theano

Cyclic computational graphs with Tensorflow or Theano

非 Y 不嫁゛ 提交于 2019-11-29 15:44:13
Both TensorFlow and Theano do not seem to support cyclic computational graphs, cyclic elements are implemented as recurrent cells with buffer and unrolling (RNN / LSTM cells), but this limitation is mostly related with the computation of back-propagation. I don't have a particular need for computing back-propagation but just the forward propagations. Is there a way to ignore this limitation, or perhaps just to break down arbitrary computational graphs in acyclic components? TensorFlow does support cyclic computation graphs. The tf.while_loop() function allows you to specify a while loop with

github上热门深度学习项目

蹲街弑〆低调 提交于 2019-11-29 11:50:43
github上热门深度学习项目 项目名 Stars 描述 TensorFlow 29622 使用数据流图进行可扩展机器学习的计算。 Caffe 11799 Caffe:深度学习的快速开放框架。 [Neural Style](https://github.com/jcjohnson/neural-style) 10148 火炬实现神经风格算法。 Deep Dream 9042 深梦。 Keras 7502 适用于Python的深度学习库。Convnets,递归神经网络等等。在Theano和TensorFlow上运行。 Roc AlphaGo 7170 由学生主导的独立复制的DeepMind 2016年自然出版物,“用深度神经网络和树搜索掌握Go游戏”(Nature 529,484-489,2016年1月28日)。 [TensorFlow Models](https://github.com/tensorflow/models) 6671 使用TensorFlow构建的模型 Neural Doodle 6275 将您的两位涂鸦变成具有深度神经网络的精美艺术品,从照片生成无缝纹理,将样式从一个图像转移到另一个图像,执行基于示例的升级,但等待......还有更多!(语义样式转换的实现。) CNTK 5957 计算网络工具包(CNTK)。 TensorFlow Examples 5872

cpu、gpu 安装框架pytorch,cntk,theano及测试

回眸只為那壹抹淺笑 提交于 2019-11-29 11:16:11
一,cpu 下安装 tensorflow conda env list source activate tensorflow 直接安装相应版本 python import tensorflow as tf tf.__version__ 1.11.0 keras 直接安装 conda env list source activate keras import keras 2.2.2 print(keras.__version__) import tensorflow as tf tf.__version__ pytorch import torch print(torch.__version__) print(torch.cuda.device_count()) print(torch.cuda.is_available()) cntk /root/anaconda3/bin/conda env list source activate cntk-py35 python 3.5.6 export PATH=/root/anaconda3/bin:$PATH python -c "import cntk; print(cntk.__version__)" theano caffe2 python 3.6.9 import caffe2 安装 conda create -n caffe2

anaconda 安装caffe,cntk,theano-未整理

半腔热情 提交于 2019-11-29 11:08:44
一,anancona 安装 https://repo.anaconda.com/archive/ conda create -n caffe_gpu -c defaults python=3.6 caffe-gpu conda create -n caffe -c defaults python=3.6 caffe 测试: import caffe python -c "import caffe; print dir(caffe)" 参考: https://blog.csdn.net/weixin_37251044/article/details/79763858 一、编译Caffe、PyCaffe URL : https://github.com/BVLC/caffe.git 1 1.下载Caffe git clone https://github.com/BVLC/caffe.git cd caffe 注意:如果想在anaconda下使用,就先 source activate caffe_env 然后在这个环境下安装 利用anaconda2随意切换proto的版本,多proto并存,protobuf,libprotobuf 2.编译caffe 用cmake默认配置: [注意]:一般需要修改config文件。 进入caffe根目录 mkdir build cd build

theano - print value of TensorVariable

帅比萌擦擦* 提交于 2019-11-29 10:36:31
问题 How can I print the numerical value of a theano TensorVariable? I'm new to theano, so please be patient :) I have a function where I get y as a parameter. Now I want to debug-print the shape of this y to the console. Using print y.shape results in the console output (i was expecting numbers, i.e. (2,4,4) ): Shape.0 Or how can I print the numerical result of for example the following code (this counts how many values in y are bigger than half the maximum): errorCount = T.sum(T.gt(T.abs_(y),T

