theano

一、认识数据分析的各个库 1、numpy 提供数组支持以及相应的高效处理函数，是Python数据分析的基础，也是SciPy、Pandas等数据处理和科学计算库最基本的函数功能库。 2、pandas 强大、灵活的数据分析和探索工具，包含Series、DataFrame等高级数据结构和工具。 3、matplotlib 基于Numpy的一套Python包，强大的数据可视化工具和作图库，是主要用于绘制数据图表的Python库，提供了绘制各类可视化图形的命令字库、简单的接口，可以方便用户轻松掌握图形的格式，绘制各类可视化图形。 4、Scikit-Learn（Sklearn） 常用的机器学习工具包，提供了完善的机器学习工具箱，支持数据预处理、分类、回归、聚类、预测和模型分析等强大机器学习库，其依赖于Numpy、Scipy和Matplotlib等。 5、SciPy 一个高级的科学计算库，常见的是插值运算、优化算法、图像处理和数学统计等。 6、Keras 是一个高层神经网络API，Keras由纯Python编写而成并基 Tensorflow 、 Theano 以及 CNTK 后端。 TensorFlow和theano以及Keras都是深度学习框架，TensorFlow和theano比较灵活，也比较难学，它们其实就是一个微分器 Keras其实就是TensorFlow和Keras的接口

I installed theano on windows 8, 64 bit. I am using anaconda implementation, python 3.4. Trying to install theano, I diligently followed all steps on this link (which helped on another computer with similar configuration): http://rosinality.ncity.net/doku.php?id=python:installing_theano (English and Korean) whenever I type 'import theano' on my IDE (pycharm) I get a long error message, but I believe the most meaningful portion is: import theano >>>>Exception: Compilation failed (return status=1): C:\Users\xxx\AppData\Local\Theano\compiledir_Windows-8-6.2.9200- Intel64_Family_6_Model_69

全栈工程师开发手册 （作者：栾鹏） python教程全解 Theano Theano在深度学习框架中是祖师级的存在。Theano基于Python语言开发的，是一个擅长处理多维数组的库，这一点和numpy很像。当与其他深度学习库结合起来，它十分适合数据探索。它为执行深度学习中大规模神经网络算法的运算所设计。其实，它可以被更好的理解为一个数学表达式的编辑器：用符号式语言定义你想要的结果，该框架会对你的程序进行编译，来高效运行于GPU或CPU。它与后来出现的TensorFlow功能十分相似，因而两者常常被放在一起比较。它们本身都偏底层，同样的，Theano 像是一个研究平台多过是一个深度学习库。你需要从底层开始做许多工作，来创建你需要的模型。比方说，Theano 没有神经网络的分级。但由于它不支持多 GPU 和水平扩展，在 TensorFlow 的热潮下（它们针对同一个领域），Theano 已然开始被遗忘了。 TensorFlow TensorFlow是由google开源出来的，因为有google作为后台，Tensorflow在深度学习领域一直很有名气。TensorFlow是一个采用数据流图，用于数值计算的开源软件库。它支持Python和C++两种类型的接口。TensorFlow可支持分布式计算，它灵活的架构让你可以在多种平台上展开计算，例如台式计算机中的一个或多个CPU（或GPU）

I am testing Theano with GPU using the script provided in the tutorial for that purpose : # Start gpu_test.py # From http://deeplearning.net/software/theano/tutorial/using_gpu.html#using-gpu from theano import function, config, shared, sandbox import theano.tensor as T import numpy import time vlen = 10 * 30 * 768 # 10 x #cores x # threads per core iters = 1000 rng = numpy.random.RandomState(22) x = shared(numpy.asarray(rng.rand(vlen), config.floatX)) f = function([], T.exp(x)) print(f.maker.fgraph.toposort()) t0 = time.time() for i in xrange(iters): r = f() t1 = time.time() print("Looping %d

To simplify the problem, say when a dimension (or a feature) is already updated n times, the next time I see the feature, I want to set the learning rate to be 1/n. I came up with these codes: def test_adagrad(): embedding = theano.shared(value=np.random.randn(20,10), borrow=True) times = theano.shared(value=np.ones((20,1))) lr = T.dscalar() index_a = T.lvector() hist = times[index_a] cost = T.sum(theano.sparse_grad(embedding[index_a])) gradients = T.grad(cost, embedding) updates = [(embedding, embedding+lr*(1.0/hist)*gradients)] ### Here should be some codes to update also times which are

I have the following code: import theano.tensor as T Words = theano.shared(value = U, name = 'Words') zero_vec_tensor = T.vector() zero_vec = np.zeros(img_w, dtype = theano.config.floatX) set_zero = theano.function([zero_vec_tensor], updates=[(Words, T.set_subtensor(Words[0,:], zero_vec_tensor))]) Which is compiling fine (where U is a numpy array of dtype float64 ). To prevent future type error I want to cast my shared tensor Words into float32 (or theano.config.floatX which is equivalent as I have set floatX to float32 in the config file). I so add Words = T.cast(Words, dtype = theano.config

I tried to update keras.json on Google Colabs, but its throwing UnsupportedOperation error Is there any other alternative to achieve this? You're opening the file as readonly -- pass 'w' to the open call on line 9. ( docs ) 来源： https://stackoverflow.com/questions/50083075/update-keras-json-on-google-colab

I have a theano tensor A such that A.shape = (40, 20, 5) and a theano matrix B such that B.shape = (40, 20). Is there a one-line operation I can perform to get a matrix C, where C.shape = (40, 20) and C(i,j) = A[i, j, B[i,j]] with theano syntax? Essentially, I want to use B as an indexing matrix; what is the most efficient/elegant to do this using theano? You can do the following in numpy: import numpy as np A = np.arange(4 * 2 * 5).reshape(4, 2, 5) B = np.arange(4 * 2).reshape(4, 2) % 5 C = A[np.arange(A.shape[0])[:, np.newaxis], np.arange(A.shape[1]), B] So you can do the same thing in