Sergey Karayev [Fri, 6 Dec 2013 03:12:50 +0000 (19:12 -0800)]
fixed bug that renormalized window crops on second resize
Sergey Karayev [Fri, 6 Dec 2013 01:21:47 +0000 (17:21 -0800)]
center_only and corners modes work correctly
Sergey Karayev [Fri, 6 Dec 2013 00:38:36 +0000 (16:38 -0800)]
processing images in batch, with option to use selective search window proposals
Yangqing Jia [Thu, 5 Dec 2013 17:38:11 +0000 (09:38 -0800)]
renaming"
Yangqing Jia [Thu, 5 Dec 2013 09:13:59 +0000 (01:13 -0800)]
Update README.md
Yangqing Jia [Thu, 5 Dec 2013 04:24:26 +0000 (20:24 -0800)]
Merge pull request #9 from jeffdonahue/fixflattenbug
fix really stupid bug in flatten layer (and add test that shows the
Jeff Donahue [Thu, 5 Dec 2013 04:16:25 +0000 (20:16 -0800)]
fix really stupid bug in flatten layer (and add test that shows the
failure case; not sure why CheckGradientExhaustive didn't catch it)
Yangqing Jia [Tue, 3 Dec 2013 18:53:29 +0000 (10:53 -0800)]
lenet.prototxt loss layer rename
Yangqing Jia [Tue, 3 Dec 2013 18:05:19 +0000 (10:05 -0800)]
mnist train script
Yangqing Jia [Mon, 2 Dec 2013 23:44:43 +0000 (15:44 -0800)]
Several changes:
changed the paths for the mnist demo
removed unused fields in SolverParameter
added solver_mode to specify CPU/GPU solving
accordingly, removed the set mode code in the examples code
removed examples/test_read_imagenet since it is trivial
removed get_cifar script since no cifar demo exists.
Yangqing Jia [Mon, 2 Dec 2013 23:19:37 +0000 (15:19 -0800)]
get_mnist.sh: changed the script to generate leveldb as well.
Yangqing Jia [Mon, 2 Dec 2013 00:38:24 +0000 (16:38 -0800)]
convert script: spacing
Yangqing Jia [Thu, 28 Nov 2013 22:51:16 +0000 (14:51 -0800)]
Merge pull request #7 from jeffdonahue/headers
modify makefile to recompile on changes to header files
Jeff Donahue [Thu, 28 Nov 2013 21:55:17 +0000 (13:55 -0800)]
modify makefile to recompile on changes to header files
Yangqing Jia [Thu, 28 Nov 2013 18:42:30 +0000 (10:42 -0800)]
Update README.md
Yangqing Jia [Thu, 28 Nov 2013 05:39:08 +0000 (21:39 -0800)]
Merge pull request #6 from jeffdonahue/flatten
add flatten layer
Jeff Donahue [Thu, 28 Nov 2013 05:29:05 +0000 (21:29 -0800)]
add flatten layer
Yangqing Jia [Thu, 28 Nov 2013 04:54:21 +0000 (20:54 -0800)]
net.cpp: LOG to DLOG
Yangqing Jia [Thu, 28 Nov 2013 04:54:01 +0000 (20:54 -0800)]
io.cpp: changed back CV_LOAD_IMAGE_COLOR for earlier versions of opencv
Yangqing Jia [Thu, 28 Nov 2013 01:00:00 +0000 (17:00 -0800)]
Update io.cpp
Yangqing Jia [Tue, 26 Nov 2013 21:16:12 +0000 (13:16 -0800)]
git ignore
Yangqing Jia [Tue, 26 Nov 2013 18:59:06 +0000 (10:59 -0800)]
net speed benchmark: set device 0
Yangqing Jia [Tue, 26 Nov 2013 17:49:29 +0000 (09:49 -0800)]
removed the -Wl flag which was an earlier experimental try
Yangqing Jia [Tue, 26 Nov 2013 17:47:26 +0000 (09:47 -0800)]
makefile update
Yangqing Jia [Mon, 25 Nov 2013 06:13:38 +0000 (22:13 -0800)]
Merge branch 'master' of github.com:Yangqing/caffe
Yangqing Jia [Mon, 25 Nov 2013 06:13:34 +0000 (22:13 -0800)]
makefile: add both lib and lib64 to the cuda library path.
Yangqing Jia [Sat, 23 Nov 2013 17:37:27 +0000 (09:37 -0800)]
makefile: added a MATLAB_DIR variable. pycaffe and matcaffe will not be compiled in default unless one calls make pycaffe or make matcaffe explicitly.
