You have a problem in your code. To help you identify it, u you can n
follow the HINTS hidded in the long output, use the Theano flag

optimizer=fast_compile

Le lun. 3 juil. 2017 10:02, 周泽彪 <[email protected]> a écrit :

>  Building model
>  Loading data
>    File
> "/opt/zebiao.zhou/anaconda2/lib/python2.7/site-packages/theano/gof/link.py",
> line 325, in raise_with_op
>      reraise(exc_type, exc_value, exc_trace)
>      reraise(exc_type, exc_value, exc_trace)
>    File
> "/opt/zebiao.zhou/anaconda2/lib/python2.7/site-packages/theano/gof/link.py",
> line 325, in raise_with_op
>      reraise(exc_type, exc_value, exc_trace)
>  Building model
>  Loading data
>    File
> "/opt/zebiao.zhou/anaconda2/lib/python2.7/site-packages/theano/gof/link.py",
> line 325, in raise_with_op
>      reraise(exc_type, exc_value, exc_trace)
>      reraise(exc_type, exc_value, exc_trace)
>    File "theano/scan_module/scan_perform.pyx", line 397, in
> theano.scan_module.scan_perform.perform
> (/opt/zebiao.zhou/.theano/compiledir_Linux-3.10-el7.x86_64-x86_64-with-centos-7.2.1511-Core-x86_64-2.7.13-64/scan_perform/mod.cpp:4490)
>    File
> "/opt/zebiao.zhou/anaconda2/lib/python2.7/site-packages/theano/scan_module/scan_op.py",
> line 989, in rval
>      r = p(n, [x[0] for x in i], o)
>    File
> "/opt/zebiao.zhou/anaconda2/lib/python2.7/site-packages/theano/scan_module/scan_op.py",
> line 978, in p
>      self, node)
>    File "theano/scan_module/scan_perform.pyx", line 405, in
> theano.scan_module.scan_perform.perform
> (/opt/zebiao.zhou/.theano/compiledir_Linux-3.10-el7.x86_64-x86_64-with-centos-7.2.1511-Core-x86_64-2.7.13-64/scan_perform/mod.cpp:4606)
>    File
> "/opt/zebiao.zhou/anaconda2/lib/python2.7/site-packages/theano/gof/link.py",
> line 325, in raise_with_op
>      reraise(exc_type, exc_value, exc_trace)
>    File "theano/scan_module/scan_perform.pyx", line 397, in
> theano.scan_module.scan_perform.perform
> (/opt/zebiao.zhou/.theano/compiledir_Linux-3.10-el7.x86_64-x86_64-with-centos-7.2.1511-Core-x86_64-2.7.13-64/scan_perform/mod.cpp:4490)
>  ValueError: dimension mismatch in args to gemv (200,0)x(250)->(0)
>  Apply node that caused the error:
> GpuGemv{no_inplace}(GpuSubtensor{int32:int32:}.0, TensorConstant{1.0},
> GpuSubtensor{:int32:, int32:int32:}.0, GpuReshape{1}.0, TensorConstant{1.0})
>  Toposort index: 27
>  Inputs types: [CudaNdarrayType(float32, vector), TensorType(float32,
> scalar), CudaNdarrayType(float32, matrix), CudaNdarrayType(float32,
> vector), TensorType(float32, scalar)]
>  Inputs shapes: [(0,), (), (200, 0), (250,), ()]
>  Inputs strides: [(1,), (), (500, 1), (1,), ()]
>  Inputs values: [CudaNdarray([]), array(1.0, dtype=float32),
> CudaNdarray([]), 'not shown', array(1.0, dtype=float32)]
>  Outputs clients: [[GpuElemwise{Composite{(scalar_sigmoid(i0) * i1)}}[(0,
> 0)](GpuGemv{no_inplace}.0, GpuReshape{1}.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.
>  Apply node that caused the error:
> for{gpu,scan_fn}(Elemwise{Composite{minimum(minimum(i0, i1), i2)}}.0,
> Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0,
> Subtensor{:int64:}.0, Subtensor{int64:int64:int8}.0,
> Subtensor{int64:int64:int8}.0, Elemwise{Composite{min    imum(minimum(i0,
> i1), i2)}}.0, ugW_copy[cuda], cW_copy[cuda], rgW_copy[cuda],
> rgb_copy[cuda], cb_copy[cuda], ugb_copy[cuda], <CudaNdarrayType(float32,
> 3D)>)
>  Toposort index: 24
>  Inputs types: [TensorType(int64, scalar), TensorType(int32, vector),
> TensorType(int32, vector), TensorType(int64, vector), TensorType(int32,
> vector), TensorType(int32, vector), TensorType(int64, scalar),
> CudaNdarrayType(float32, matrix), CudaNdarrayType(float32, mat    rix),
> CudaNdarrayType(float32, matrix), CudaNdarrayType(float32, vector),
> CudaNdarrayType(float32, vector), CudaNdarrayType(float32, vector),
> CudaNdarrayType(float32, 3D)]
>  Inputs shapes: [(), (256,), (256,), (256,), (256,), (256,), (), (250,
> 700), (50, 500), (200, 500), (500,), (200,), (700,), (256, 6, 50)]
>  Inputs strides: [(), (4,), (4,), (8,), (24,), (4,), (), (700, 1), (500,
> 1), (500, 1), (1,), (1,), (1,), (300, 50, 1)]
>  Inputs values: [array(256), 'not shown', 'not shown', 'not shown', 'not
> shown', 'not shown', array(256), 'not shown', 'not shown', 'not shown',
> 'not shown', 'not shown', 'not shown', 'not shown']
>  Outputs clients: [[GpuDot22(for{gpu,scan_fn}.0, lstmW_copy[cuda]),
> GpuGemv{inplace}(GpuCAReduce{add}{0,1}.0, TensorConstant{1.0},
> for{gpu,scan_fn}.0, U_copy[cuda], TensorConstant{1.0}),
> GpuElemwise{Composite{(i0 * tanh((i1 + i2)))}}[(0, 1)](for{gpu,scan_fn}.0,
> GpuDo    t22.0, <CudaNdarrayType(float32, row)>)]]
>
>
>
>
> who can help me~~i don‘t know how to solve it .
>
> --
>
> ---
> 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.
>

-- 

--- 
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.

Reply via email to