#!/usr/bin/env python
import tensorflow as tf
# 每个批次的大小
batch_size = 50
# 计算一共有多少个批次
#n_batch = mnist.train.num_examples // batch_size
input_num = 16
output_num = 11
def create_file(path,output_num):
with open(path,'r') as file:
lines = file.readlines()
count = 0
data = []
featuresList = []
labelList = []
label = []
label3 = []
for line in lines:
word = line.split(" ")
features = []
#label3=[]
for i in range(1, len(word)):
if i < (len(word) - 1):
features.append(word[i].split(":")[1])
else:
features.append(word[len(word) - 1].split(":")[1].split("
")[0])
label.append(int(word[0]))
count = count + 1
#print(count)
featuresList.append(features)
labelList.append(label)
for m in labelList[0]:
label2 = []
for k in range(output_num):
k+=1
#print(k,m)
if m == k:
label2.append(1)
else:
label2.append(0)
label3.append(label2)
data.append(featuresList)
data.append(label3)
return data[0],data[1]
data = create_file("train02.txt",output_num)
test = create_file("train02.txt",output_num)
d = tf.convert_to_tensor(data[0])#训练集
d1 = tf.convert_to_tensor(data[1])
# 初始化权值
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1) # 生成一个截断的正态分布
return tf.Variable(initial)
# 初始化偏置
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
# 卷积层
def conv2d(x, W):
# x input tensor of shape `[batch, in_height, in_width, in_channels]`
# W filter / kernel tensor of shape [filter_height, filter_width, in_channels, out_channels]
# `strides[0] = strides[3] = 1`. strides[1]代表x方向的步长，strides[2]代表y方向的步长
# padding: A `string` from: `"SAME", "VALID"`
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
# 池化层
def max_pool_2x2(x):
# ksize [1,x,y,1]
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
# 定义两个placeholder
x = tf.placeholder(tf.float32, [None, input_num])
y = tf.placeholder(tf.float32, [None, output_num])
# 改变x的格式转为4D的向量[batch, in_height, in_width, in_channels]`
x_image = tf.reshape(x, [-1, 4, 4, 1])
# 初始化第一个卷积层的权值和偏置
W_conv1 = weight_variable([2, 2, 1, 16]) # 5*5的采样窗口，32个卷积核从1个平面抽取特征
b_conv1 = bias_variable([16]) # 每一个卷积核一个偏置值
# 把x_image和权值向量进行卷积，再加上偏置值，然后应用于relu激活函数
conv2d_1 = conv2d(x_image, W_conv1) + b_conv1
h_conv1 = tf.nn.relu(conv2d_1)
h_pool1 = max_pool_2x2(h_conv1) # 进行max-pooling
# 初始化第二个卷积层的权值和偏置
#W_conv2 = weight_variable([2, 2, 16, 32]) # 5*5的采样窗口，64个卷积核从32个平面抽取特征
#b_conv2 = bias_variable([32]) # 每一个卷积核一个偏置值
# 把h_pool1和权值向量进行卷积，再加上偏置值，然后应用于relu激活函数
#conv2d_2 = conv2d(h_pool1, W_conv2) + b_conv2
#h_conv2 = tf.nn.relu(conv2d_2)
#h_pool2 = max_pool_2x2(h_conv2) # 进行max-pooling
# 28*28的图片第一次卷积后还是28*28，第一次池化后变为14*14
# 第二次卷积后为14*14，第二次池化后变为了7*7
# 进过上面操作后得到64张7*7的平面
# 初始化第一个全连接层的权值
W_fc1 = weight_variable([2 * 2 * 16, 512]) # 上一场有7*7*64个神经元，全连接层有1024个神经元
b_fc1 = bias_variable([512]) # 1024个节点
# 把池化层2的输出扁平化为1维
h_pool2_flat = tf.reshape(h_pool1, [-1, 2 * 2 * 16])
# 求第一个全连接层的输出
wx_plus_b1 = tf.matmul(h_pool2_flat, W_fc1) + b_fc1
h_fc1 = tf.nn.relu(wx_plus_b1)
# keep_prob用来表示神经元的输出概率
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# 初始化第二个全连接层
W_fc2 = weight_variable([512, output_num])
b_fc2 = bias_variable([output_num])
wx_plus_b2 = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
# 计算输出
prediction = tf.nn.softmax(wx_plus_b2)
# 交叉熵代价函数
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(labels=y, logits=prediction))
# 使用AdamOptimizer进行优化
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
# 结果存放在一个布尔列表中
correct_prediction = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 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(max_to_keep=4)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
batch_xs = sess.run(d)
batch_ys = sess.run(d1)
n_batch = len(batch_xs)//batch_size
print(n_batch,"n_batch")
for epoch in range(50):
i_item=0
for batch in range(n_batch+1):
begin = batch * batch_size
if batch == n_batch:
end = len(batch_xs)
else:
end = (batch + 1)*batch_size
batch_x = batch_xs[begin:end]
batch_y = batch_ys[begin:end]
# print(begin)
# print(end)
# print(batch_y)
sess.run(train_step, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 0.7})
if epoch % 10 ==0:
saver.save(sess,"model/my-model",global_step=epoch)
acc = sess.run(accuracy, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.0})
print("Iter " + str(epoch) + ", Testing Accuracy= " + str(acc))