Issue with running tutorial

[sdwfrost]

Everything goes fine until the very end

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
/usr/local/lib/python3.4/dist-packages/theano/compile/function_module.py in __call__(self, *args, **kwargs)
    858         try:
--> 859             outputs = self.fn()
    860         except Exception:

ValueError: softmaxes.shape[0] (100) != y_lengths.shape[0] (0)

During handling of the above exception, another exception occurred:

ValueError                                Traceback (most recent call last)
<ipython-input-13-8890488df5a1> in <module>()
      1 # train:
      2 for i in range(10000):
----> 3     error = model.update_fun(numerical_lines, numerical_lengths)
      4     if i % 100 == 0:
      5         print("epoch %(epoch)d, error=%(error).2f" % ({"epoch": i, "error": error}))

/usr/local/lib/python3.4/dist-packages/theano/compile/function_module.py in __call__(self, *args, **kwargs)
    869                     node=self.fn.nodes[self.fn.position_of_error],
    870                     thunk=thunk,
--> 871                     storage_map=getattr(self.fn, 'storage_map', None))
    872             else:
    873                 # old-style linkers raise their own exceptions

/usr/local/lib/python3.4/dist-packages/theano/gof/link.py in raise_with_op(node, thunk, exc_info, storage_map)
    312         # extra long error message in that case.
    313         pass
--> 314     reraise(exc_type, exc_value, exc_trace)
    315 
    316 

/usr/local/lib/python3.4/dist-packages/six.py in reraise(tp, value, tb)
    683             value = tp()
    684         if value.__traceback__ is not tb:
--> 685             raise value.with_traceback(tb)
    686         raise value
    687 

/usr/local/lib/python3.4/dist-packages/theano/compile/function_module.py in __call__(self, *args, **kwargs)
    857         t0_fn = time.time()
    858         try:
--> 859             outputs = self.fn()
    860         except Exception:
    861             if hasattr(self.fn, 'position_of_error'):

ValueError: softmaxes.shape[0] (100) != y_lengths.shape[0] (0)
Apply node that caused the error: <theano_lstm.masked_loss.MaskedLoss object at 0x7f374891eb70>(InplaceDimShuffle{2,0,1}.0, Subtensor{::, int64::}.0, Elemwise{add,no_inplace}.0, Alloc.0)
Toposort index: 145
Inputs types: [TensorType(float64, 3D), TensorType(int32, matrix), TensorType(int32, vector), TensorType(int32, vector)]
Inputs shapes: [(100, 55, 51), (100, 55), (0,), (0,)]
Inputs strides: [(8, 40800, 800), (224, 4), (4,), (4,)]
Inputs values: ['not shown', 'not shown', array([], dtype=int32), array([], dtype=int32)]
Outputs clients: [[Sum{acc_dtype=float64}(<theano_lstm.masked_loss.MaskedLoss object at 0x7f374891eb70>.0), Shape_i{0}(<theano_lstm.masked_loss.MaskedLoss object at 0x7f374891eb70>.0)]]

Backtrace when the node is created:
  File "/home/simon/Programs/theano_lstm/theano_lstm/masked_loss.py", line 327, in make_node
    T.Tensor(dtype=softmaxes.dtype, broadcastable=[False])()])

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

Versions of software below

numpy==1.10.4
scipy==0.17.0
Theano==0.7.0
theano-lstm==0.0.14

[MLRules]

Same Error here.

numpy==1.11.1 scipy==0.18.0 Theano==0.9.0.dev2

Traceback (most recent call last): File "\Anaconda3\envs\p34\lib\site-packages\theano-0.9.0.dev2-py3.4.egg\theano\compile\function_module.py", line 866, in call self.fn() if output_subset is None else\ ValueError: softmaxes.shape0 != y_lengths.shape0

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/TheanoLSTM.py", line 248, in error = model.update_fun(numerical_lines, numerical_lengths) File "\Anaconda3\envs\p34\lib\site-packages\theano-0.9.0.dev2-py3.4.egg\theano\compile\function_module.py", line 879, in call storage_map=getattr(self.fn, 'storage_map', None)) File "\Anaconda3\envs\p34\lib\site-packages\theano-0.9.0.dev2-py3.4.egg\theano\gof\link.py", line 325, in raise_with_op reraise(exc_type, exc_value, exc_trace) File "\Anaconda3\envs\p34\lib\site-packages\six.py", line 685, in reraise raise value.with_traceback(tb) File "\Anaconda3\envs\p34\lib\site-packages\theano-0.9.0.dev2-py3.4.egg\theano\compile\function_module.py", line 866, in call self.fn() if output_subset is None else\ ValueError: softmaxes.shape0 != y_lengths.shape0 Apply node that caused the error: <theano_lstm.masked_loss.MaskedLoss object at 0x0000000006029B38>(InplaceDimShuffle{2,0,1}.0, Subtensor{::, int64::}.0, Elemwise{add,no_inplace}.0, Alloc.0) Toposort index: 149 Inputs types: [TensorType(float64, 3D), TensorType(int32, matrix), TensorType(int32, vector), TensorType(int32, vector)] Inputs shapes: [(100, 37, 57), (100, 37), (0,), (0,)] Inputs strides: [(8, 45600, 800), (152, 4), (4,), (4,)] Inputs values: ['not shown', 'not shown', array([], dtype=int32), array([], dtype=int32)] Outputs clients: [[Sum{acc_dtype=float64}(<theano_lstm.masked_loss.MaskedLoss object at 0x0000000006029B38>.0), Shape_i{0}(<theano_lstm.masked_loss.MaskedLoss object at 0x0000000006029B38>.0)]]

Backtrace when the node is created(use Theano flag traceback.limit=N to make it longer): File "/TheanoLSTM.py", line 242, in celltype=RNN # use RNN or LSTM File "/TheanoLSTM.py", line 73, in init self.create_cost_fun() File "/TheanoLSTM.py", line 145, in create_cost_fun starting_when).sum() File "\Anaconda3\envs\p34\lib\site-packages\theano-0.9.0.dev2-py3.4.egg\theano\gof\op.py", line 602, in call node = self.make_node(_inputs, *_kwargs) File "D:\Dev\Machine Learning\Theano\TheanoLSTM\theano_lstm\masked_loss.py", line 327, in make_node T.Tensor(dtype=softmaxes.dtype, broadcastable=[False])()])

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

Process finished with exit code 1

[gkennos]

I had that error and fixed it by changing the function pad_into_matrix as follows (notice moving the list(lengths) earlier because the call to max consumes the iterator object so list(lengths) returns [] if applied after max()):

def pad_into_matrix(rows, padding = 0):
    if len(rows) == 0:
        return np.array([0, 0], dtype=np.int32)
    lengths = list(map(len, rows))
    width = max(lengths)
    height = len(rows)
    mat = np.empty([height, width], dtype=rows[0].dtype)
    mat.fill(padding)
    for i, row in enumerate(rows):
        mat[i, 0:len(row)] = row
    return mat, lengths