Theano:这个共享变量已经有了一个更新表达式

时间:2015-11-25 19:51:36

标签: python neural-network theano

在调用theano.function()时,有没有办法在同一个共享变量上定义多个更新?

示例:

updates = []
updates.append([(self.W, self.W - 1)])
updates.append([(self.W, self.W - 2)])
train = th.function(inputs=[index], outputs=[cost], updates=updates)

会抛出错误this shared variable already has an update expression

ignore_bug_before` to at least "0.7".
  tolerate_inplace_aliasing=tolerate_inplace_aliasing)
Traceback (most recent call last):
  File "ae.py", line 340, in <module>
    main()
  File "ae.py", line 315, in main
    ae.train(n_epochs=n_epochs, mini_batch_size=100, learning_rate=0.002, train_data= train_sentence_embeddings, test_data= test_sentence_embeddings)
  File "ae.py", line 97, in train
    givens={x:self.X[index:index+mini_batch_size,:]})
  File "/usr/local/lib/python2.7/dist-packages/theano/compile/function.py", line 266, in function
    profile=profile)
  File "/usr/local/lib/python2.7/dist-packages/theano/compile/pfunc.py", line 489, in pfunc
    no_default_updates=no_default_updates)
  File "/usr/local/lib/python2.7/dist-packages/theano/compile/pfunc.py", line 198, in rebuild_collect_shared
    (store_into, update_d[store_into]))
ValueError: ('this shared variable already has an update expression', (W, DimShuffle{1,0}.0))

我有兴趣这样做,因为我有权重矩阵,我需要更新它的不同部分有不同的更新(我使用set_subtensor)。

1 个答案:

答案 0 :(得分:4)

正如theano-users邮件列表this thread中所解释的那样......

您需要链接set_subtensor,以便最终只在更新列表中为整个张量输入一个条目。

例如(代码不像原版,因为原版实际上并没有在任何地方包含set_subtensor):

new_w = self.W
new_W = theano.tensor.set_subtensor(new_W[0], -1)
new_W = theano.tensor.set_subtensor(new_W[1], -2)
updates = [(self.W, new_W)]
train = theano.function(inputs=[index], outputs=[cost], updates=updates)