tensorflow
darren2015zdc
这个作者很懒,什么都没留下…
展开
-
Tensorflow学习:Tensorboard可视化(二)
命名空间1. 不同的命名空间。tf.variable_scople 与tf.name_scope函数提供命名空间管理功能。 大部分情况下等价。 唯一的区别,在使用tf.get_viriable函数时。import tensorflow as tfwith tf.variable_scope("foo"): a = tf.get_variable("bar", [1]) pri原创 2017-05-25 09:35:54 · 542 阅读 · 0 评论 -
TF/06_Neural_Networks/05 06 07 08
05 Implementing Different Layers06 Using Multiple Layers07 Improving Linear Regression08 Learning to Play Tic-Tac-ToeGoalThis example intends to feed examples of best moves for many different board com转载 2017-05-26 20:30:19 · 471 阅读 · 0 评论 -
TF/06_Neural_Networks/04_Single_Hidden_Layer_Network
Implementing a One Layer Neural NetworkWe will use the Iris data for this exercise. We will build a one-hidden layer fully connected neural network to predict one of the flower attributes from the oth转载 2017-05-26 19:58:36 · 585 阅读 · 0 评论 -
TF/06_Neural_Networks/01_Introduction02gate03activate fuctions
Ch 6: Neural NetworksNeural Networks are very important in machine learning and growing in popularity due to the major breakthroughs in prior unsolved problems. We must start with introducing ‘shallow转载 2017-05-26 19:51:19 · 429 阅读 · 0 评论 -
TF/05_Nearest_Neighbor_Methods/06 Nearest Neighbors for Image Recognition
06 Nearest Neighbors for Image Recognition# 06_image_recognition.py# MNIST Digit Prediction with k-Nearest Neighbors#-----------------------------------------------## This script will load the MNIS转载 2017-05-26 19:33:53 · 421 阅读 · 0 评论 -
TF/05_Nearest_Neighbor_Methods/TF/05_Nearest_Neighbor_Methods
TF/05_Nearest_Neighbor_Methods# 05_address_matching.py# Address Matching with k-Nearest Neighbors#----------------------------------## This function illustrates a way to perform# address matching转载 2017-05-26 19:28:30 · 444 阅读 · 0 评论 -
TF/05_Nearest_Neighbor_Methods/03 Working with Text Distances04 Computing with Mixed Distance Functi
03 Working with Text Distances# Text Distances#----------------------------------## This function illustrates how to use# the Levenstein distance (edit distance)# in TensorFlow.import tensorflow a转载 2017-05-26 19:25:23 · 874 阅读 · 0 评论 -
TF/05_Nearest_Neighbor_Methods/01 02_Working_with_Nearest_Neighbors
Ch 5: Nearest Neighbor MethodsNearest Neighbor methods are a very popular ML algorithm. We show how to implement k-Nearest Neighbors, weighted k-Nearest Neighbors, and k-Nearest Neighbors with mixed d转载 2017-05-26 18:43:45 · 494 阅读 · 0 评论 -
TF/04_Support_Vector_Machines/06_Implementing_Multiclass_SVMs
Implementing Multiclass SVMsHere, we implement a 1-vs-all voting method for a multiclass SVM. We attempt to separate the three Iris flower classes with TensorFlow.# 06_multiclass_svm.py# Multi-class转载 2017-05-26 12:02:37 · 378 阅读 · 0 评论 -
Protocal Buffers 介绍
https://developers.google.com/protocol-buffers/docs/overviewDeveloper GuideWelcome to the developer documentation for protocol buffers – a language-neutral, platform-neutral, extensibl转载 2017-05-30 17:05:05 · 631 阅读 · 0 评论 -
TFcaiCH3
1. 定义两个不同的图import tensorflow as tfg1 = tf.Graph()with g1.as_default(): v = tf.get_variable("v", [1], initializer = tf.zeros_initializer()) # 设置初始值为0g2 = tf.Graph()with g2.as_default(): v = tf转载 2017-05-31 20:56:29 · 227 阅读 · 0 评论 -
用于tensorflow-serving python 参考
https://github.com/sebastian-schlecht/tensorflow-serving-pythontensorflow-serving-pythonMinimal Python client to communicate with TensorFlow Serving. https://github.com/yesup/tensorflow-servin...原创 2019-01-18 14:08:59 · 236 阅读 · 0 评论 -
anaconda 中 python2,3 的兼容
前言现在Python3 被越来越多的开发者所接受,同时让人尴尬的是很多遗留的老系统依旧运行在 Python2 的环境中,因此有时你不得不同时在两个版本中进行开发,调试。如何在系统中同时共存 Python2 和 Python3 是开发者不得不面对的问题,一个利好的消息是,Anaconda 能完美解决Python2 和 Python3 的共存问题,而且在 Windows 平台经常出现安转载 2017-09-15 09:41:17 · 1008 阅读 · 0 评论 -
CUDA安装后路径不全导致TensorFlow MNIST例子运行中PyThon发生异常
CUDA安装后路径不全导致TensorFlow MNIST例子运行中PyThon发生异常 http://blog.csdn.net/rick_howe/article/details/55190063运行带GPU支持的TF例子:MNIST,中间发生PyThon执行非法指令错误,同时运行窗口报告:Couldn't open CUDA library cupti64转载 2017-09-12 09:34:50 · 2754 阅读 · 2 评论 -
Failed to import pydot. You must install pydot and graphviz for `pydotprint` to work.
