hello everyone,
i can not fix following error, can anyone give me some help ? thanks a lot.
Traceback (most recent call last):
File "mx_1.8m_u8_manvob.py", line 171, in <module>
cost = tr_fn(bx, bxm, by, bym)
File
"/scratch2/wzhang/4.software/Theano/theano/compile/function_module.py",
line 879, in __call__
storage_map=getattr(self.fn, 'storage_map', None))
File "/scratch2/wzhang/4.software/Theano/theano/gof/link.py", line 325,
in raise_with_op
reraise(exc_type, exc_value, exc_trace)
File
"/scratch2/wzhang/4.software/Theano/theano/compile/function_module.py",
line 866, in __call__
self.fn() if output_subset is None else\
ValueError: GpuReshape: cannot reshape input of shape (960, 960) to shape
(12, 80).
Apply node that caused the error:
GpuReshape{2}(GpuElemwise{sub,no_inplace}.0, MakeVector{dtype='int64'}.0)
Toposort index: 776
Inputs types: [CudaNdarrayType(float32, matrix), TensorType(int64, vector)]
Inputs shapes: [(960, 960), (2,)]
Inputs strides: [(960, 1), (8,)]
Inputs values: ['not shown', array([12, 80])]
Outputs clients: [[GpuElemwise{mul,no_inplace}(GpuReshape{2}.0,
GpuDimShuffle{1,0}.0)]]
HINT: Re-running with most Theano optimization disabled could give you a
back-trace of when this node was created. This can be done with by setting
the Theano flag 'optimizer=fast_compile'. If that does not work, Theano
optimizations can be disabled with 'optimizer=None'.
HINT: Use the Theano flag 'exception_verbosity=high' for a debugprint and
storage map footprint of this apply node.
--
---
You received this message because you are subscribed to the Google Groups
"theano-users" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
For more options, visit https://groups.google.com/d/optout.
