前向传播 ->搭建模型，实现推理（以全连接网络为例）

• 生产一批零件将体积X1和重量X2为特征输入NN，通过NN后输出一个数值。

  
  2.png
  微信截图_20190924222755.png

3.png

# 两层简单神经网络
import tensorflow as tf

# 定义输入和参数
x = tf.constant([[0.7, 0.5]])
w1 = tf.Variable(tf.random_normal([2, 3], stddev=1, seed=1))
w2 = tf.Variable(tf.random_normal([3,1], stddev=1,seed=1))
# 定义前向传播过程
a = tf.matmul(x, w1)
y = tf.matmul(a, w2)

# 用会话计算结果
with tf.Session() as sess:
    init_op = tf.global_variables_initializer()
    sess.run(init_op)
    print("y is %s"%sess.run(init_op))

# 两层简单神经网络
import tensorflow as tf

# 定义输入和参数
x = tf.constant([[0.7, 0.5]])
w1 = tf.Variable(tf.random_normal([2, 3], stddev=1, seed=1))
w2 = tf.Variable(tf.random_normal([3, 1], stddev=1, seed=1))

# 定义前向传播过程
a = tf.matmul(x, w1)
y = tf.matmul(a, w2)

# 用会话计算结果
with tf.Session() as sess:
    init_op = tf.global_variables_initializer()
    sess.run(init_op)
    print("y is %s" % sess.run(y, feed_dict={x: [[0.7, 0.5]]}))

# 两层简单神经网络（全连接）

import tensorflow as tf

# 定义输入和参数
# 用placeholder定义输入（sess.run喂多组数据）
x = tf.placeholder(tf.float32, shape=(None, 2))
w1 = tf.Variable(tf.random_normal([2, 3], stddev=1, seed=1))
w2 = tf.Variable(tf.random_normal([3, 1], stddev=1, seed=1))

# 定义前向传播过程
a = tf.matmul(x, w1)
y = tf.matmul(a, w2)

# 调用会话计算结果
with tf.Session() as sess:
    init_op = tf.global_variables_initializer()
    sess.run(init_op)
    print("the result is %s" % sess.run(y, feed_dict={x: [[0.7, 0.5], [0.2, 0.3], [0.3, 0.4], [0.4, 0.5]]}))
    print("w1:%s" % sess.run(w1))
    print("w2:%s" % sess.run(w2))