, high=2))

# Declare Theano symbolic variables
x = T.dmatrix("x")
y = T.dvector("y")

# initialize the weights and biases
w = theano.shared(rng.randn(feats), name="w")
b = theano.shared(0., name="b")

# Construct Theano expression graph
p_1 = 1 / (1 + T.exp(-T.dot(x, w) - b))
prediction = p_1 > 0.5
xent = -y * T.log(p_1) - (1-y) * T.log(1-p_1)
cost = xent.mean() + 0.01 * (w ** 2).sum()
gw, gb = T.grad(cost, [w, b])

# Compile
learning_rate = 0.1
train = theano.function(
          inputs=[x, y],
          updates=((w, w - learning_rate * gw), (b, b - learning_rate * gb)))
predict = theano.function(inputs=[x], outputs=prediction)

# Training
for i in range(500):
    train(D[0], D[1])

# save model
with open('save/model.pickle', 'wb') as file:
    model = [w.get_value(), b.get_value()]
    pickle.dump(model, file)
    print(model[0][:10])
    print("accuracy:", compute_accuracy(D[1], predict(D[0])))

# load model
with open('save/model.pickle', 'rb') as file:
    model = pickle.load(file)
    w.set_value(model[0])
    b.set_value(model[1])
    print(w.get_value()[:10])
    print("accuracy:", compute_accuracy(D[1], predict(D[0])))