以前写过一篇tensorflow 训练保存模型,本文的改进:换了一种模型,然后采用tensorboard来获取tesnor的名字。
训练模型:
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
from tensorflow.python.framework import graph_util
#载入数据集
mnist = input_data.read_data_sets("MNIST_data",one_hot=True)
#每个批次的大小
batch_size = 100
#计算一共有多少个批次
n_batch = mnist.train.num_examples // batch_size
#定义两个placeholder
x = tf.placeholder(tf.float32,[None,784])
y = tf.placeholder(tf.float32,[None,10])
keep_prob=tf.placeholder(tf.float32)
lr = tf.Variable(0.001, dtype=tf.float32)
#创建一个简单的神经网络
W1 = tf.Variable(tf.truncated_normal([784,500],stddev=0.1))
b1 = tf.Variable(tf.zeros([500])+0.1)
L1 = tf.nn.tanh(tf.matmul(x,W1)+b1)
L1_drop = tf.nn.dropout(L1,keep_prob)
W2 = tf.Variable(tf.truncated_normal([500,300],stddev=0.1))
b2 = tf.Variable(tf.zeros([300])+0.1)
L2 = tf.nn.tanh(tf.matmul(L1_drop,W2)+b2)
L2_drop = tf.nn.dropout(L2,keep_prob)
W3 = tf.Variable(tf.truncated_normal([300,10],stddev=0.1))
b3 = tf.Variable(tf.zeros([10])+0.1)
prediction = tf.nn.softmax(tf.matmul(L2_drop,W3)+b3)
#交叉熵代价函数
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(labels=y,logits=prediction))
#训练
train_step = tf.train.AdamOptimizer(lr).minimize(loss)
#初始化变量
init = tf.global_variables_initializer()
#结果存放在一个布尔型列表中
correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(prediction,1))#argmax返回一维张量中最大的值所在的位置
#求准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
saver = tf.train.Saver() #声明saver用于保存模型
import os
ckpt_dir = "./ckpt_dir"
if not os.path.exists(ckpt_dir):
os.makedirs(ckpt_dir)
with tf.Session() as sess:
sess.run(init)
for epoch in range(20):
sess.run(tf.assign(lr, 0.001 * (0.95 ** epoch)))
for batch in range(n_batch):
batch_xs,batch_ys = mnist.train.next_batch(batch_size)
sess.run(train_step,feed_dict={x:batch_xs,y:batch_ys,keep_prob:0.8})
learning_rate = sess.run(lr)
acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels,keep_prob:1.0})
print ("Iter " + str(epoch) + ", Testing Accuracy= " + str(acc) + ", Learning Rate= " + str(learning_rate))
a = epoch%5
if 0==a :
saver.save(sess,ckpt_dir+"/Test1.ckpt",epoch) #模型保存
saver.save(sess,ckpt_dir+"/Test1.ckpt",epoch) #模型保存
读取模型测试
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
from tensorflow.python.framework import graph_util
#载入数据集
mnist = input_data.read_data_sets("MNIST_data",one_hot=True)
saver = tf.train.import_meta_graph("./ckpt_dir/Test1.ckpt-19.meta")
#这里名字是训练的时候打印出来的
with tf.Session() as sess:
saver.restore(sess,"ckpt_dir/Test1.ckpt-19")
acc = sess.run("Mean_1:0",feed_dict={"Placeholder:0":mnist.test.images,"Placeholder_1:0":mnist.test.labels,"Placeholder_2:0":1.0})
print ("Testing Accuracy= " + str(acc))
#这里是把图结构保存下来
with tf.Session() as sess:
saver.restore(sess,"ckpt_dir/Test1.ckpt-19")
writer = tf.summary.FileWriter("logs/", sess.graph)
然后输入命令:
tesnorboard --logdir logs
打开谷歌浏览器,输入命令生成的地址:
就可以看到网络结构了,然后就可以知道tensor的名字了
图示的圈圈就是找到的输入的节点。
但是下一个问题来了,这个图中间包含了反向传播、saver什么的,如果不是自己训练的,根本看不明白!那要怎么样做呢?怎么才能得到一个仅仅前向传播的方便理解的网络结构呢?
待研究中……