Theano - Keras - 没有名为`pool`的模块

时间:2016-01-20 11:02:30

标签: python machine-learning theano deep-learning keras

我已按以下顺序安装了bleeding edge theano和以下软件包:

gfortran:

sudo apt-get install gfortran 

OpenBLAS:

git clone https://github.com/xianyi/OpenBLAS  
cd OpenBLAS  
make FC=gfortran  
sudo make PREFIX=/usr/local install 

Anaconda,首先下载了Anaconda3-2.4.1-Linux-x86_64.sh,然后:

bash Anaconda3-2.4.1-Linux-x86_64.sh  

然后,pydot(更新后):

conda update conda  
conda update anaconda  
conda install pydot 

他们克隆并安装了Theano:

git clone git://github.com/Theano/Theano.git
python setup.py develop

我从windows移到了linux,并对安装theano感到非常高兴。

我运行一个小脚本,以验证它确实正常工作。

from theano import function, config, shared, sandbox
import theano.tensor as T
import numpy as np
import time

vlen = 10*30*768 # assuming 30 cores and 768 threads per core
iters = 1000

rng = np.random.RandomState(22)
x = shared(np.asarray(rng.rand(vlen), config.floatX))
f = function([], T.exp(x))

print (f.maker.fgraph.toposort()  )
t0 = time.time()
for i in range (iters):
    r = f()
t1 = time.time()
print("Looping " + str(iters) + " times took " + str(t1-t0) + "seconds")
print("Result is " + str(r))
if np.any([isinstance(x.op, T.Elemwise) for x in f.maker.fgraph.toposort()]):
    print ("Used the CPU")
else:
    print (" Used the GPU")

所以,它是有效的,可能是一个微不足道的例子来证明一个观点。

之后,来keras

git clone https://github.com/fchollet/keras.git
python setup.py install

然后我转到keras的examples目录,只需输入

即可
python mnist_mlp.py

我收到以下错误:

Traceback (most recent call last):
  File "mnist_mlp.py", line 13, in <module>
    from keras.models import Sequential
  File "/home/user/anaconda3/lib/python3.5/site-packages/Keras-0.3.1-py3.5.egg/keras/models.py", line 15, in <module>
  File "/home/user/anaconda3/lib/python3.5/site-packages/Keras-0.3.1-py3.5.egg/keras/backend/__init__.py", line 46, in <module>
  File "/home/user/anaconda3/lib/python3.5/site-packages/Keras-0.3.1-py3.5.egg/keras/backend/theano_backend.py", line 4, in <module>
  File "/home/user/anaconda3/lib/python3.5/site-packages/Theano-0.8.0.dev0-py3.5.egg/theano/tensor/signal/downsample.py", line 2, in <module>
    import pool
ImportError: No module named 'pool'

现在,到底是什么...... 我错过了一些包吗?

我认为这不是keras的问题,而是theano问题。

我继续尝试了一个肮脏的技巧pip install pool,然后重新运行上面的例子,但是我得到了错误:

module 'pool' has no attribute 'max_pool2D'

如果需要,我也可以提供堆栈跟踪。

我一直在努力让theano继续努力,急切地想要开始......在整个装置耗尽之前,

1 个答案:

答案 0 :(得分:2)

似乎无法编译文件theano/tensor/signal/pool.py存在问题并修复github