<?xml version="1.0" encoding="utf-8" ?><rss version="2.0"><channel><title><![CDATA[Hanx_22的博客]]></title><description><![CDATA[]]></description><link>https://blog.youkuaiyun.com/Hanx_22</link><language>zh-cn</language><generator>https://blog.youkuaiyun.com/</generator><copyright><![CDATA[Copyright &copy; Hanx_22]]></copyright><item><title><![CDATA[流畅的python笔记2.2 列表推导式和生成器表达式]]></title><link>https://blog.youkuaiyun.com/Hanx_22/article/details/77899418</link><guid>https://blog.youkuaiyun.com/Hanx_22/article/details/77899418</guid><author>Hanx_22</author><pubDate>Fri, 08 Sep 2017 21:50:26 +0800</pubDate><description><![CDATA[1.列表推导式
#coding=utf-8\
colors = ['black', 'white']
sizes = ['S', 'M', 'L']
tshirts = [(color, size) for color in colors for size in sizes]
print(tshirts) 当列表推导式中有多个for时，按如下顺序生成列表：
[('black', 'S'), (]]></description><category></category></item><item><title><![CDATA[流畅的python笔记1.2]]></title><link>https://blog.youkuaiyun.com/Hanx_22/article/details/77857444</link><guid>https://blog.youkuaiyun.com/Hanx_22/article/details/77857444</guid><author>Hanx_22</author><pubDate>Tue, 05 Sep 2017 22:18:03 +0800</pubDate><description><![CDATA[1.2 如何使用特殊方法
首先创建类：
#coding=utf-8\
from math import hypot
class Vector:
    def __init__(self, x=0, y=0):
        self.x = x
        self.y = y
    #pythonz中有一个内置函数repr，能将一个对象以字符串的形式表达出来以便辨认
    def]]></description><category></category></item><item><title><![CDATA[流畅的python笔记1.1]]></title><link>https://blog.youkuaiyun.com/Hanx_22/article/details/77841663</link><guid>https://blog.youkuaiyun.com/Hanx_22/article/details/77841663</guid><author>Hanx_22</author><pubDate>Mon, 04 Sep 2017 20:44:53 +0800</pubDate><description><![CDATA[1.1 一摞python风格的纸牌
首先，创建纸牌类：
#coding=utf-8\
import collections

#利用collections.namedtuple创建一个类，名字叫Card,类中只有属性没有方法，
#含有属性‘rank’，‘suit’
Card = collections.namedtuple('Card', ['rank', 'suit'])

class Fr]]></description><category></category></item><item><title><![CDATA[rnn decoder]]></title><link>https://blog.youkuaiyun.com/Hanx_22/article/details/77747119</link><guid>https://blog.youkuaiyun.com/Hanx_22/article/details/77747119</guid><author>Hanx_22</author><pubDate>Thu, 31 Aug 2017 15:18:53 +0800</pubDate><description><![CDATA[1.rnn_decoder
def _extract_argmax_and_embed(embedding,
                              output_projection=None,
                              update_embedding=True):
  """Get a loop_function that extrac]]></description><category></category></item><item><title><![CDATA[pure seq2seq]]></title><link>https://blog.youkuaiyun.com/Hanx_22/article/details/77746447</link><guid>https://blog.youkuaiyun.com/Hanx_22/article/details/77746447</guid><author>Hanx_22</author><pubDate>Thu, 31 Aug 2017 14:50:14 +0800</pubDate><description><![CDATA[1.pure seq2seq
enc_inputs = tf.placeholder(
    tf.int32,
    shape=[None, enc_sentence_length],
    name='input_sentences')            #enc_sentence_length:为encoder端的time_setp数

sequence_lengths = t]]></description><category></category></item><item><title><![CDATA[关于多gpu测试的疑问]]></title><link>https://blog.youkuaiyun.com/Hanx_22/article/details/77389380</link><guid>https://blog.youkuaiyun.com/Hanx_22/article/details/77389380</guid><author>Hanx_22</author><pubDate>Sat, 19 Aug 2017 00:02:47 +0800</pubDate><description><![CDATA[1.首先保存模型以及值：
import tensorflow as tf

input = tf.placeholder(tf.float32, [], 'input')
with tf.name_scope('hans'):

    weights = tf.get_variable('weights', [], tf.float32, tf.ones_initializer(tf.floa]]></description><category></category></item><item><title><![CDATA[存储与读取变量]]></title><link>https://blog.youkuaiyun.com/Hanx_22/article/details/77280681</link><guid>https://blog.youkuaiyun.com/Hanx_22/article/details/77280681</guid><author>Hanx_22</author><pubDate>Wed, 16 Aug 2017 22:29:41 +0800</pubDate><description><![CDATA[1.存储模型并且指定存储的变量
#coding=utf-8
import tensorflow as tf

x = tf.placeholder(shape=[1], dtype=tf.float32, name='xx')

variable_0 = tf.get_variable('v0', [1], tf.float32, initializer=tf.random_normal_ini]]></description><category></category></item><item><title><![CDATA[建立与读取.pb文件]]></title><link>https://blog.youkuaiyun.com/Hanx_22/article/details/77278832</link><guid>https://blog.youkuaiyun.com/Hanx_22/article/details/77278832</guid><author>Hanx_22</author><pubDate>Wed, 16 Aug 2017 21:58:17 +0800</pubDate><description><![CDATA[#coding=utf-8
import tensorflow as tf
from tensorflow.python.framework import graph_util

x = tf.placeholder(shape=[1], dtype=tf.float32, name='x')

varibale_1 = tf.get_variable('v1', [1], tf.float32,]]></description><category></category></item><item><title><![CDATA[从collection中取op]]></title><link>https://blog.youkuaiyun.com/Hanx_22/article/details/77256159</link><guid>https://blog.youkuaiyun.com/Hanx_22/article/details/77256159</guid><author>Hanx_22</author><pubDate>Wed, 16 Aug 2017 17:10:10 +0800</pubDate><description><![CDATA[#coding=utf-8

import tensorflow as tf
with tf.name_scope("hello") as name_scope:
    arr1 = tf.get_variable("arr1", shape=[2,10],dtype=tf.float32)
    a = tf.Variable(0,name='a')

arr2 = tf.get_varia]]></description><category></category></item><item><title><![CDATA[用tensorflow创建文件目录以及删除目录下所有内容]]></title><link>https://blog.youkuaiyun.com/Hanx_22/article/details/77248495</link><guid>https://blog.youkuaiyun.com/Hanx_22/article/details/77248495</guid><author>Hanx_22</author><pubDate>Wed, 16 Aug 2017 15:30:37 +0800</pubDate><description><![CDATA[#coding=utf-8
import tensorflow as tf

tf.app.flags.DEFINE_string('checkpoint_path', 'E:/E/test/src/checkpoint', '')
tf.app.flags.DEFINE_boolean('restore', False, 'whether to resotre from checkpoint')]]></description><category></category></item><item><title><![CDATA[tensorflow学习1]]></title><link>https://blog.youkuaiyun.com/Hanx_22/article/details/76284012</link><guid>https://blog.youkuaiyun.com/Hanx_22/article/details/76284012</guid><author>Hanx_22</author><pubDate>Fri, 28 Jul 2017 22:02:38 +0800</pubDate><description><![CDATA[1.图的创建与选择

import tensorflow as tf

g1 = tf.Graph()
with g1.as_default():
    v = tf.get_variable("v", [1], initializer = tf.zeros_initializer()) # 设置初始值为0

g2 = tf.Graph()
with g2.as_default():
   ]]></description><category></category></item></channel></rss>