Ross Girshick [Fri, 22 Nov 2013 22:16:58 +0000 (14:16 -0800)]
update Makefile and add some more docs
Ross Girshick [Fri, 22 Nov 2013 22:03:55 +0000 (14:03 -0800)]
Merge remote-tracking branch 'origin/master'
Ross Girshick [Fri, 22 Nov 2013 22:03:36 +0000 (14:03 -0800)]
cleanup and include ILSVRC mean image
Ross Girshick [Fri, 22 Nov 2013 21:16:23 +0000 (13:16 -0800)]
first pass at matlab wrapper (somewhat messy still)
Yangqing Jia [Fri, 22 Nov 2013 01:00:57 +0000 (17:00 -0800)]
fix Makefile problem
Ross Girshick [Thu, 21 Nov 2013 23:45:04 +0000 (15:45 -0800)]
fixed minor typo in imagenet wrapper
Yangqing Jia [Thu, 21 Nov 2013 21:31:18 +0000 (13:31 -0800)]
cleaned makefile a little bit
Yangqing Jia [Thu, 21 Nov 2013 19:19:12 +0000 (11:19 -0800)]
Merge branch 'master' of github.com:Yangqing/caffe
Yangqing Jia [Thu, 21 Nov 2013 19:16:08 +0000 (11:16 -0800)]
remove remaining distributed solver stuff
Yangqing Jia [Thu, 21 Nov 2013 19:16:08 +0000 (11:16 -0800)]
remove caffe header for distributed solver
Yangqing Jia [Thu, 21 Nov 2013 19:11:46 +0000 (11:11 -0800)]
removed the unsuccessful distributed solver code
Yangqing Jia [Tue, 19 Nov 2013 23:05:39 +0000 (15:05 -0800)]
fix pycaffe dependency
Yangqing Jia [Tue, 19 Nov 2013 22:37:19 +0000 (14:37 -0800)]
fixed the missing CV flag
Yangqing Jia [Tue, 19 Nov 2013 22:31:42 +0000 (14:31 -0800)]
makefile: not compile test in default
Yangqing Jia [Tue, 19 Nov 2013 22:03:56 +0000 (14:03 -0800)]
Merge branch 'master' of github.com:Yangqing/caffe
Yangqing Jia [Tue, 19 Nov 2013 21:39:20 +0000 (13:39 -0800)]
makefile: fixed the nvcc path
Yangqing Jia [Tue, 19 Nov 2013 21:37:28 +0000 (13:37 -0800)]
io.cpp: changed the imread flag to cv::IMREAD_COLOR
Yangqing Jia [Tue, 19 Nov 2013 19:06:12 +0000 (11:06 -0800)]
Merge branch 'master' of github.com:Yangqing/caffe
Yangqing Jia [Tue, 19 Nov 2013 17:08:31 +0000 (09:08 -0800)]
added explanation notes to syncedmem
Yangqing Jia [Tue, 19 Nov 2013 16:51:43 +0000 (08:51 -0800)]
imagenet_solver.prototxt: added back the missing test line, not sure when it slipped off the repo
Yangqing Jia [Tue, 19 Nov 2013 00:06:37 +0000 (16:06 -0800)]
Merge branch 'master' of github.com:Yangqing/caffe
Yangqing Jia [Tue, 19 Nov 2013 00:06:33 +0000 (16:06 -0800)]
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.
Jeff Donahue [Sun, 17 Nov 2013 22:39:42 +0000 (14:39 -0800)]
print status message on error opening leveldb
Jeff Donahue [Sun, 17 Nov 2013 21:45:22 +0000 (13:45 -0800)]
Merge branch 'master', remote-tracking branch 'origin'
Yangqing Jia [Sun, 17 Nov 2013 02:41:28 +0000 (18:41 -0800)]
removed the StillFresh function that was used to make sure training does not happen with an earlier version of code.
Yangqing Jia [Sat, 16 Nov 2013 00:58:53 +0000 (16:58 -0800)]
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.
Yangqing Jia [Fri, 15 Nov 2013 16:02:48 +0000 (08:02 -0800)]
wrapper update
Yangqing Jia [Fri, 15 Nov 2013 05:12:23 +0000 (21:12 -0800)]
finetune code
Yangqing Jia [Thu, 14 Nov 2013 22:51:27 +0000 (14:51 -0800)]
pycaffe: added a temporary numpy 1.6 compile solution
Yangqing Jia [Thu, 14 Nov 2013 22:33:24 +0000 (14:33 -0800)]
misc update
Yangqing Jia [Thu, 14 Nov 2013 00:31:40 +0000 (16:31 -0800)]
pycaffe update and imagenet wrapper
Yangqing Jia [Wed, 13 Nov 2013 19:29:26 +0000 (11:29 -0800)]
pycaffe update
Yangqing Jia [Tue, 12 Nov 2013 22:31:09 +0000 (14:31 -0800)]
linecount improvement
Yangqing Jia [Tue, 12 Nov 2013 22:21:24 +0000 (14:21 -0800)]
ilsvrc 2012 mean
Yangqing Jia [Tue, 12 Nov 2013 22:16:34 +0000 (14:16 -0800)]
removed obsolete scripts
Yangqing Jia [Tue, 12 Nov 2013 22:15:33 +0000 (14:15 -0800)]
python reorganization
Yangqing Jia [Tue, 12 Nov 2013 22:14:02 +0000 (14:14 -0800)]
changed makefile, and removed the no longer needed cuda convnet translator.
