Tensorflow学习(4)-Tensorflow中实现神经网络的训练过程的大致框架

import tensorflow as tf

batch_size = n
# 2是输出节点的个数
x = tf.placeholder(tf.float32, shape=[batch_size, 2], name='x-input')
y_ = tf.placeholder(tf.float32, shape=[batch_size, 1], name='y-input')

# 定义神经网络结构和优化算法。
loss = ...
train_step = tf.train.AdamOptimizer(learning_rate).minimize(loss)

# 训练神经网络

with tf.Session() as sess:
    # 参数初始化
    init_op = tf.global_variables_initializer()
    sess.run(init_op)
    # 迭代更新参数
    # 定义训练多少个batch
    STEPS = 5000
    for i in range(STEPS):
        current_X = ...
        current_Y = ...
        sess.run(train_step,feed_dict={x:current_X,y_:current_Y})