torms3 / kaffe Goto Github PK

(598/600) loc: (120, 406, 398)
Elapsed: 1.83546996117
(599/600) loc: (120, 406, 406)
Elapsed: 1.56470108032
Traceback (most recent call last):
  File "forward.py", line 76, in <module>
    for key in fs.outputs.data.iterkeys():
AttributeError: 'dict' object has no attribute 'data'

python /opt/kaffe/python/forward.py 0 /tmp/julia1L0IrZ.cfg
/opt/caffe/python/caffe/pycaffe.py:13: RuntimeWarning: to-Python converter for std::vector<int, std::allocator<int> > already registered; second conversion method ignored.
  from ._caffe import \
Floating point exception (core dumped)

I0831 08:47:41.129072 14740 net.cpp:249] relu1a does not need backward computation.
I0831 08:47:41.129076 14740 net.cpp:249] conv1a does not need backward computation.
I0831 08:47:41.129081 14740 net.cpp:249] input does not need backward computation.
I0831 08:47:41.129086 14740 net.cpp:292] This network produces output output
I0831 08:47:41.129158 14740 net.cpp:306] Network initialization done.
I0831 08:47:41.129164 14740 net.cpp:307] Memory required for data: 1173627840
I0831 08:47:41.129873 14740 hdf5.cpp:32] Datatype class: H5T_FLOAT
I0831 08:47:41.133083 14740 net.cpp:868] Ignoring source layer drop
I0831 08:47:41.133123 14740 net.cpp:868] Ignoring source layer label
I0831 08:47:41.133133 14740 net.cpp:868] Ignoring source layer label_mask
I0831 08:47:41.133142 14740 net.cpp:868] Ignoring source layer loss

[VolumeDataProvider]
constructing dataset 0...
/tmp/juliaYPS8H7.img.h5
Forward scan dataset 0
(1/18) loc: (10, 123, 123)
F0831 08:47:42.173065 14740 syncedmem.cpp:171] Check failed: error == cudaSuccess (2 vs. 0)  out of memory
*** Check failure stack trace: ***
ERROR: LoadError: failed process: Process(`python /opt/kaffe/python/forward.py 0 /tmp/julia2swuM0.cfg`, ProcessSignaled(6)) [0]