Keras verbose training progress bar writing a new line on each batch issue

情到浓时终转凉″ 提交于 2019-11-29 03:42:29
running a Dense feed-forward neural net in Keras. there are class_weights for two outputs, and sample_weights for a third output. fore some reason it prints the progress verbose display for each batch calculated, and not updating the print on the same line as its supposed to... Did this ever happens to you? How is it fixed? From the shell: 42336/747322 [====>.........................] - ETA: 79s - loss: 20.7154 - x1_loss: 9.5913 - x2_loss: 10.0536 - x3_loss: 1.0705 - x1_acc: 0.6930 - x2_acc: 0.4433 - x3_acc: 0.6821 143360/747322 [====>.........................] - ETA: 78s - loss: 20.7387 - x1

python常用数据处理库

本小妞迷上赌 提交于 2019-11-29 03:22:37
Python之所以能够成为数据分析与挖掘领域的最佳语言,是有其独特的优势的。因为他有很多这个领域相关的库可以用,而且很好用,比如Numpy、SciPy、Matploglib、Pandas、ScikitLearn、Keras、Gensim等 1)Numpy,它给Python提供了真正的数组功能,包括多维数组,以及对数据进行快速处理的函数,Numpy还是更多高级扩展库的依赖库,比如后续的Scipy、Matplotlib、Pandas等,都一样; 2)Scipy,他让Python成了半个MATLAB,Scipy提供了真正的矩阵类型,及其大量基于矩阵运算的对象和函数,他包括的功能包括最优化、线性代数、积分、插值、你和、特殊函数、快速傅里叶变换、信号处理与图像处理、常微分求解方程和其他科学与工程中常用的计算;Scipy依赖于Numpy; 3)Matplotlib,对于Python来说,Matplotlib是最著名的绘图库,主要是二维绘图,当然,也可以支持一些简答的三围绘图; 4)Pandas,他是Python下最强大的数据分析和探索工具,没有之一。他包含的高级的数据结构和精巧的工具,使得在Python中处理数据非常快速和简单,Pandas构建在NumPy之上,他使得以Numpy为中心的应用很容易使用,Pandas的名称来自于面板数据(Panel Data)和Python数据分析(Data

g++ error on import of Theano on Windows 7

╄→гoц情女王★ 提交于 2019-11-29 03:08:31
问题 I'm attempting to get setup with a proper g++ installation according to the theano installation guide. I've previously had theano working with the python only implementation. I'm using the bleeding edge version of theano from their git repo on python 3.4. I've tried using the theano suggested TDM-GCC-64 method as well as MinGW, and both result in the exact same error. (copied as readable as possible) Problem occurred during compilation with the command line below: C:\MinGW\bin\g++.exe -shared

How to change Keras backend (where's the json file)?

ε祈祈猫儿з 提交于 2019-11-29 01:13:05
I have installed Keras, and wanted to switch the backend to Theano. I checked out this post , but still have no idea where to put the created json file. Also, below is the error I got when running import keras in Python Shell: Using TensorFlow backend. Traceback (most recent call last): File "", line 1, in import keras File "C:\Python27\lib\site-packages\keras__init__.py", line 2, in from . import backend File "C:\Python27\lib\site-packages\keras\backend__init__.py", line 64, in from .tensorflow_backend import * File "C:\Python27\lib\site-packages\keras\backend\tensorflow_backend.py", line 1,

How can I assign/update subset of tensor shared variable in Theano?

心已入冬 提交于 2019-11-28 21:11:55
When compiling a function in theano , a shared variable(say X) can be updated by specifying updates=[(X, new_value)] . Now I am trying to update only subset of a shared variable: from theano import tensor as T from theano import function import numpy X = T.shared(numpy.array([0,1,2,3,4])) Y = T.vector() f = function([Y], updates=[(X[2:4], Y)] # error occur: # 'update target must # be a SharedVariable' The codes will raise a error "update target must be a SharedVariable", I guess that means update targets can't be non-shared variables. So is there any way to compile a function to just udpate