tuzhaopeng / nmt-coverage Goto Github PK

Traceback (most recent call last):
  File "train.py", line 100, in <module>
    main()
  File "train.py", line 81, in main
    enc_dec.build()
  File "/projects/tir1/users/cmalaviy/NMT-Coverage/experiments/nmt/encdec.py", line 1864, in build
    c=self.sampling_c)
  File "/projects/tir1/users/cmalaviy/NMT-Coverage/experiments/nmt/encdec.py", line 1725, in build_sampler
    name="{}_sampler_scan".format(self.prefix))
  File "/projects/tir1/users/cmalaviy/anaconda2/lib/python2.7/site-packages/theano/scan_module/scan.py", line 1071, in scan
    scan_outs = local_op(*scan_inputs)
  File "/projects/tir1/users/cmalaviy/anaconda2/lib/python2.7/site-packages/theano/gof/op.py", line 615, in __call__
    node = self.make_node(*inputs, **kwargs)
  File "/projects/tir1/users/cmalaviy/anaconda2/lib/python2.7/site-packages/theano/scan_module/scan_op.py", line 578, in make_node
    inner_sitsot_out.type.ndim))
ValueError: When compiling the inner function of scan (the function called by scan in each of its iterations) the following error has been encountered: The initial state (`outputs_info` in scan nomenclature) of variable IncSubtensor{Set;:int64:}.0 (argument number 4) has 4 dimension(s), while the corresponding variable in the result of the inner function of scan (`fn`) has 1 dimension(s) (it should be one less than the initial state). For example, if the inner function of scan returns a vector of size d and scan uses the values of the previous time-step, then the initial state in scan should be a matrix of shape (1, d). The first dimension of this matrix corresponds to the number of previous time-steps that scan uses in each of its iterations. In order to solve this issue if the two varialbe currently have the same dimensionality, you can increase the dimensionality of the variable in the initial state of scan by using dimshuffle or shape_padleft.