Theano Scan Op的梯度输入断开

Question

我有许多不同大小的物品。 对于每个组，一个（已知）项是“正确”项。 有一个功能可以为每个项目分配分数。 这样就形成了项目得分的平面向量，以及告诉索引每个组从何处开始以及其大小的向量。 我希望对每个组中的分数进行“ softmax”运算，以分配项概率，然后取正确答案的概率对数的总和。 这是一个更简单的版本，在这里，我们只返回正确答案的分数，而没有softmax和对数。

import numpy                                                                                                                                                                                                                                                                          
import theano                                                                                                                                                                                                                                                                         
import theano.tensor as T                                                                                                                                                                                                                                                             
from theano.printing import Print                                                                                                                                                                                                                                                     

def scoreForCorrectAnswer(groupSize, offset, correctAnswer, preds):  
    # for each group, this will get called with the size of
    # the group, the offset of where the group begins in the 
    # predictions vector, and which item in that group is correct                                                                                                                                                                                                                                                                                                                                                                                                                                              
    relevantPredictions = preds[offset:offset+groupSize]                                                                                                                                                                                                                              
    ans = Print("CorrectAnswer")(correctAnswer)                                                                                                                                                                                                                                       
    return relevantPredictions[ans]       

groupSizes = T.ivector('groupSizes')                                                                                                                                                                                                                                                  
offsets = T.ivector('offsets')                                                                                                                                                                                                                                                        
x = T.fvector('x')                                                                                                                                                                                                                                                                    
W = T.vector('W')                                                                                                                                                                                                                                                                     
correctAnswers = T.ivector('correctAnswers')                                                                                                                                                                                                                                          

# for this simple example, we'll just score the items by
# element-wise product with a weight vector                                                                                                                                                                                                                                                                                  
predictions = x * W                                                                                                                                                                                                                                                                   

(values, updates) = theano.map(fn=scoreForCorrectAnswer,                                                                                                                                                                                                                                       
   sequences = [groupSizes, offsets, correctAnswers],                                                                                                                                                                                                                                
   non_sequences = [predictions] )                                                                                                                                                                                                                                                    

func = theano.function([groupSizes, offsets, correctAnswers,                                                                                                                                                                                                                          
        W, x], [values])                                                                                                                                                                                                                                                              

sampleInput = numpy.array([0.1,0.7,0.3,0.05,0.3,0.3,0.3], dtype='float32')                                                                                                                                                                                                            
sampleW = numpy.array([1.0, 1.0, 1.0, 1.0, 1.0, 1.0, 1.0], dtype='float32')                                                                                                                                                                                                           
sampleOffsets = numpy.array([0,4], dtype='int32')                                                                                                                                                                                                                                     
sampleGroupSizes = numpy.array([4,3], dtype='int32')                                                                                                                                                                                                                                  
sampleCorrectAnswers = numpy.array([1,2], dtype='int32')                                                                                                                                                                                                                              

data = func (sampleGroupSizes, sampleOffsets, sampleCorrectAnswers, sampleW, sampleInput)                                                                                                                                                                                             
print data                                                                                                                                                                                                                                                                            

#these all three raise the same exception (see below)                                                                                                                                                                                                                                             
gW1 = T.grad(cost=T.sum(values), wrt=W)                                                                                                                                                                                                                                               
gW2 = T.grad(cost=T.sum(values), wrt=W, disconnected_inputs='warn')                                                                                                                                                                                                                   
gW3 = T.grad(cost=T.sum(values), wrt=W, consider_constant=[groupSizes,offsets])   

这样可以正确地计算输出，但是当我尝试相对于参数W进行渐变时，我得到了（路径缩写）：

Traceback (most recent call last):
  File "test_scan_for_stackoverflow.py", line 37, in <module>
    gW = T.grad(cost=T.sum(values), wrt=W)
  File "Theano-0.6.0rc2-py2.7.egg/theano/gradient.py", line 438, in grad
    outputs, wrt, consider_constant)
  File "Theano-0.6.0rc2-py2.7.egg/theano/gradient.py", line 698, in _populate_var_to_app_to_idx
    account_for(output)
  File "Theano-0.6.0rc2-py2.7.egg/theano/gradient.py", line 694, in account_for
    account_for(ipt)
  File "Theano-0.6.0rc2-py2.7.egg/theano/gradient.py", line 669, in account_for
    connection_pattern = _node_to_pattern(app)
  File "Theano-0.6.0rc2-py2.7.egg/theano/gradient.py", line 554, in _node_to_pattern
    connection_pattern = node.op.connection_pattern(node)
  File "Theano-0.6.0rc2-py2.7.egg/theano/scan_module/scan_op.py", line 1331, in connection_pattern
ils)
  File "Theano-0.6.0rc2-py2.7.egg/theano/scan_module/scan_op.py", line 1266, in compute_gradient
    known_grads={y: g_y}, wrt=x)
  File "Theano-0.6.0rc2-py2.7.egg/theano/gradient.py", line 511, in grad
    handle_disconnected(elem)
  File "Theano-0.6.0rc2-py2.7.egg/theano/gradient.py", line 497, in handle_disconnected
    raise DisconnectedInputError(message)
theano.gradient.DisconnectedInputError: grad method was asked to compute 
the gradient with respect to a variable that is not part of the 
computational graph of the cost, or is used only by a 
non-differentiable operator: groupSizes[t]

现在， groupSizes是恒定的，因此没有理由需要对其进行任何渐变。 通常，您可以通过抑制DisconnectedInputError或告诉Theano在T.grad调用groupSizes视为常量来处理groupSizes （请参见示例脚本的最后T.grad行）。 但是，似乎没有什么办法通过这样的东西倒在内部T.grad中的梯度计算调用ScanOp 。

我想念什么吗？ 这些方法是使梯度计算通过ScanOp进行工作的一种方法吗？

Answer 1

截至2月中旬，这确实是Theano错误。 2013（0.6.0rc-2）。 截至本文发布之日，它已在github上的开发版本中修复。