Question

现在，我已经训练了一个非常简单的神经网络来获取正弦函数模型，但是如何使用该模型进行预测呢？就像如果我输入x = 3.14，那么我将得到零或其他值。在代码中，我定义了add_layer函数，并存储了变量。现在，如果我恢复变量，如何从特定输入获得输出？我搜索了很多信息，但无法弄清楚。

import tensorflow as tf
import numpy as np

def add_layer(inputs, in_size, out_size, activation_function=None):
   Weights = tf.Variable(tf.random_normal([in_size, out_size]))
   biases = tf.Variable(tf.zeros([1, out_size]) + 0.1)
   Wx_plus_b = tf.matmul(inputs, Weights) + biases
   if activation_function is None:
       outputs = Wx_plus_b
   else:
       outputs = activation_function(Wx_plus_b)
   return outputs

x_data = np.linspace(-1,1,300)[:, np.newaxis]
noise = np.random.normal(0, 0.05, x_data.shape)
y_data = np.sin(x_data) + noise


xs = tf.placeholder(tf.float32, [None, 1])
ys = tf.placeholder(tf.float32, [None, 1])


l1 = add_layer(xs, 1, 10, activation_function=tf.nn.relu)

prediction = add_layer(l1, 10, 1, activation_function=None)


loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction),
                    reduction_indices=[1]))


train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)



init = tf.initialize_all_variables()
saver = tf.train.Saver()


isTrain = True


with tf.Session() as sess:
    if isTrain:
        sess.run(init)
        for i in range(1000):

           sess.run(train_step, feed_dict={xs: x_data, ys: y_data})
           if i % 50 == 0:

               print(sess.run(loss, feed_dict={xs: x_data, ys: y_data}))

        print(sess.run(ys, feed_dict={xs:x_data}))
        saver.save(sess,"sin/net.ckpt")
    else:
        saver.restore(sess, "sin/net.ckpt")

如何从张量流模型获取输出？

0 个答案: