Sergio Guadarrama [Thu, 11 Sep 2014 22:19:57 +0000 (15:19 -0700)]
Fixed MemoryDataLayer to make it work with pycaffe
Sergio Guadarrama [Sat, 20 Sep 2014 00:10:59 +0000 (17:10 -0700)]
Move data_mean into data_transformer remove datum_* from BaseData
Conflicts:
src/caffe/layers/memory_data_layer.cpp
Jeff Donahue [Fri, 3 Oct 2014 01:26:44 +0000 (18:26 -0700)]
Merge pull request #1204 from jeffdonahue/exp-layer
EXP neuron layer
Jeff Donahue [Fri, 3 Oct 2014 00:11:38 +0000 (17:11 -0700)]
save/restore shared weights unit test
Jeff Donahue [Thu, 2 Oct 2014 23:20:04 +0000 (16:20 -0700)]
[fix] comment typo
Jeff Donahue [Thu, 2 Oct 2014 06:12:06 +0000 (23:12 -0700)]
Add ExpLayer to calculate y = base ^ (scale * x + shift)
Jeff Donahue [Thu, 2 Oct 2014 06:11:41 +0000 (23:11 -0700)]
Add caffe_gpu_exp math function
Yangqing Jia [Thu, 2 Oct 2014 20:01:17 +0000 (13:01 -0700)]
Merge pull request #1208 from Yangqing/dev
add factory header to caffe hpp
Evan Shelhamer [Thu, 2 Oct 2014 19:50:46 +0000 (12:50 -0700)]
Merge pull request #1196 from longjon/python-solver-improvements
Python solver improvements
Yangqing Jia [Thu, 2 Oct 2014 19:11:45 +0000 (12:11 -0700)]
add factory header to caffe hpp
Jonathan L Long [Thu, 2 Oct 2014 18:53:55 +0000 (11:53 -0700)]
Back-merge to include #1198
Jonathan L Long [Thu, 2 Oct 2014 18:52:48 +0000 (11:52 -0700)]
Merge pull request #1198 from dbbert/patch-1
Bert [Wed, 1 Oct 2014 13:29:24 +0000 (15:29 +0200)]
Update detect.py
This generator causes an error in detect_windows because it is run twice there.
Better store it as a data structure instead.
Jeff Donahue [Thu, 2 Oct 2014 18:19:05 +0000 (11:19 -0700)]
[fix] lint causing travis failures
Evan Shelhamer [Thu, 2 Oct 2014 07:12:31 +0000 (00:12 -0700)]
Merge pull request #951 from gcinbis/patch-1
Lock the mex file to avoid MATLAB crashes
Jeff Donahue [Thu, 2 Oct 2014 03:53:31 +0000 (20:53 -0700)]
caffe.proto: do some minor cleanup (fix comments, alphabetization)
Jeff Donahue [Wed, 1 Oct 2014 21:47:16 +0000 (14:47 -0700)]
Back-merge branch 'master' into dev (for fix in PR #1203)
Jeff Donahue [Wed, 1 Oct 2014 21:46:18 +0000 (14:46 -0700)]
Merge pull request #1203 from jeffdonahue/fix-output-blob-indexing
[fix] solver indexing of output blobs was incorrect for non-singleton outputs
Jeff Donahue [Wed, 1 Oct 2014 21:19:30 +0000 (14:19 -0700)]
[fix] solver indexing of output blobs was incorrect for non-singleton
outputs
Jeff Donahue [Wed, 1 Oct 2014 07:50:55 +0000 (00:50 -0700)]
Merge pull request #1096 from qipeng/smoothed-cost
Display averaged loss over the last several iterations
Jonathan L Long [Wed, 1 Oct 2014 03:26:25 +0000 (20:26 -0700)]
[pycaffe] expose SGDSolver.iter
Jonathan L Long [Wed, 1 Oct 2014 03:24:47 +0000 (20:24 -0700)]
add accessor for Solver::iter_
This will be useful in code controlling the solver (from pycaffe, for
example).
Jonathan L Long [Tue, 30 Sep 2014 23:21:18 +0000 (16:21 -0700)]
[pycaffe] expose SGDSolver.test_nets
Jonathan L Long [Tue, 30 Sep 2014 23:20:27 +0000 (16:20 -0700)]
[pycaffe] add converter for vectors of Nets
Jonathan L Long [Wed, 1 Oct 2014 02:16:56 +0000 (19:16 -0700)]
[pycaffe] fix comment typo
Evan Shelhamer [Wed, 1 Oct 2014 00:24:26 +0000 (17:24 -0700)]
[fix] check and load weight for backward w.r.t. data
fix NULL pointer when back-propagating to the data for fixed i.e. not
back-propagated weights. same issue as #1048
Yangqing Jia [Tue, 30 Sep 2014 22:57:38 +0000 (15:57 -0700)]
remove a wrong space in common.hpp
Jonathan L Long [Tue, 30 Sep 2014 22:28:36 +0000 (15:28 -0700)]
fix cuDNN build by readding line deleted in #1167
Jeff Donahue [Tue, 30 Sep 2014 19:52:47 +0000 (12:52 -0700)]
Merge pull request #1191 from jeffdonahue/hdf5data-cleanup
HDF5DataLayer cleanup
Jeff Donahue [Tue, 30 Sep 2014 19:32:34 +0000 (12:32 -0700)]
hdf5_load_nd_dataset_helper: check that dataset exists first
Jeff Donahue [Tue, 30 Sep 2014 19:27:09 +0000 (12:27 -0700)]
HDF5DataLayer: die on failure to open source file
Jeff Donahue [Tue, 30 Sep 2014 18:15:21 +0000 (11:15 -0700)]
Die on failure to load HDF5 data file.
Jeff Donahue [Tue, 30 Sep 2014 18:13:59 +0000 (11:13 -0700)]
Cleanup HDF5DataLayer log messages.
-Only use "DLOG" during Forward/Backward for less noise during
training/testing
-Cleanup spacing, capitalization, etc.
Jeff Donahue [Tue, 30 Sep 2014 18:37:55 +0000 (11:37 -0700)]
hdf5_data_layer.cpp: fix indentation
Jeff Donahue [Tue, 30 Sep 2014 18:06:57 +0000 (11:06 -0700)]
Merge pull request #1183 from pluskid/hdf5layer
Chiyuan Zhang [Fri, 26 Sep 2014 20:20:48 +0000 (16:20 -0400)]
added test case to cover new HDF5 behavior
Chiyuan Zhang [Fri, 26 Sep 2014 15:21:59 +0000 (11:21 -0400)]
make HDF5 layer support multiple data output
Jeff Donahue [Tue, 30 Sep 2014 18:00:37 +0000 (11:00 -0700)]
test_gradient_based_solver.cpp: removed unused typedefs
Yangqing Jia [Tue, 30 Sep 2014 17:35:39 +0000 (10:35 -0700)]
Merge pull request #1167 from Yangqing/factory
Layer factory.
Yangqing Jia [Tue, 30 Sep 2014 17:20:36 +0000 (10:20 -0700)]
doxygen
longjon [Tue, 30 Sep 2014 04:40:23 +0000 (21:40 -0700)]
Merge pull request #1187 from longjon/fix-cudnn-pooling-tests
Fix cuDNN pooling tests
Jonathan L Long [Tue, 30 Sep 2014 04:21:03 +0000 (21:21 -0700)]
cuDNN pooling layer tests know that nonzero padding is not supported
After #1172, some cuDNN pooling layer tests were failing due to use of
padding. (Before #1172, these tests were actually testing PoolingLayer
instead of CuDNNPoolingLayer via the fallback.) This commit disables
many tests via commenting, so that they can be easily readded when cuDNN
gains pooling padding support.
Jonathan L Long [Tue, 30 Sep 2014 04:20:37 +0000 (21:20 -0700)]
use method overrides for CuDNNPoolingLayer top blob checking
longjon [Tue, 30 Sep 2014 03:35:02 +0000 (20:35 -0700)]
Merge pull request #1186 from ashafaei/error-fixes
Fixed some errors in layer_factory and cudnn_pooling
Alireza Shafaei [Tue, 30 Sep 2014 03:24:00 +0000 (20:24 -0700)]
Fixed some errors in layer_factory and cudnn_pooling
Jeff Donahue [Mon, 29 Sep 2014 21:16:58 +0000 (14:16 -0700)]
Merge remote-tracking branch 'bvlc/master' into dev
Conflicts:
src/caffe/layers/hdf5_data_layer.cpp
Jeff Donahue [Mon, 29 Sep 2014 21:14:50 +0000 (14:14 -0700)]
Merge pull request #1166 from pluskid/master
bugfix: HDF5 layer reshape bug
Sergey Karayev [Mon, 29 Sep 2014 09:55:22 +0000 (02:55 -0700)]
[examples] adding class names and deploy version of Flickr Style net
Yangqing Jia [Mon, 29 Sep 2014 02:16:01 +0000 (19:16 -0700)]
static initialization order fiasco
Yangqing Jia [Mon, 29 Sep 2014 01:11:35 +0000 (18:11 -0700)]
add explicit declaration - does that help the flakyness?
