torms3 / kaffe Goto Github PK
View Code? Open in Web Editor NEWCaffe interface to support Deep Learning for Connectomics
Caffe interface to support Deep Learning for Connectomics
the forward pass is almost done. any clue?
(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'
leave an issue here to keep in mind that the inference could be speed up by improving the patch blending.
any idea what is happening?
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]
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.