参考:http://blog.csdn.net/u014749291/article/details/54891087?utm_source=itdadao&utm_medium=referralwindows平台下,pip安装pydot和graphviz:pip install pygotpip install graphviz测试时:import转载 2017-07-12 14:33:50 · 21317 阅读 · 15 评论 -
Windows下Pycharm使用Tensorflow、Theano和Keras的方法
参考: http://blog.csdn.net/hanlin_tan/article/details/70246641首先安装Anaconda x64版本(x86版本无法使用Tensorflow)。Tensorflow 1.2发布了,支持Python 3.6。因此无需再创建python 3.5环境,也就是无需执行conda create -n tensor转载 2017-07-12 09:46:53 · 3459 阅读 · 0 评论 -
Ubuntu下如何安装TensorFlow
Ubuntu下如何安装TensorFlow引言基于Anaconda的tensorflow安装1 下载linux版本的Anaconda安装包2 安装Anaconda利用anaconda安装tensorflow1 建立一个 conda 计算环境2 激活环境使用 conda 安装 TensorFlow3 安装tensorflow4 如何在jupyter中使转载 2017-07-02 13:26:32 · 793 阅读 · 0 评论 -
Android手机移植TensorFlow,实现物体识别、行人检测、图像风格迁移
Android手机移植TensorFlow,实现物体识别、行人检测、图像风格迁移转载: http://mp.weixin.qq.com/s/ZUaxGPgqAGrN9itwRnSL2A详解如何将TensorFlow训练的模型移植到安卓手机http://mp.weixin.qq.com/s/yBGoANoWh4Grk-PS3qxmfg最近上Gi转载 2017-05-31 23:04:35 · 7615 阅读 · 2 评论 -
机器学习与人工智能资源,等待更新
机器学习与人工智能技术分享(未完待续)https://www.zybuluo.com/vivounicorn/note/446479#516-原创 2017-05-31 21:00:01 · 375 阅读 · 0 评论 -
TF/04_Support_Vector_Machines/05_Implementing_Nonlinear_SVMs
05 Implementing NonLinear SVMsHere we show how to use the prior Gaussian RBF kernel to predict I.setosa from the Iris dataset.# 05_nonlinear_svm.py# Nonlinear SVM Example#----------------------------转载 2017-05-26 11:52:26 · 261 阅读 · 0 评论 -
TF/04_Support_Vector_Machines/01_Introduction
Ch 4: Support Vector MachinesThis chapter shows how to implement various SVM methods with TensorFlow. We first create a linear SVM and also show how it can be used for regression. We then introduce k转载 2017-05-26 11:22:39 · 346 阅读 · 0 评论 -
TF/02_TensorFlow_Way/03 Working with Multiple Layers04 Implementing Loss Functions
Working with Multiple LayersSummaryIn this script, we will perform a 1D spatial moving average across a vector. Then we will create a “custom” operation by multiplying the output by a specific matrix:原创 2017-05-25 16:10:28 · 680 阅读 · 0 评论 -
TF/02_TensorFlow_Way/01 02
Operations as a Computational GraphSummaryIn this script, we create an array and feed it into a placeholder. We then multiply it by a constant.Computational Graph OutputViewing the computational graph原创 2017-05-25 15:39:17 · 336 阅读 · 0 评论 -
tensorflow_cookbook:Ch 1: Getting Started with TensorFlow(8)08_Additional_Resources
Additional ResourcesOfficial Resources:TensorFlow Python APITensorFlow on GithubTensorFlow TutorialsUdacity Deep Learning ClassTensorFlow PlaygroundGithub Tutorials and Examples:Tutorials by pkm原创 2017-05-25 14:55:01 · 854 阅读 · 0 评论 -
tensorflow_cookbook:Ch 1: Getting Started with TensorFlow_(7)Data Source Information
7. Data Source InformationHere are the sources of the data sets used in this book. The following links are the original sources with explanations and citations. The script in this directory demonstrate原创 2017-05-25 14:50:08 · 804 阅读 · 0 评论 -
tensorflow_cookbook:Ch 1: Getting Started with TensorFlow_(5,6)
5.Declaring Operations# Operations#----------------------------------## This function introduces various operations# in TensorFlow# Declaring Operationsimport matplotlib.pyplot as pltimport numpy原创 2017-05-25 14:39:39 · 580 阅读 · 0 评论 -
tensorflow_cookbook:Ch 1: Getting Started with TensorFlow_(3,4)
Variables and PlaceholdersHere we initialize a simple placeholder for a piece of data. We then feed a random number into an identity function. If viewed in Tensorboard, the following graph will be crea原创 2017-05-25 14:23:55 · 635 阅读 · 0 评论 -
tensorflow_cookbook:Ch 1: Getting Started with TensorFlow_(1,2)