Yangqing Jia [Tue, 12 Nov 2013 22:05:28 +0000 (14:05 -0800)]
changed the python file paths
Yangqing Jia [Tue, 12 Nov 2013 21:49:37 +0000 (13:49 -0800)]
added pycaffe wrapper. Preparing to clean the structure
Yangqing Jia [Tue, 12 Nov 2013 01:08:27 +0000 (17:08 -0800)]
Merge branch 'master' of github.com:Yangqing/caffe
Conflicts:
Makefile
Yangqing Jia [Tue, 12 Nov 2013 01:07:32 +0000 (17:07 -0800)]
remove python deps
Yangqing Jia [Tue, 12 Nov 2013 01:03:27 +0000 (17:03 -0800)]
stochastic pooling: avoid nan
Yangqing Jia [Tue, 12 Nov 2013 01:02:38 +0000 (17:02 -0800)]
io.hpp bugfix
Yangqing Jia [Mon, 11 Nov 2013 19:40:31 +0000 (11:40 -0800)]
added infogain loss layer
Yangqing Jia [Mon, 11 Nov 2013 19:10:39 +0000 (11:10 -0800)]
bugfix
Yangqing Jia [Fri, 8 Nov 2013 21:50:12 +0000 (13:50 -0800)]
misc update
Yangqing Jia [Thu, 7 Nov 2013 19:29:22 +0000 (11:29 -0800)]
Merge branch 'master' of github.com:Yangqing/caffeine
Yangqing Jia [Thu, 7 Nov 2013 19:29:18 +0000 (11:29 -0800)]
ilsvrc 2012 train file list
Yangqing Jia [Thu, 7 Nov 2013 19:06:20 +0000 (11:06 -0800)]
distributed solver still having bugs. Pausing for now...
Yangqing Jia [Thu, 7 Nov 2013 00:38:34 +0000 (16:38 -0800)]
distributed solver: small fix, still bugs
Yangqing Jia [Wed, 6 Nov 2013 23:27:26 +0000 (15:27 -0800)]
distributed server update. bug in synchronous connections.
Yangqing Jia [Wed, 6 Nov 2013 22:02:33 +0000 (14:02 -0800)]
data layer: random skip
Yangqing Jia [Wed, 6 Nov 2013 19:28:17 +0000 (11:28 -0800)]
working asynchronous sgd code. may have errors.
Yangqing Jia [Mon, 4 Nov 2013 19:14:36 +0000 (11:14 -0800)]
distributed solver - not checked thoroughly
Yangqing Jia [Mon, 4 Nov 2013 19:13:19 +0000 (11:13 -0800)]
solver minor change
Yangqing Jia [Fri, 1 Nov 2013 17:23:07 +0000 (10:23 -0700)]
accuracy layer: also produce logprob
Yangqing Jia [Fri, 1 Nov 2013 00:02:22 +0000 (17:02 -0700)]
imagenet solver 2nd try
Yangqing Jia [Thu, 31 Oct 2013 23:59:44 +0000 (16:59 -0700)]
imagenet test prototxt
Yangqing Jia [Thu, 31 Oct 2013 23:52:22 +0000 (16:52 -0700)]
solver restructuring: now all prototxt are specified in the solver protocol buffer
Yangqing Jia [Thu, 31 Oct 2013 19:18:35 +0000 (12:18 -0700)]
stochastic pooling test
Yangqing Jia [Thu, 31 Oct 2013 18:10:54 +0000 (11:10 -0700)]
test convolution more thoroughly
Yangqing Jia [Wed, 30 Oct 2013 23:52:34 +0000 (16:52 -0700)]
script to convert cifar data
Yangqing Jia [Wed, 30 Oct 2013 23:47:58 +0000 (16:47 -0700)]
script to get cifar
Yangqing Jia [Wed, 30 Oct 2013 22:55:10 +0000 (15:55 -0700)]
test net scripts
Yangqing Jia [Wed, 30 Oct 2013 22:54:36 +0000 (15:54 -0700)]
data_layer: more clear logging
Yangqing Jia [Wed, 30 Oct 2013 22:41:57 +0000 (15:41 -0700)]
syncedmem: added code to not use cudamalloc/cudafree
Yangqing Jia [Wed, 30 Oct 2013 21:30:54 +0000 (14:30 -0700)]
data_layer: do center cropping when testing
Yangqing Jia [Wed, 30 Oct 2013 21:30:27 +0000 (14:30 -0700)]
common.cpp: rand seed fix
Yangqing Jia [Wed, 30 Oct 2013 18:20:51 +0000 (11:20 -0700)]
Merge branch 'master' of github.com:Yangqing/caffeine
Yangqing Jia [Wed, 30 Oct 2013 18:20:46 +0000 (11:20 -0700)]
pooling layer: added stochastic pooling layer, not tested, compilable
Yangqing Jia [Wed, 30 Oct 2013 18:20:15 +0000 (11:20 -0700)]
convert_imageset.cpp script: added error message
Yangqing Jia [Mon, 28 Oct 2013 23:18:07 +0000 (16:18 -0700)]
caffe common cpp: fixed an embarassing bug
Yangqing Jia [Mon, 28 Oct 2013 21:28:55 +0000 (14:28 -0700)]
removed an accidental mnist update