When I try to run the following code:
a = T.matrix('a')
b = T.matrix('b')
f = theano.function([a, b], T.batched_dot(a,b))
f([[1, 2], [5, 6]],[[3,4],[7,8]])
I get the following error and stack trace:
---------------------------------------------------------------------------
ImportError Traceback (most recent call last)
<ipython-input-13-42cb5508791b> in <module>()
1 a = T.matrix('a')
2 b = T.matrix('b')
----> 3 f = theano.function([a, b], T.batched_dot(a,b))
4 f([[1, 2], [5, 6]],[[3,4],[7,8]])
/usr/local/lib/python2.7/dist-packages/theano/compile/function.pyc in function(inputs, outputs, mode, updates, givens, no_default_updates, accept_inplace, name, rebuild_strict, allow_input_downcast, profile, on_unused_input)
264 allow_input_downcast=allow_input_downcast,
265 on_unused_input=on_unused_input,
--> 266 profile=profile)
267 # We need to add the flag check_aliased inputs if we have any mutable or
268 # borrowed used defined inputs
/usr/local/lib/python2.7/dist-packages/theano/compile/pfunc.pyc in pfunc(params, outputs, mode, updates, givens, no_default_updates, accept_inplace, name, rebuild_strict, allow_input_downcast, profile, on_unused_input)
509 return orig_function(inputs, cloned_outputs, mode,
510 accept_inplace=accept_inplace, name=name, profile=profile,
--> 511 on_unused_input=on_unused_input)
512
513
/usr/local/lib/python2.7/dist-packages/theano/compile/function_module.pyc in orig_function(inputs, outputs, mode, accept_inplace, name, profile, on_unused_input)
1464 profile=profile,
1465 on_unused_input=on_unused_input).create(
-> 1466 defaults)
1467
1468 t2 = time.time()
/usr/local/lib/python2.7/dist-packages/theano/compile/function_module.pyc in create(self, input_storage, trustme)
1322 theano.config.traceback.limit = 0
1323 _fn, _i, _o = self.linker.make_thunk(
-> 1324 input_storage=input_storage_lists)
1325 finally:
1326 theano.config.traceback.limit = limit_orig
/usr/local/lib/python2.7/dist-packages/theano/gof/link.pyc in make_thunk(self, input_storage, output_storage)
517 def make_thunk(self, input_storage=None, output_storage=None):
518 return self.make_all(input_storage=input_storage,
--> 519 output_storage=output_storage)[:3]
520
521 def make_all(self, input_storage, output_storage):
/usr/local/lib/python2.7/dist-packages/theano/gof/vm.pyc in make_all(self, profiler, input_storage, output_storage)
895 storage_map,
896 compute_map,
--> 897 no_recycling))
898 if not hasattr(thunks[-1], 'lazy'):
899 # We don't want all ops maker to think about lazy Ops.
/usr/local/lib/python2.7/dist-packages/theano/scan_module/scan_op.pyc in make_thunk(self, node, storage_map, compute_map, no_recycling)
592 name=self.name,
593 profile=profile,
--> 594 on_unused_input='ignore')
595
596 try:
/usr/local/lib/python2.7/dist-packages/theano/compile/function.pyc in function(inputs, outputs, mode, updates, givens, no_default_updates, accept_inplace, name, rebuild_strict, allow_input_downcast, profile, on_unused_input)
264 allow_input_downcast=allow_input_downcast,
265 on_unused_input=on_unused_input,
--> 266 profile=profile)
267 # We need to add the flag check_aliased inputs if we have any mutable or
268 # borrowed used defined inputs
/usr/local/lib/python2.7/dist-packages/theano/compile/pfunc.pyc in pfunc(params, outputs, mode, updates, givens, no_default_updates, accept_inplace, name, rebuild_strict, allow_input_downcast, profile, on_unused_input)
509 return orig_function(inputs, cloned_outputs, mode,
510 accept_inplace=accept_inplace, name=name, profile=profile,
--> 511 on_unused_input=on_unused_input)
512
513
/usr/local/lib/python2.7/dist-packages/theano/compile/function_module.pyc in orig_function(inputs, outputs, mode, accept_inplace, name, profile, on_unused_input)
1464 profile=profile,
1465 on_unused_input=on_unused_input).create(
-> 1466 defaults)
1467
1468 t2 = time.time()
/usr/local/lib/python2.7/dist-packages/theano/compile/function_module.pyc in create(self, input_storage, trustme)
1322 theano.config.traceback.limit = 0
1323 _fn, _i, _o = self.linker.make_thunk(
-> 1324 input_storage=input_storage_lists)
1325 finally:
1326 theano.config.traceback.limit = limit_orig
/usr/local/lib/python2.7/dist-packages/theano/gof/link.pyc in make_thunk(self, input_storage, output_storage)
517 def make_thunk(self, input_storage=None, output_storage=None):
518 return self.make_all(input_storage=input_storage,
--> 519 output_storage=output_storage)[:3]
520
521 def make_all(self, input_storage, output_storage):
/usr/local/lib/python2.7/dist-packages/theano/gof/vm.pyc in make_all(self, profiler, input_storage, output_storage)
895 storage_map,
896 compute_map,
--> 897 no_recycling))
898 if not hasattr(thunks[-1], 'lazy'):
899 # We don't want all ops maker to think about lazy Ops.