网站链接 :https://github.com/nfmcclure/tensorflow_cookbookCh 1: Getting Started with TensorFlowIntroduction to How TensorFlow Graphs WorkTensorFlow has a unique way of solving problems. This unique way all原创 2017-05-25 14:05:36 · 1282 阅读 · 0 评论 -
Tensorflow学习:Tensorboard可视化
基础简介* 例程*import tensorflow as tfinput1 = tf.constant([1.0, 2.0, 3.0], name = "input1")input2 = tf.Variable(tf.random_uniform([3]), name = "input2")output = tf.add_n([input1, input2], name= "add")#生原创 2017-05-25 09:06:04 · 675 阅读 · 0 评论 -
TF/02_TensorFlow_Way/05 Implementing Back Propagation
# 05_back_propagation.py# Back Propagation#----------------------------------## This python function shows how to implement back propagation# in regression and classification models.import matplot原创 2017-05-25 16:16:12 · 460 阅读 · 0 评论 -
TF/02_TensorFlow_Way/06 Working_with_Batch_and_Stochastic_Training
Working with Batch and Stochastic TrainingSummaryHere, we introduce the differences between batch and stochastic training and how to implement both in TensorFlow. Stochastic training is defined as trai原创 2017-05-25 16:21:31 · 566 阅读 · 0 评论 -
TF/04_Support_Vector_Machines/02_Working_with_Linear_SVMs03_Reduction_to_Linear_Regression
02 Working with Linear SVMsWe introduce a linear SVM on a binary set, which will be a subset of the Iris data. We know for I. setosa, that petal width and sepal length are completely separable. We wil转载 2017-05-26 11:36:56 · 580 阅读 · 0 评论 -
TF/04_Support_Vector_Machines/04_Working_with_Kernels
Working with KernelsLinear SVMs are very powerful. But sometimes the data are not very linear. To this end, we can use the ‘kernel trick’ to map our data into a higher dimensional space, where it may转载 2017-05-26 11:44:37 · 413 阅读 · 0 评论 -
TF/03_Linear_Regression/05Deming06Lasso Ridge 07Elasticnet
05 Implementing Deming RegressionDeming regression, also known as total regression, is regular regression that minimizes the shortest distance to the line. Contrast this to regular regression, in whic原创 2017-05-26 09:58:28 · 718 阅读 · 0 评论 -
TF/03_Linear_Regression/04_Loss_Functions_in_Linear_Regressions
Loss Functions in Linear RegressionThe choice of loss function can significantly impact the convergence of TensorFlow algorithms. We will compare and contrast using the L1 and L2 loss functions for li原创 2017-05-26 09:42:33 · 591 阅读 · 0 评论 -
TF/03_Linear_Regression/01 02
01 Using the Matrix Inverse MethodHere we implement solving 2D linear regression via the matrix inverse method in TensorFlow.ModelGiven A * x = b, we can solve for x via:(t(A) * A) * x = t(A) * bx = (t原创 2017-05-26 09:17:20 · 526 阅读 · 0 评论 -
TF/03_Linear_Regression/03_TensorFlow_Way_of_Linear_Regression
Learning the TensorFlow Way of RegressionIn this section we will implement linear regression as an iterative computational graph in TensorFlow. To make this more pertinent, instead of using generated原创 2017-05-26 09:37:49 · 438 阅读 · 0 评论 -
TF/02_TensorFlow_Way/08 Evaluating_Models
Evaluating ModelsSummaryHere we will perform two modeling tasks: regression and classification. We will show how to evaluate the models in the Tensorflow algorithmRegression ModelThe regression model原创 2017-05-25 16:31:02 · 407 阅读 · 0 评论 -
TF/02_TensorFlow_Way/07 Combining_Everything_Together
Combining Everything TogetherSummaryWe will create a very simple linear classifier in this example. The data set of interest will be the Iris data. We will optimize a linear separator between pedal l原创 2017-05-25 16:25:28 · 266 阅读 · 0 评论 -
tensorflow 更新的记录
https://fossies.org/linux/tensorflow/RELEASE.md原创 2019-01-28 11:02:01 · 301 阅读 · 0 评论