Hi, I have already set optimizer = None. But Theano cause Memory Error. Thanks, Tsuyoshi.
On Friday, May 24, 2019 at 3:47:16 PM UTC+9, toto haryanto wrote: > > Dear > Miyamoto. > It Seem out of memory problem. > You can open file *.theanorc* and edit the *optimizer*. > *optimizer = fast_run* or if it is not success you can set the *optimizer > = None* > > Thanks > > Regards > Toto > > > > *Toto Haryanto* > > *Mahasiswa Program Doktor* > *Fakultas Ilmu Komputer * > *Universitas Indonesia * > > ========================== > Office: > Depertemen Ilmu Komputer IPB > Jl. Meranti Wing 20 Level 5 > Kampus Darmaga-Bogor > (0251)8625584 > <http://cs.ipb.ac.id/~bioinfo/> > email : totoha...@[ipb.ac.id || apps.ipb.ac.id <javascript:>] > http://totoharyanto.staff.ipb.ac.id > http://cs.ipb.ac.id/~bioinfo/ > ========================== > > > On Fri, May 24, 2019 at 10:55 AM 宮本剛 <[email protected] > <javascript:>> wrote: > >> Hi. >> >> I tried to execute a sample python program on the book >> Deep-Learning-with-Keras >> <https://github.com/PacktPublishing/Deep-Learning-with-Keras> >> >> But the program cause Memory Error detailed follows: >> >> MemoryError: >> Apply node that caused the error: Elemwise{sgn}(Elemwise{add,no_inplace}.0) >> Toposort index: 419 >> Inputs types: [TensorType(float32, 4D)] >> Inputs shapes: [(3, 400, 400, 64)] >> Inputs strides: [(40960000, 1600, 4, 640000)] >> Inputs values: ['not shown'] >> Inputs type_num: [11] >> Outputs clients: [[Elemwise{mul}(Elemwise{mul}.0, Elemwise{sgn}.0)]] >> >> Backtrace when the node is created(use Theano flag traceback.limit=N to make >> it longer): >> File "C:\ProgramData\Anaconda3\lib\site-packages\theano\gradient.py", line >> 1326, in access_grad_cache >> term = access_term_cache(node)[idx] >> File "C:\ProgramData\Anaconda3\lib\site-packages\theano\gradient.py", line >> 1021, in access_term_cache >> output_grads = [access_grad_cache(var) for var in node.outputs] >> File "C:\ProgramData\Anaconda3\lib\site-packages\theano\gradient.py", line >> 1021, in <listcomp> >> output_grads = [access_grad_cache(var) for var in node.outputs] >> File "C:\ProgramData\Anaconda3\lib\site-packages\theano\gradient.py", line >> 1326, in access_grad_cache >> term = access_term_cache(node)[idx] >> File "C:\ProgramData\Anaconda3\lib\site-packages\theano\gradient.py", line >> 1021, in access_term_cache >> output_grads = [access_grad_cache(var) for var in node.outputs] >> File "C:\ProgramData\Anaconda3\lib\site-packages\theano\gradient.py", line >> 1021, in <listcomp> >> output_grads = [access_grad_cache(var) for var in node.outputs] >> File "C:\ProgramData\Anaconda3\lib\site-packages\theano\gradient.py", line >> 1326, in access_grad_cache >> term = access_term_cache(node)[idx] >> File "C:\ProgramData\Anaconda3\lib\site-packages\theano\gradient.py", line >> 1162, in access_term_cache >> new_output_grads) >> >> Debugprint of the apply node: >> Elemwise{sgn} [id A] <TensorType(float32, 4D)> '' >> |Elemwise{add,no_inplace} [id B] <TensorType(float32, 4D)> '' >> |InplaceDimShuffle{0,2,3,1} [id C] <TensorType(float32, 4D)> '' >> | |AbstractConv2d{convdim=2, border_mode='half', subsample=(1, 1), >> filter_flip=True, imshp=(None, 3, None, None), kshp=(64, 3, 3, 3), >> filter_dilation=(1, 1), num_groups=1, unshared=False} [id D] >> <TensorType(float32, 4D)> '' >> | |InplaceDimShuffle{0,3,1,2} [id E] <TensorType(float32, 4D)> '' >> | | |Join [id F] <TensorType(float32, 4D)> '' >> | | |TensorConstant{0} [id G] <TensorType(int8, scalar)> >> | | |/variable [id H] <TensorType(float32, 4D)> >> | | |/variable [id I] <TensorType(float32, 4D)> >> | | |/placeholder [id J] <TensorType(float32, 4D)> >> | |InplaceDimShuffle{3,2,0,1} [id K] <TensorType(float32, 4D)> '' >> | |block1_conv1/kernel [id L] <TensorType(float32, 4D)> >> |Reshape{4} [id M] <TensorType(float32, (True, True, True, False))> '' >> |block1_conv1/bias [id N] <TensorType(float32, vector)> >> |MakeVector{dtype='int64'} [id O] <TensorType(int64, vector)> '' >> |Elemwise{Cast{int64}} [id P] <TensorType(int64, scalar)> '' >> | |TensorConstant{1} [id Q] <TensorType(int8, scalar)> >> |Elemwise{Cast{int64}} [id R] <TensorType(int64, scalar)> '' >> | |TensorConstant{1} [id Q] <TensorType(int8, scalar)> >> |Elemwise{Cast{int64}} [id S] <TensorType(int64, scalar)> '' >> | |TensorConstant{1} [id Q] <TensorType(int8, scalar)> >> |Subtensor{int64} [id T] <TensorType(int64, scalar)> '' >> |Shape [id U] <TensorType(int64, vector)> '' >> | |block1_conv1/bias [id N] <TensorType(float32, vector)> >> |Constant{0} [id V] <int64> >> >> >> I don't know what's wrong. >> >> >> >> -- >> >> --- >> 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] <javascript:>. >> To view this discussion on the web visit >> https://groups.google.com/d/msgid/theano-users/31013f94-a40c-4c52-bf3b-d78390a33a61%40googlegroups.com >> >> <https://groups.google.com/d/msgid/theano-users/31013f94-a40c-4c52-bf3b-d78390a33a61%40googlegroups.com?utm_medium=email&utm_source=footer> >> . >> 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]. To view this discussion on the web visit https://groups.google.com/d/msgid/theano-users/08903454-b4f8-4b87-ab2e-fa72fa43ae7c%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