Yangqing Jia [Sun, 28 Sep 2014 23:04:53 +0000 (16:04 -0700)]
add long-ignored threshold layer
Yangqing Jia [Sun, 28 Sep 2014 22:46:03 +0000 (15:46 -0700)]
consolidate duplicate code
Yangqing Jia [Sun, 28 Sep 2014 07:11:05 +0000 (00:11 -0700)]
cmake.
Yangqing Jia [Sat, 27 Sep 2014 20:18:27 +0000 (13:18 -0700)]
Mute factory registration message
Yangqing Jia [Sat, 27 Sep 2014 20:17:33 +0000 (13:17 -0700)]
Add back static library. Using -Wl,--whole-archive will allow us to preserve all symbols.
Yangqing Jia [Sat, 27 Sep 2014 19:06:10 +0000 (12:06 -0700)]
Pre-lunch fun: add a dynamic library guard test.
Yangqing Jia [Fri, 26 Sep 2014 23:17:04 +0000 (16:17 -0700)]
more docs
Yangqing Jia [Fri, 26 Sep 2014 20:58:45 +0000 (13:58 -0700)]
running factory.
Yangqing Jia [Mon, 29 Sep 2014 00:40:45 +0000 (17:40 -0700)]
Merge pull request #1172 from Yangqing/conv_factory
Pooling factory
Yangqing Jia [Sun, 28 Sep 2014 22:33:52 +0000 (15:33 -0700)]
message
Yangqing Jia [Sun, 28 Sep 2014 15:16:52 +0000 (08:16 -0700)]
Merge pull request #1161 from jjkjkj/dev-threshold-fix
Fix Threshold layer
Yangqing Jia [Sun, 28 Sep 2014 03:22:10 +0000 (20:22 -0700)]
const fix
Yangqing Jia [Sun, 28 Sep 2014 03:10:13 +0000 (20:10 -0700)]
cudnn pooling fallback option
Chiyuan Zhang [Fri, 26 Sep 2014 19:21:57 +0000 (15:21 -0400)]
fix hdf5 data layer bug
Chiyuan Zhang [Fri, 26 Sep 2014 19:21:45 +0000 (15:21 -0400)]
update HDF5 layer test data.
Chiyuan Zhang [Fri, 26 Sep 2014 17:18:38 +0000 (13:18 -0400)]
tweak test case to expose bug.
jjkjkj [Fri, 26 Sep 2014 09:39:49 +0000 (12:39 +0300)]
Update layer_factory.cpp
longjon [Thu, 25 Sep 2014 17:35:32 +0000 (10:35 -0700)]
Merge pull request #1149 from ashafaei/crop_bugfix
Fixed the bug with random offset selection
longjon [Thu, 25 Sep 2014 17:22:23 +0000 (10:22 -0700)]
Merge pull request #1157 from ducha-aiki/fix-extract-features
Small fix in extract_features
Alireza Shafaei [Wed, 24 Sep 2014 05:35:00 +0000 (22:35 -0700)]
Random crop bugfix and abstracting random number generation inside data_transformer
D.Mishkin [Thu, 25 Sep 2014 14:30:48 +0000 (17:30 +0300)]
Removed unnecessary "mutable"
Evan Shelhamer [Thu, 25 Sep 2014 03:29:23 +0000 (20:29 -0700)]
Merge pull request #1147 from savy-91/patch-1
Changed "blas" to "openblas"
Evan Shelhamer [Thu, 25 Sep 2014 03:19:39 +0000 (20:19 -0700)]
Merge pull request #1138 from ksimonyan/vgg_models_support
VGG models support
Evan Shelhamer [Wed, 24 Sep 2014 21:48:04 +0000 (14:48 -0700)]
Back-merge
Fixed param order of cv::Size in cv::resize
switch examples to lmdb (except for custom data loaders)
fix cifar10 paths so they can be run from caffe root
default backend to lmdb for image conversion and mean computation
Evan Shelhamer [Wed, 24 Sep 2014 21:43:35 +0000 (14:43 -0700)]
Merge pull request #1152 from sguada/fix_cv_size_order
Fix param order of cv::Size in cv::resize
Sergio [Wed, 24 Sep 2014 21:27:57 +0000 (14:27 -0700)]
Fixed param order of cv::Size in cv::resize
Karen Simonyan [Wed, 24 Sep 2014 21:08:46 +0000 (22:08 +0100)]
added a Matlab demo with mean BGR pixel subtraction instead of the mean image subtraction
savy-91 [Tue, 23 Sep 2014 19:57:16 +0000 (21:57 +0200)]
Changed "blas" to "openblas"
The change was made because openblas has to be linked as "-lopenblas" and not "-lblas". This caused an error when compiling.
