Hallo zusammen,
ich benutze theano für die gradientenberechnung.
Meine Funktion und die Gradienten werden wohl richtig compiliert.
Doch nach Aufruf eines Funktionswertes für einen Beispieldatensatz erhalte ich folgenden Fehler:
[codebox=pycon file=Unbenannt.txt]Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "...\Anaconda2\lib\site-packages\spyder\utils\site\sitecustomize.py", line 888, in debugfile
debugger.run("runfile(%r, args=%r, wdir=%r)" % (filename, args, wdir))
File "...\Anaconda2\lib\bdb.py", line 400, in run
exec cmd in globals, locals
File "<string>", line 1, in <module>
File "...\Anaconda2\lib\site-packages\spyder\utils\site\sitecustomize.py", line 866, in runfile
execfile(filename, namespace)
File "...\Anaconda2\lib\site-packages\spyder\utils\site\sitecustomize.py", line 87, in execfile
exec(compile(scripttext, filename, 'exec'), glob, loc)
File ".../desktop/vssgp_lvm/vssgp_lvm_startme.py", line 61, in <module>
vSSGP_LVM_opt.callback(x0)
File "vSSGP_LVM_opt.py", line 82, in callback
LL = self.vssgp_lvm.f['LL'](**params)
File "theano\compile\function_module.py", line 886, in __call__
storage_map=getattr(self.fn, 'storage_map', None))
File "theano\gof\link.py", line 325, in raise_with_op
reraise(exc_type, exc_value, exc_trace)
File "theano\compile\function_module.py", line 873, in __call__
self.fn() if output_subset is None else\
ValueError: Input dimension mis-match. (input[0].shape[0] = 50, input[1].shape[0] = 1)
Apply node that caused the error: Elemwise{sub,no_inplace}(InplaceDimShuffle{0,1,x}.0, InplaceDimShuffle{1,0,x}.0)
Toposort index: 61
Inputs types: [TensorType(float64, (False, False, True)), TensorType(float64, (False, False, True))]
Inputs shapes: [(50L, 1L, 1L), (1L, 50L, 1L)]
Inputs strides: [(8L, 8L, 8L), (400L, 8L, 8L)]
Inputs values: ['not shown', 'not shown']
Outputs clients: [[Elemwise{Composite{((exp((i0 * i1)) * cos((i2 + i3))) + (exp((i0 * i4)) * cos((i5 + i6 + i7))))}}[(0, 1)](TensorConstant{(1L, 1L, 1L) of -0.5}, Sum{axis=[3], acc_dtype=float64}.0, Sum{axis=[3], acc_dtype=float64}.0, Elemwise{sub,no_inplace}.0, Sum{axis=[3], acc_dtype=float64}.0, Sum{axis=[3], acc_dtype=float64}.0, InplaceDimShuffle{0,1,x}.0, InplaceDimShuffle{1,0,x}.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[/code]
kennt sich hier jemand aus und kann mir helfen?
Grüße Romaxx
