# -*- coding: utf-8 -*-
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
from tensorflow.python.framework import graph_util
log_dir = './tensorboard'
mnist = input_data.read_data_sets(train_dir="./mnist_data",one_hot=True)
if tf.gfile.Exists(log_dir):
tf.gfile.DeleteRecursively(log_dir)
tf.gfile.MakeDirs(log_dir)
#定義輸入數據mnist圖片大小28*28*1=784,None表示batch_size
x = tf.placeholder(dtype=tf.float32,shape=[None,28*28],name="input")
#定義標簽數據,mnist共10類
y_ = tf.placeholder(dtype=tf.float32,shape=[None,10],name="y_")
#將數據調整為二維數據，w*H*c---> 28*28*1,-1表示N張
image = tf.reshape(x,shape=[-1,28,28,1])
#第一層，卷積核={5*5*1*32}，池化核={2*2*1,1*2*2*1}
w1 = tf.Variable(initial_value=tf.random_normal(shape=[5,5,1,32],stddev=0.1,dtype=tf.float32,name="w1"))
b1= tf.Variable(initial_value=tf.zeros(shape=[32]))
conv1 = tf.nn.conv2d(input=image,filter=w1,strides=[1,1,1,1],padding="SAME",name="conv1")
relu1 = tf.nn.relu(tf.nn.bias_add(conv1,b1),name="relu1")
pool1 = tf.nn.max_pool(value=relu1,ksize=[1,2,2,1],strides=[1,2,2,1],padding="SAME")
#shape={None，14,14,32}
#第二層，卷積核={5*5*32*64}，池化核={2*2*1,1*2*2*1}
w2 = tf.Variable(initial_value=tf.random_normal(shape=[5,5,32,64],stddev=0.1,dtype=tf.float32,name="w2"))
b2 = tf.Variable(initial_value=tf.zeros(shape=[64]))
conv2 = tf.nn.conv2d(input=pool1,filter=w2,strides=[1,1,1,1],padding="SAME")
relu2 = tf.nn.relu(tf.nn.bias_add(conv2,b2),name="relu2")
pool2 = tf.nn.max_pool(value=relu2,ksize=[1,2,2,1],strides=[1,2,2,1],padding="SAME",name="pool2")
#shape={None，7,7,64}
#FC1
w3 = tf.Variable(initial_value=tf.random_normal(shape=[7*7*64,1024],stddev=0.1,dtype=tf.float32,name="w3"))
b3 = tf.Variable(initial_value=tf.zeros(shape=[1024]))
#關鍵，進行reshape
input3 = tf.reshape(pool2,shape=[-1,7*7*64],name="input3")
fc1 = tf.nn.relu(tf.nn.bias_add(value=tf.matmul(input3,w3),bias=b3),name="fc1")
#shape={None，1024}
#FC2
w4 = tf.Variable(initial_value=tf.random_normal(shape=[1024,10],stddev=0.1,dtype=tf.float32,name="w4"))
b4 = tf.Variable(initial_value=tf.zeros(shape=[10]))
fc2 = tf.nn.bias_add(value=tf.matmul(fc1,w4),bias=b4,name="logit")
#shape={None，10}
#定義交叉熵損失
# 使用softmax將NN計算輸出值表示為概率
y = tf.nn.softmax(fc2,name="out")
# 定義交叉熵損失函數
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits=fc2,labels=y_)
loss = tf.reduce_mean(cross_entropy)
tf.summary.scalar('Cross_Entropy',loss)
#定義solver
train = tf.train.AdamOptimizer(learning_rate=0.0001).minimize(loss=loss)
for var in tf.trainable_variables():
print var
#train = tf.train.AdamOptimizer(learning_rate=0.0001).minimize(loss=loss)
#定義正確值,判斷二者下標index是否相等
correct_predict = tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
#定義如何計算準確率
accuracy = tf.reduce_mean(tf.cast(correct_predict,dtype=tf.float32),name="accuracy")
tf.summary.scalar('Training_ACC',accuracy)
#定義初始化op
merged = tf.summary.merge_all()
init = tf.global_variables_initializer()
saver = tf.train.Saver()
#訓練NN
with tf.Session() as session:
session.run(fetches=init)
writer = tf.summary.FileWriter(log_dir,session.graph) #定義記錄日志的位置
for i in range(0,500):
xs, ys = mnist.train.next_batch(100)
session.run(fetches=train,feed_dict={x:xs,y_:ys})
if i%10 == 0:
train_accuracy,summary = session.run(fetches=[accuracy,merged],feed_dict={x:xs,y_:ys})
writer.add_summary(summary,i)
print(i,"accuracy=",train_accuracy)
'''
#訓練完成后，將網絡中的權值轉化為常量，形成常量graph，注意：需要x與label
constant_graph = graph_util.convert_variables_to_constants(sess=session,
input_graph_def=session.graph_def,
output_node_names=['out','y_','input'])
#將帶權值的graph序列化，寫成pb文件存儲起來
with tf.gfile.FastGFile("lenet.pb", mode='wb') as f:
f.write(constant_graph.SerializeToString())
'''
saver.save(session,'./ckpt')
tensorflow在保存權重模型時多使用tf.train.Saver().save 函數進行權重保存，保存的ckpt文件無法直接打開，但tensorflow提供了相關函數 tf.train.NewCheckpointReader 可以對ckpt文件進行權重查看。
