編譯的時候出現了一些問題，記錄一下

==========================

經過查閱資料，把alexnet_base.py和customlayer.py裡都修改了一下

from keras.layer import merge

就可以了

全部改成merge（程式碼段裡相應的也需要修改）

全部從keras.layer裡import，而不是keras.layers.core

============================

首先我是用的是tensorflow作為backend，一開始再jupyter notebook上直接編譯的時候

ValueError: You are tring to use the old GPU back-end. It was removed from Theano. Use device=cuda* now. See https://github.com/Theano/Theano/wiki/Converting-to-the-new-gpu-back-end%28gpuarray%29 for more information.
 

開啟code/alexnet_base.py

修改了

os.environ['THEANO_FLAGS'] = "device=cuda×"  

/home/chutz/anaconda3/lib/python3.6/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
  from ._conv import register_converters as _register_converters
Using TensorFlow backend.
WARNING (theano.tensor.blas): Using NumPy C-API based implementation for BLAS functions.
ERROR (theano.gpuarray): Could not initialize pygpu, support disabled
Traceback (most recent call last):
  File "/home/chutz/anaconda3/lib/python3.6/site-packages/theano/gpuarray/__init__.py", line 227, in <module>
    use(config.device)
  File "/home/chutz/anaconda3/lib/python3.6/site-packages/theano/gpuarray/__init__.py", line 214, in use
    init_dev(device, preallocate=preallocate)
  File "/home/chutz/anaconda3/lib/python3.6/site-packages/theano/gpuarray/__init__.py", line 99, in init_dev
    **args)
  File "pygpu/gpuarray.pyx", line 651, in pygpu.gpuarray.init
  File "pygpu/gpuarray.pyx", line 569, in pygpu.gpuarray.pygpu_init
ValueError: invalid literal for int() with base 10: '*'
 

我就註釋了import theano as T，如果有知道原因的大神還請不吝賜教

再執行就出現了

ImportError                               Traceback (most recent call last)
<ipython-input-1-fcf16f365b4d> in <module>()
      4 from keras.optimizers import SGD
      5 
----> 6from alexnet_base import *
      7 from utils import *

/media/chutz/000FC3F700054C75/AlexNet/AlexNet-Experiments-Keras/Code/alexnet_base.py
 
 in <module>()
     11     Input, Merge, Lambda
     12 from keras.layers.convolutional import Convolution2D, MaxPooling2D, ZeroPadding2D
---> 13from convnetskeras.customlayers import convolution2Dgroup, crosschannelnormalization,\
     14     splittensor, Softmax4D
     15 

/media/chutz/000FC3F700054C75/AlexNet/AlexNet-Experiments-Keras/convnets-keras/convnetskeras/customlayers.py in <module>()
      1 import numpy as np
----> 2from keras.layers.core import  Lambda, Merge
      3 from keras.layers.convolutional import Convolution2D
      4 from keras import backend as K
      5 

ImportError: cannot import name 'Merge'