一个处女座的程序猿

低调,谦虚,不骄不躁。 观察Amazon,追踪FaceBook,跟紧Google,偷窥Microsoft,朝向Silicon Valley …… 哈哈,一起学习啦。本博主做事,从来都是走心不走肾,...

TF之BN:BN算法对多层中的每层神经网络加快学习QuadraticFunction_InputData+Histogram+BN的Error_curve

# 23 Batch Normalization   import numpy as np import tensorflow as tf import matplotlib.pyplot as plt     ACTIVATION = tf.nn.tanh N_LAYER...

2018-01-31 21:56:44

阅读数:101

评论数:0

Numpy:利用Numpy库建立可视化输入的二次函数数据点集np.linspace+np.random.shuffle+np.random.normal

import numpy as np import matplotlib.pyplot as plt def fix_seed(seed=1): #重复观看一样东西 # reproducible np.random.seed(seed) # make up data建...

2018-01-31 21:55:22

阅读数:77

评论数:0

TF之RNN:实现利用scope.reuse_variables()告诉TF想重复利用RNN的参数的案例

import tensorflow as tf # 22 scope (name_scope/variable_scope) from __future__ import print_function class TrainConfig: batch_size = 20 tim...

2018-01-30 21:54:23

阅读数:226

评论数:2

TF之RNN:TF的RNN中的常用的两种定义scope的方式get_variable和Variable—Jason niu

# tensorflow中的两种定义scope(命名变量)的方式tf.get_variable和tf.Variable。Tensorflow当中有两种途径生成变量 variable import tensorflow as tf #T1法 tf.name_scope() with tf.na...

2018-01-30 21:01:08

阅读数:76

评论数:0

TF之AE:AE实现TF自带数据集AE的encoder之后decoder之前的非监督学习分类

import tensorflow as tf import numpy as np import matplotlib.pyplot as plt #Import MNIST data from tensorflow.examples.tutorials.mnist import input_...

2018-01-30 11:36:21

阅读数:84

评论数:0

TF之AE:AE实现TF自带数据集数字真实值对比AE先encoder后decoder预测数字的精确对比

import tensorflow as tf import numpy as np import matplotlib.pyplot as plt #Import MNIST data from tensorflow.examples.tutorials.mnist import input...

2018-01-27 20:00:56

阅读数:70

评论数:0

TF之RNN:matplotlib动态演示之基于顺序的RNN回归案例实现高效学习逐步逼近余弦曲线

import tensorflow as tf import numpy as np import matplotlib.pyplot as plt BATCH_START = 0 TIME_STEPS = 20 BATCH_SIZE = 50 INPUT_SIZE = 1...

2018-01-27 14:31:54

阅读数:97

评论数:0

TF之RNN:TensorBoard可视化之基于顺序的RNN回归案例实现蓝色正弦虚线预测红色余弦实线

import tensorflow as tf import numpy as np import matplotlib.pyplot as plt BATCH_START = 0 TIME_STEPS = 20 BATCH_SIZE = 50 INPUT_SIZE ...

2018-01-27 13:25:42

阅读数:203

评论数:0

TF之RNN:(TF自带函数下载MNIST55000训练集图片)基于顺序的RNN分类案例手写数字图片识别实现高精度99%准确率

import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets('MNIST_data', one_hot=True) lr...

2018-01-26 21:37:38

阅读数:113

评论数:0

TF之LiR:基于tensorflow实现机器学习之线性回归算法

TF之LiR:基于tensorflow实现机器学习之线性回归算法

2018-01-25 22:09:19

阅读数:63

评论数:0

TF:利用TF的train.Saver将训练好的W、b模型文件保存+新建载入刚训练好模型(用于以后预测新的数据)

import tensorflow as tf import numpy as np W = tf.Variable([[2,1,8],[1,2,5]], dtype=tf.float32, name='weights') b = tf.Variable([[1,2,5]], dtype=tf....

2018-01-25 22:07:24

阅读数:94

评论数:0

TF之CNN:CNN实现mnist数据集预测 96%采用placeholder用法+2层C及其max_pool法+隐藏层dropout法+输出层softmax法+目标函数cross_entropy法+

TF:TF下CNN实现mnist数据集预测 96%采用placeholder用法+2层C及其max_pool法+隐藏层dropout法+输出层softmax法+目标函数cross_entropy法+AdamOptimizer算法 import tensorflow as tf from tenso...

2018-01-24 23:17:46

阅读数:126

评论数:0

TF之CNN:利用sklearn(自带手写图片识别数据集)使用dropout解决学习中overfitting的问题+Tensorboard显示变化曲线

import tensorflow as tf from sklearn.datasets import load_digits #from sklearn.cross_validation import train_test_split from sklearn.model_selection ...

2018-01-24 18:36:14

阅读数:149

评论数:0

成功解决This module was deprecated in version 0.18 in favor of the model_selection module into which all

解决问题:This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved....

2018-01-24 17:38:52

阅读数:1724

评论数:0

TF之NN:(TF自带函数下载MNIST55000训练集图片)实现手写数字图片识别87.4%准确率识别:SGD法+softmax法+cross_entropy法

 TF之NN:(TF自带函数下载MNIST55000训练集图片)实现手写数字图片识别87.4%准确率识别:SGD法+softmax法+cross_entropy法 import numpy as np import tensorflow as tf import matplotlib.pypl...

2018-01-24 16:46:22

阅读数:161

评论数:0

TF:TF之Tensorboard实践:将神经网络Tensorboard形式得到events.out.tfevents文件+dos内运行该文件本地服务器输出到网页可视化

TF:TF之Tensorboard实践:将神经网络Tensorboard形式得到events.out.tfevents文件+dos内运行该文件本地服务器输出到网页可视化import tensorflow as tf import numpy as np def add_layer(i...

2018-01-24 15:48:10

阅读数:433

评论数:0

VB:使用Visual Studio 2010中的VB语言工具箱DataGridView调用SQL数据库Database的表格文件

1、先在VB窗口中添加工具箱中的DataGridView小工具 2、然后在窗口的DataGridView小工具上上进行连接数据库即可

2018-01-24 14:35:14

阅读数:94

评论数:0

TF版本问题:由于不同的TensorFlow版本之间某些函数的用法引起的错误

Transitioning to TensorFlow 1.0参照外文:https://www.tensorflow.org/install/migration1、解决问题AttributeError: module 'tensorflow' has no attribute 'histogram...

2018-01-23 21:59:43

阅读数:244

评论数:0

TF之Tensorboard:Tensorflow之Tensorboard可视化使用之详细攻略

TF:Tensorboard之SCALARS、GRAPHS、DISTRIBUTIONS、HISTOGRAMS详细总结来啊,亲先来个直观感受!就问你,Tensorboard,牛不牛叉?TensorBoard 是 TensorFlow 上一个非常酷的功能,我们都知道神经网络很多时候就像是个黑盒子,里面...

2018-01-23 21:06:37

阅读数:254

评论数:0

成功解决tensorboard调用events.out.tfevents文件得到网址出现No dashboards are active for the current data set问题

解决问题:Tensorboard网址出现No dashboards are active for the current data set根据tensorboard调用events.out.tfevents文件得到网址出现No dashboards are active for the curre...

2018-01-23 20:51:05

阅读数:1778

评论数:0

提示
确定要删除当前文章?
取消 删除