/usr/local/lib/python2.7/dist-packages/theano/sandbox/cuda/__init__.pyc in make_thunk(self, node, storage_map, compute_map, no_recycling)
257 enable_cuda=False)
258 return super(GpuOp, self).make_thunk(node, storage_map,
--> 259 compute_map, no_recycling)
260
261 theano.compile.debugmode.default_make_thunk.append(
/usr/local/lib/python2.7/dist-packages/theano/gof/op.pyc in make_thunk(self, node, storage_map, compute_map, no_recycling)
737 logger.debug('Trying CLinker.make_thunk')
738 outputs = cl.make_thunk(input_storage=node_input_storage,
--> 739 output_storage=node_output_storage)
740 fill_storage, node_input_filters, node_output_filters = outputs
741
/usr/local/lib/python2.7/dist-packages/theano/gof/cc.pyc in make_thunk(self, input_storage, output_storage, keep_lock)
1071 cthunk, in_storage, out_storage, error_storage = self.__compile__(
1072 input_storage, output_storage,
-> 1073 keep_lock=keep_lock)
1074
1075 res = _CThunk(cthunk, init_tasks, tasks, error_storage)
/usr/local/lib/python2.7/dist-packages/theano/gof/cc.pyc in __compile__(self, input_storage, output_storage, keep_lock)
1013 input_storage,
1014 output_storage,
-> 1015 keep_lock=keep_lock)
1016 return (thunk,
1017 [link.Container(input, storage) for input, storage in
/usr/local/lib/python2.7/dist-packages/theano/gof/cc.pyc in cthunk_factory(self, error_storage, in_storage, out_storage, keep_lock)
1440 else:
1441 module = get_module_cache().module_from_key(
-> 1442 key=key, lnk=self, keep_lock=keep_lock)
1443
1444 vars = self.inputs + self.outputs + self.orphans
/usr/local/lib/python2.7/dist-packages/theano/gof/cmodule.pyc in module_from_key(self, key, lnk, keep_lock)
1074 try:
1075 location = dlimport_workdir(self.dirname)
-> 1076 module = lnk.compile_cmodule(location)
1077 name = module.__file__
1078 assert name.startswith(location)
/usr/local/lib/python2.7/dist-packages/theano/gof/cc.pyc in compile_cmodule(self, location)
1352 lib_dirs=self.lib_dirs(),
1353 libs=libs,
-> 1354 preargs=preargs)
1355 except Exception, e:
1356 e.args += (str(self.fgraph),)
/usr/local/lib/python2.7/dist-packages/theano/sandbox/cuda/nvcc_compiler.pyc in compile_str(module_name, src_code, location, include_dirs, lib_dirs, libs, preargs, rpaths, py_module)
432 #touch the __init__ file
433 open(os.path.join(location, "__init__.py"), 'w').close()
--> 434 return dlimport(lib_filename)
/usr/local/lib/python2.7/dist-packages/theano/gof/cmodule.pyc in dlimport(fullpath, suffix)
291 importlib.invalidate_caches()
292 t0 = time.time()
--> 293 rval = __import__(module_name, {}, {}, [module_name])
294 t1 = time.time()
295 import_time += t1 - t0
ImportError: ('The following error happened while compiling the node', for{gpu,scan_fn}(Elemwise{minimum,no_inplace}.0, GpuSubtensor{int64:int64:int8}.0, GpuSubtensor{int64:int64:int8}.0, Elemwise{minimum,no_inplace}.0), '\n', 'The following error happened while compiling the node', GpuAlloc{memset_0=True}(CudaNdarrayConstant{0.0}, TensorConstant{1}), '\n', '/home/alex/.theano/compiledir_Linux-3.13--generic-x86_64-with-Ubuntu-14.04-trusty-x86_64-2.7.6-64/tmppLzatX/e0c22e1de788a177e13f39a93c579f18.so: undefined symbol: _Z17CudaNdarray_SIZEtPK11CudaNdarray', '[GpuAlloc{memset_0=True}(CudaNdarrayConstant{0.0}, TensorConstant{1})]')
If I replace matrix with vector or tensor3 (and supply properly shaped tensors to the function call), it compiles and runs. For matrix none of dot, tensor_dot, batched_dot work, but addition and subtraction work.
I ran pip install --upgrade theano, and the errors stayed. pip reports my current version to be 0.7. Since it only fails for matrices, could it be because of some library theano depends on that I somehow happen to have misconfigured?
What I did wrong was pip install --upgrade theano. Turned out I already had theano 0.7, which is the latest, so pip install --upgrade did nothing (but it was not apparent because it did upgrade the dependencies).
pip uninstall theano && pip install theano fixed the problem