我正在尝试在keras中实现一个神经网络,其设计如下:http://nlp.cs.rpi.edu/paper/AAAI15.pdf。该算法基本上有三个输入。输入2和输入3通过相同的权重矩阵W1相乘产生O2和O3。输入1通过W2相乘产生O1。然后,我们需要对O1 * O2和O1 * O3进行点积。我正在尝试在keras中实现这一点。
我首先想到使用keras Graph类,并将W1作为具有两个输入和两个输出的共享节点层。到目前为止还好。然后问题就出现了,即如何使用O1去点乘这两个输出。我尝试定义自定义函数:
编译时出现问题,因为Keras只想给Lambda层提供一个输入:
我认为一种替代方案可能是使用一个
如果我使用
我考虑尝试将O1、O2和O3连接在一起成为单个向量作为输出层,然后在目标函数内执行乘法。但是,这将要求目标函数拆分其输入,这在keras中似乎不可能(相关的Theano函数没有传递到keras API)。
有人知道解决方案吗?
编辑:
我认为我取得了一些进展,因为我发现
我首先想到使用keras Graph类,并将W1作为具有两个输入和两个输出的共享节点层。到目前为止还好。然后问题就出现了,即如何使用O1去点乘这两个输出。我尝试定义自定义函数:
def layer_mult(X, Y):
return K.dot(X * K.transpose(Y))
然后:
ntm.add_node(Lambda(layer_mult, output_shape = (1,1)), name = "ls_pos", inputs = ["O1", "O2"])
ntm.add_node(Lambda(layer_mult, output_shape = (1,1)), name = "ls_neg", inputs = ["O1", "O3"])
编译时出现问题,因为Keras只想给Lambda层提供一个输入:
1045 func = types.FunctionType(func, globals())
1046 if hasattr(self, 'previous'):
-> 1047 return func(self.previous.get_output(train))
1048 else:
1049 return func(self.input)
TypeError: layer_mult() takes exactly 2 arguments (1 given)
我认为一种替代方案可能是使用一个
Merge
类,它将dot
作为允许合并的类型。但是,Merge
类的输入层必须传递给构造函数。因此,似乎没有办法将共享节点的输出传递到Merge
中以将Merge
添加到Graph
中。如果我使用
Sequential
容器,我可以将它们馈送到Merge
中。但是,那么就没有办法实现两个Sequential
层需要共享相同的权重矩阵。我考虑尝试将O1、O2和O3连接在一起成为单个向量作为输出层,然后在目标函数内执行乘法。但是,这将要求目标函数拆分其输入,这在keras中似乎不可能(相关的Theano函数没有传递到keras API)。
有人知道解决方案吗?
编辑:
我认为我取得了一些进展,因为我发现
shared_node
正在实现dot
(即使它不在文档中)。所以我到了:ntm = Graph()
ntm.add_input(name='g', input_shape=(300,)) # Vector of 300 units, normally distributed around zero
ntm.add_node([pretrained bit], name = "lt", input = "g") # 300 * 128, output = (,128)
n_docs = 1000
ntm.add_input("d_pos", input_shape = (n_docs,)) # (,n_docs)
ntm.add_input("d_neg", input_shape = (n_docs,)) # (,n_docs)
ntm.add_shared_node(Dense(128, activation = "softmax",
# weights = pretrained_W1,
W_constraint = unitnorm(),
W_regularizer = l2(0.001)
), name = "ld",
inputs = ["d_pos", "d_neg"],
outputs = ["ld_pos", "ld_neg"],
merge_mode=None) # n_docs * 128, output = (,128) * 2
ntm.add_shared_node(ActivityRegularization(0,0), #ActivityRegularization is being used as a passthrough - the function of the node is to dot* its inputs
name = "ls_pos",
inputs = ["lt", "d_pos"],
merge_mode = 'dot') # output = (,1)
ntm.add_shared_node(ActivityRegularization(0,0),
name = "ls_neg",
inputs = ["lt", "d_neg"],
merge_mode = 'dot') # output = (,1)
ntm.add_shared_node(ActivityRegularization(0,0),
name = "summed",
inputs = ["ls_pos", "ls_neg"],
merge_mode = 'sum') # output = (,1)
ntm.add_node(ThresholdedReLU(0.5),
input = "summed", name = "loss") # output = (,1)
ntm.add_output(name = "loss_out",
input= "loss")
def obj(X, Y):
return K.sum(Y)
ntm.compile(loss = {'loss_out' : obj}, optimizer = "sgd")
现在出现了以下错误:
>>> ntm.compile(loss = {'loss_out' : obj}, optimizer = "sgd")
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "build/bdist.macosx-10.5-x86_64/egg/keras/models.py", line 602, in compile
File "build/bdist.macosx-10.5-x86_64/egg/keras/layers/advanced_activations.py", line 149, in get_output
File "build/bdist.macosx-10.5-x86_64/egg/keras/layers/core.py", line 117, in get_input
File "build/bdist.macosx-10.5-x86_64/egg/keras/layers/core.py", line 1334, in get_output
File "build/bdist.macosx-10.5-x86_64/egg/keras/layers/core.py", line 1282, in get_output_sum
File "build/bdist.macosx-10.5-x86_64/egg/keras/layers/core.py", line 1266, in get_output_at
File "build/bdist.macosx-10.5-x86_64/egg/keras/layers/core.py", line 730, in get_output
File "build/bdist.macosx-10.5-x86_64/egg/keras/layers/core.py", line 117, in get_input
File "build/bdist.macosx-10.5-x86_64/egg/keras/layers/core.py", line 1340, in get_output
File "build/bdist.macosx-10.5-x86_64/egg/keras/layers/core.py", line 1312, in get_output_dot
File "/Volumes/home500/anaconda/envs/[-]/lib/python2.7/site-packages/theano/tensor/var.py", line 360, in dimshuffle
pattern)
File "/Volumes/home500/anaconda/envs/[-]/lib/python2.7/site-packages/theano/tensor/elemwise.py", line 164, in __init__
(input_broadcastable, new_order))
ValueError: ('You cannot drop a non-broadcastable dimension.', ((False, False, False, False), (0, 'x')))