Karen Simonyan [Tue, 23 Sep 2014 15:39:08 +0000 (16:39 +0100)]
RGB -> BGR in the matlab demo
Karen Simonyan [Mon, 22 Sep 2014 19:39:37 +0000 (20:39 +0100)]
added example usage to the Matlab script
Karen Simonyan [Mon, 22 Sep 2014 19:09:35 +0000 (20:09 +0100)]
added comments to the Matlab demo script
Karen Simonyan [Sun, 21 Sep 2014 16:59:25 +0000 (17:59 +0100)]
added matcaffe_demo for the VGG models (RGB input)
Karen Simonyan [Sun, 21 Sep 2014 16:58:41 +0000 (17:58 +0100)]
added support for "k" LRN parameter to upgrade_proto
Karen Simonyan [Thu, 18 Sep 2014 00:08:56 +0000 (01:08 +0100)]
adds a parameter to the LRN layer (denoted as "k" in [Krizhevsky et al., NIPS 2012])
Sergey Karayev [Mon, 22 Sep 2014 05:53:30 +0000 (22:53 -0700)]
web demo fix, closes #1002
Evan Shelhamer [Mon, 22 Sep 2014 05:08:08 +0000 (22:08 -0700)]
Merge pull request #1128 from shelhamer/default-db-lmdb
default to lmdb for database storage
Evan Shelhamer [Sun, 21 Sep 2014 22:32:03 +0000 (15:32 -0700)]
switch examples to lmdb (except for custom data loaders)
Jeff Donahue [Fri, 19 Sep 2014 19:38:39 +0000 (12:38 -0700)]
fix cifar10 paths so they can be run from caffe root
Evan Shelhamer [Sun, 21 Sep 2014 22:20:47 +0000 (15:20 -0700)]
default backend to lmdb for image conversion and mean computation
lmdb is 10-15% faster than leveldb although it takes ~1.1x the storage.
This is usually irrelevant in prefetching since both are fast enough,
but more important lmdb allows multiple, concurrent reads for training
and evaluation several models on the same data.
Evan Shelhamer [Sun, 21 Sep 2014 21:21:16 +0000 (14:21 -0700)]
Back-merge
define up-to-date all-in-one model for pascal finetuning
load transform params in window data layer
include WindowDataLayer in data param upgrade
Fix typo in LRN-expression in docs
Sergio Guadarrama [Sun, 21 Sep 2014 20:21:22 +0000 (13:21 -0700)]
Merge pull request #1126 from shelhamer/window-data-param-upgrade
[fix] include WindowDataLayer in data param upgrade
Evan Shelhamer [Sun, 21 Sep 2014 18:38:20 +0000 (11:38 -0700)]
define up-to-date all-in-one model for pascal finetuning
Evan Shelhamer [Sun, 21 Sep 2014 17:29:39 +0000 (10:29 -0700)]
load transform params in window data layer
Evan Shelhamer [Sun, 21 Sep 2014 16:52:51 +0000 (09:52 -0700)]
include WindowDataLayer in data param upgrade
Jeff Donahue [Sat, 20 Sep 2014 15:39:14 +0000 (08:39 -0700)]
Merge pull request #1115 from rickardnorlander/master
Fix typo in LRN-expression in docs
longjon [Sat, 20 Sep 2014 06:51:25 +0000 (23:51 -0700)]
Merge pull request #1118 from shelhamer/1x1-conv
Optimize 1x1 convolution for Network-in-Network style operation
Evan Shelhamer [Sat, 20 Sep 2014 06:12:12 +0000 (23:12 -0700)]
combine col_{data,diff} into single col_buff to halve memory usage
conv forward / backward only need one of the im2col data and diff
at-a-time so consolidating the two saves a lazy allocation.
Evan Shelhamer [Sat, 20 Sep 2014 05:31:52 +0000 (22:31 -0700)]
Back-merge
Evan Shelhamer [Sat, 20 Sep 2014 01:59:38 +0000 (18:59 -0700)]
optimize 1x1 convolution for Network-in-Network style layers
1x1 convolution with stride 1 is a special case of Caffe matrix
multiplication convolution for which im2col / col2im transformations are
actually the identity. For this special case the memory and
transformation are skipped.
Evan Shelhamer [Sat, 20 Sep 2014 04:32:16 +0000 (21:32 -0700)]
drop out-of-date conv test comments