tensorflow的函数

Posted 2020-10-12 Qniguoym

1.

if __name__=="__main__":
    tf.app.run()#运行之前定义的main函数
#将传进来的参数，以及flags.FLAGS定义的参数传入到main函数中

2.

#flags的定义
flags=tf.app.flags
flags.DEFINE_string("save_path",None,"Directory to write the model and training summaries.")
FLAGS=flags.FLAGS

3.

tf.random_uniform((2,2),minval=-0.5,maxval=0.5,dtype=tf.float32)
tf.random_uniform([2,2],minval=-0.5,maxval=0.5,dtype=tf.float32)
#是相同的

4.

tf.nn.uniform_candidate_sampler()#均匀地采样出类别子集
tf.nn.log_uniform_candidate_sampler()
tf.nn.fixed_unigram_candidate_sampler()#按照用户提供的概率分布进行采样

tf.nn.uniform_candidate_sampler(true_classes=,num_true=,num_sampled=,unique=,range_max=,)
#目标的类别,size为[batch_size,num_true]
# num_true 每个训练例子目标类别的数量
#num_sampled 每个批次抽样的类别的数量
#unique 被抽样的类别是否是unique的
#range_max 可能类别的数量

5.

tf.nn.embedding_lookup(params=,ids=,)
#在params中查找ids元素的表示、
#抽取出ids元素行号的数据，列的维度是相同的

tf.reduce_mean(-tf.reduce_sum(y*tf.log(a),reduction_indices=[1]))
#0是按照列向量求均值，1是按照行向量求均值，得到的都是行向量

6.最简单的mnist识别代码

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import tensorflow as tf
import numpy as np
import math
import gzip
import os
import tempfile
from tensorflow.examples.tutorials.mnist import input_data
flags = tf.app.flags
FLAGS = flags.FLAGS
flags.DEFINE_string(‘data_dir‘, ‘/Users/guoym/Desktop/models-master‘, ‘Directory for storing data‘)
mnist = input_data.read_data_sets(FLAGS.data_dir, one_hot=True)
x = tf.placeholder(tf.float32, [None, 784]) # 占位符
y = tf.placeholder(tf.float32, [None, 10])
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
a = tf.nn.softmax(tf.matmul(x, W) + b)
cross_entropy=tf.reduce_mean(-tf.reduce_sum(y*tf.log(a),reduction_indices=[1]))
#注意区分矩阵乘法和一一对应的乘法
optimizer=tf.train.GradientDescentOptimizer(0.5)
train=optimizer.minimize(cross_entropy)

correct_prediction=tf.equal(tf.argmax(a,1),tf.argmax(y,1))
accuracy=tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

sess=tf.InteractiveSession()
tf.initialize_all_variables().run()
for i in range(1000):
    batch_xs,batch_ys=mnist.train.next_batch(100)
    train.run({x:batch_xs,y:batch_ys})
print (sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels}))