Out of bounds issue with vocab size not divisible by 10

[ftyers]

I get this error when I try and run with a vocabulary size that is not divisible by 10. Padding the vocabulary solves the problem, but it would be good to know why it is happening.

Cost graph is built
INFO:blocks.algorithms:Taking the cost gradient
INFO:blocks.algorithms:The cost gradient computation graph is built
INFO:blocks.main_loop:Entered the main loop
INFO:blocks.algorithms:Initializing the training algorithm
INFO:blocks.algorithms:The training algorithm is initialized
ERROR:blocks.main_loop:Error occured during training.

Blocks will attempt to run `on_error` extensions, potentially saving data, before exiting and reraising the error. Note that the usual `after_training` extensions will *not* be run. The original error will be re-raised and also stored in the training log. Press CTRL + C to halt Blocks immediately.

-------------------------------------------------------------------------------
BEFORE FIRST EPOCH
-------------------------------------------------------------------------------
Training status:
     batch_interrupt_received: False
     epoch_interrupt_received: False
     epoch_started: True
     epochs_done: 0
     iterations_done: 0
     received_first_batch: False
     resumed_from: None
     training_started: True
Log records from the iteration 0:
     time_initialization: 31.707899903063662

Traceback (most recent call last):
  File "morf-gen-nn/train.py", line 275, in <module>
    main_loop.run()
  File "/home/fran/local/lib/python3.5/site-packages/blocks-0.2.0-py3.5.egg/blocks/main_loop.py", line 197, in run
    reraise_as(e)
  File "/home/fran/local/lib/python3.5/site-packages/blocks-0.2.0-py3.5.egg/blocks/utils/__init__.py", line 258, in reraise_as
    six.reraise(type(new_exc), new_exc, orig_exc_traceback)
  File "/usr/lib/python3/dist-packages/six.py", line 686, in reraise
    raise value
  File "/home/fran/local/lib/python3.5/site-packages/blocks-0.2.0-py3.5.egg/blocks/main_loop.py", line 183, in run
    while self._run_epoch():
  File "/home/fran/local/lib/python3.5/site-packages/blocks-0.2.0-py3.5.egg/blocks/main_loop.py", line 232, in _run_epoch
    while self._run_iteration():
  File "/home/fran/local/lib/python3.5/site-packages/blocks-0.2.0-py3.5.egg/blocks/main_loop.py", line 253, in _run_iteration
    self.algorithm.process_batch(batch)
  File "/home/fran/local/lib/python3.5/site-packages/blocks-0.2.0-py3.5.egg/blocks/algorithms/__init__.py", line 190, in process_batch
    self._function(*ordered_batch)
  File "/home/fran/local/lib/python3.5/site-packages/Theano-0.8.2-py3.5.egg/theano/compile/function_module.py", line 871, in __call__
    storage_map=getattr(self.fn, 'storage_map', None))
  File "/home/fran/local/lib/python3.5/site-packages/Theano-0.8.2-py3.5.egg/theano/gof/link.py", line 314, in raise_with_op
    reraise(exc_type, exc_value, exc_trace)
  File "/usr/lib/python3/dist-packages/six.py", line 685, in reraise
    raise value.with_traceback(tb)
  File "/home/fran/local/lib/python3.5/site-packages/Theano-0.8.2-py3.5.egg/theano/compile/function_module.py", line 859, in __call__
    outputs = self.fn()
IndexError: index 69 is out of bounds for size 69
Apply node that caused the error: AdvancedSubtensor1(W, Reshape{1}.0)
Toposort index: 105
Inputs types: [TensorType(float64, matrix), TensorType(int64, vector)]
Inputs shapes: [(69, 100), (190,)]
Inputs strides: [(800, 8), (8,)]
Inputs values: ['not shown', 'not shown']
Outputs clients: [[Reshape{3}(AdvancedSubtensor1.0, MakeVector{dtype='int64'}.0)]]

Backtrace when the node is created(use Theano flag traceback.limit=N to make it longer):
  File "morf-gen-nn/train.py", line 233, in <module>
    batch_cost = m.cost(chars, chars_mask, targets, targets_mask).sum()
  File "/home/fran/local/lib/python3.5/site-packages/blocks-0.2.0-py3.5.egg/blocks/bricks/base.py", line 362, in __call__
    return self.application.apply(self, *args, **kwargs)
  File "/home/fran/local/lib/python3.5/site-packages/blocks-0.2.0-py3.5.egg/blocks/bricks/base.py", line 297, in apply
    outputs = self.application_function(brick, *args, **kwargs)
  File "morf-gen-nn/train.py", line 133, in cost
    self.fork.apply(self.lookup.apply(chars), as_dict=True),mask=chars_mask)),
  File "/home/fran/local/lib/python3.5/site-packages/blocks-0.2.0-py3.5.egg/blocks/bricks/base.py", line 362, in __call__
    return self.application.apply(self, *args, **kwargs)
  File "/home/fran/local/lib/python3.5/site-packages/blocks-0.2.0-py3.5.egg/blocks/bricks/base.py", line 297, in apply
    outputs = self.application_function(brick, *args, **kwargs)
  File "/home/fran/local/lib/python3.5/site-packages/blocks-0.2.0-py3.5.egg/blocks/bricks/lookup.py", line 68, in apply
    return self.W[indices.flatten()].reshape(output_shape)

HINT: Use the Theano flag 'exception_verbosity=high' for a debugprint and storage map footprint of this apply node.

Original exception:
    IndexError: index 69 is out of bounds for size 69
Apply node that caused the error: AdvancedSubtensor1(W, Reshape{1}.0)
Toposort index: 105
Inputs types: [TensorType(float64, matrix), TensorType(int64, vector)]
Inputs shapes: [(69, 100), (190,)]
Inputs strides: [(800, 8), (8,)]
Inputs values: ['not shown', 'not shown']
Outputs clients: [[Reshape{3}(AdvancedSubtensor1.0, MakeVector{dtype='int64'}.0)]]

Backtrace when the node is created(use Theano flag traceback.limit=N to make it longer):
  File "morf-gen-nn/train.py", line 233, in <module>
    batch_cost = m.cost(chars, chars_mask, targets, targets_mask).sum()
  File "/home/fran/local/lib/python3.5/site-packages/blocks-0.2.0-py3.5.egg/blocks/bricks/base.py", line 362, in __call__
    return self.application.apply(self, *args, **kwargs)
  File "/home/fran/local/lib/python3.5/site-packages/blocks-0.2.0-py3.5.egg/blocks/bricks/base.py", line 297, in apply
    outputs = self.application_function(brick, *args, **kwargs)
  File "morf-gen-nn/train.py", line 133, in cost
    self.fork.apply(self.lookup.apply(chars), as_dict=True),mask=chars_mask)),
  File "/home/fran/local/lib/python3.5/site-packages/blocks-0.2.0-py3.5.egg/blocks/bricks/base.py", line 362, in __call__
    return self.application.apply(self, *args, **kwargs)
  File "/home/fran/local/lib/python3.5/site-packages/blocks-0.2.0-py3.5.egg/blocks/bricks/base.py", line 297, in apply
    outputs = self.application_function(brick, *args, **kwargs)
  File "/home/fran/local/lib/python3.5/site-packages/blocks-0.2.0-py3.5.egg/blocks/bricks/lookup.py", line 68, in apply
    return self.W[indices.flatten()].reshape(output_shape)

HINT: Use the Theano flag 'exception_verbosity=high' for a debugprint and storage map footprint of this apply node.