get_mnist.sh: changed the script to generate leveldb as well.
convert script: spacing
Merge pull request #7 from jeffdonahue/headers
modify makefile to recompile on changes to header files
modify makefile to recompile on changes to header files
modify makefile to recompile on changes to header files
Update README.md
Merge pull request #6 from jeffdonahue/flatten
add flatten layer
add flatten layer
add flatten layer
net.cpp: LOG to DLOG
io.cpp: changed back CV_LOAD_IMAGE_COLOR for earlier versions of opencv
Update io.cpp
git ignore
net speed benchmark: set device 0
removed the -Wl flag which was an earlier experimental try
makefile update
Merge branch 'master' of github.com:Yangqing/caffe
makefile: add both lib and lib64 to the cuda library path.
makefile: added a MATLAB_DIR variable. pycaffe and matcaffe will not be compiled in default unless one calls make pycaffe or make matcaffe explicitly.
update Makefile and add some more docs
Merge remote-tracking branch 'origin/master'
cleanup and include ILSVRC mean image
first pass at matlab wrapper (somewhat messy still)
fix Makefile problem
fixed minor typo in imagenet wrapper
cleaned makefile a little bit
Merge branch 'master' of github.com:Yangqing/caffe
remove remaining distributed solver stuff
remove caffe header for distributed solver
removed the unsuccessful distributed solver code
fix pycaffe dependency
fixed the missing CV flag
makefile: not compile test in default
Merge branch 'master' of github.com:Yangqing/caffe
makefile: fixed the nvcc path
io.cpp: changed the imread flag to cv::IMREAD_COLOR
Merge branch 'master' of github.com:Yangqing/caffe
added explanation notes to syncedmem
imagenet_solver.prototxt: added back the missing test line, not sure when it slipped off the repo
Merge branch 'master' of github.com:Yangqing/caffe
imagenet deploy prototxt: instead of having a data layer, this network proto takes an external blob called data. The shape is hardcoded to accompany the imagenet python wrapper at python/caffe/imagenet/wrapper.py. You need to change the shape if you intend to use other shapes.
print status message on error opening leveldb
Merge branch 'master', remote-tracking branch 'origin'
removed the StillFresh function that was used to make sure training does not happen with an earlier version of code.
Made a major change: when initializing a network, the input size are no longer provided by an additional vector of blobs, but should be specified in the netparameters proto by the field "input_dim". This avoid the often awkward code of creating a dummy input vector just for the sake of initializing the network.
wrapper update
finetune code
pycaffe: added a temporary numpy 1.6 compile solution
misc update
pycaffe update and imagenet wrapper
pycaffe update
linecount improvement
ilsvrc 2012 mean
removed obsolete scripts
python reorganization
changed makefile, and removed the no longer needed cuda convnet translator.
changed the python file paths
added pycaffe wrapper. Preparing to clean the structure
Merge branch 'master' of github.com:Yangqing/caffe
Conflicts:
Makefile
Conflicts:
Makefile
remove python deps
stochastic pooling: avoid nan
io.hpp bugfix
added infogain loss layer
bugfix
misc update
Merge branch 'master' of github.com:Yangqing/caffeine
ilsvrc 2012 train file list
distributed solver still having bugs. Pausing for now...
distributed solver: small fix, still bugs
distributed server update. bug in synchronous connections.
data layer: random skip
working asynchronous sgd code. may have errors.
distributed solver - not checked thoroughly
solver minor change
accuracy layer: also produce logprob
imagenet solver 2nd try
imagenet test prototxt
solver restructuring: now all prototxt are specified in the solver protocol buffer
stochastic pooling test
test convolution more thoroughly
script to convert cifar data
script to get cifar
test net scripts
data_layer: more clear logging
syncedmem: added code to not use cudamalloc/cudafree
data_layer: do center cropping when testing
common.cpp: rand seed fix
Merge branch 'master' of github.com:Yangqing/caffeine
pooling layer: added stochastic pooling layer, not tested, compilable
convert_imageset.cpp script: added error message
caffe common cpp: fixed an embarassing bug
removed an accidental mnist update
python code: use BGR order to match the C++ code
syncedmem bugfix
option to run on cpu without gpu
imagenet solver: a better decreasing policy
bugfix and made the C++ interface for creating leveldb
Merge branch 'master' of github.com:Yangqing/caffe
added back opencv dependency and convert scripts
added back opencv dependency and convert scripts
regarding https://plus.google.com/113952791760990667476/posts/Q5fwQY6JeEq - stopped the adagrad attempt.
neuron layer test: added bnll