platform/upstream/caffe.git
8 years agoMerge pull request #3090 from longjon/summarize-tool
Yangqing Jia [Wed, 9 Dec 2015 01:38:00 +0000 (17:38 -0800)]
Merge pull request #3090 from longjon/summarize-tool

A Python script for at-a-glance net summary

8 years agoMerge pull request #3395 from BonsaiAI/extract_features-compatibility
Jon Long [Fri, 4 Dec 2015 21:11:30 +0000 (13:11 -0800)]
Merge pull request #3395 from BonsaiAI/extract_features-compatibility

Fix compatibility issues with extract_features

8 years agoCorrect type of device_id; disambiguate shared_ptr
T.E.A de Souza [Sun, 29 Nov 2015 06:24:09 +0000 (14:24 +0800)]
Correct type of device_id; disambiguate shared_ptr

8 years agoMerge pull request #3404 from BonsaiAI/remove-hamming-dist
Jon Long [Wed, 2 Dec 2015 08:11:26 +0000 (00:11 -0800)]
Merge pull request #3404 from BonsaiAI/remove-hamming-dist

Remove hamming_distance and popcount

8 years agoRemove hamming_distance and popcount
Tea [Wed, 2 Dec 2015 07:39:19 +0000 (15:39 +0800)]
Remove hamming_distance and popcount

8 years agoMerge pull request #3313 from gdh1995/master
Evan Shelhamer [Wed, 2 Dec 2015 06:17:36 +0000 (22:17 -0800)]
Merge pull request #3313 from gdh1995/master

don't divide by 0 duration when downloading model binary

8 years agoMerge pull request #3267 from cbalint13/cmake-cudnn
Evan Shelhamer [Wed, 2 Dec 2015 06:05:37 +0000 (22:05 -0800)]
Merge pull request #3267 from cbalint13/cmake-cudnn

[build] Display and store cuDNN version numbers for CMake

8 years agoMerge pull request #3285 from longjon/cuda-dead-cpp
Evan Shelhamer [Wed, 2 Dec 2015 06:04:34 +0000 (22:04 -0800)]
Merge pull request #3285 from longjon/cuda-dead-cpp

Remove dead preprocessor code for number of CUDA threads

8 years agoMerge pull request #3315 from shelhamer/layer-headers
Evan Shelhamer [Wed, 2 Dec 2015 05:30:35 +0000 (21:30 -0800)]
Merge pull request #3315 from shelhamer/layer-headers

Dismantle Layer Headers

8 years agodismantle layer headers
Evan Shelhamer [Tue, 10 Nov 2015 08:22:58 +0000 (00:22 -0800)]
dismantle layer headers

No more monolithic includes: split layers into their own headers for modular inclusion and build.

8 years agoMerge pull request #3378 from BonsaiAI/fix-temp-dir-creation-failure
Ronghang Hu [Sat, 28 Nov 2015 04:53:46 +0000 (20:53 -0800)]
Merge pull request #3378 from BonsaiAI/fix-temp-dir-creation-failure

Safely create temporary files and directories

8 years agoSecure temporary file creation
Tea [Wed, 25 Nov 2015 03:43:45 +0000 (11:43 +0800)]
Secure temporary file creation

8 years agoSecure implementation of MakeTempDir
T.E.A de Souza [Tue, 24 Nov 2015 06:33:27 +0000 (14:33 +0800)]
Secure implementation of MakeTempDir

8 years agoMerge pull request #3320 from BonsaiAI/disambiguate-dtype
Ronghang Hu [Fri, 27 Nov 2015 19:29:15 +0000 (11:29 -0800)]
Merge pull request #3320 from BonsaiAI/disambiguate-dtype

Cast std::max args to Dtype

8 years agoMerge pull request #2693 from AdamStelmaszczyk/patch-1
Ronghang Hu [Fri, 27 Nov 2015 19:25:52 +0000 (11:25 -0800)]
Merge pull request #2693 from AdamStelmaszczyk/patch-1

Deprecated OpenCV consts leading to compilation error

8 years agoMerge pull request #3361 from BonsaiAI/avoid-snprintf
Ronghang Hu [Fri, 27 Nov 2015 18:50:52 +0000 (10:50 -0800)]
Merge pull request #3361 from BonsaiAI/avoid-snprintf

replace snprintf with a C++98 equivalent

8 years agoMerge pull request #3352 from lukeyeager/bvlc/pytest-python-layer
Ronghang Hu [Thu, 26 Nov 2015 18:45:19 +0000 (10:45 -0800)]
Merge pull request #3352 from lukeyeager/bvlc/pytest-python-layer

Skip python layer tests if WITH_PYTHON_LAYER unset

8 years agoMerge pull request #3389 from ronghanghu/remove-stepearly
Ronghang Hu [Thu, 26 Nov 2015 18:34:09 +0000 (10:34 -0800)]
Merge pull request #3389 from ronghanghu/remove-stepearly

Remove bogus stepearly in MNIST example

8 years agoRemove bogus stepearly in MNIST example
Ronghang Hu [Thu, 26 Nov 2015 05:02:02 +0000 (21:02 -0800)]
Remove bogus stepearly in MNIST example

This `examples/lenet/lenet_stepearly_solver.prototxt` is introduced in #190 by mistake, since stepearly is never actually merged.

8 years agoreplace snprintf with a C++98 equivalent
Tea [Tue, 17 Nov 2015 09:05:56 +0000 (17:05 +0800)]
replace snprintf with a C++98 equivalent

8 years agoMerge pull request #3296 from cdoersch/normalize_batch
Jeff Donahue [Mon, 23 Nov 2015 03:33:36 +0000 (19:33 -0800)]
Merge pull request #3296 from cdoersch/normalize_batch

Better normalization options for SoftmaxWithLoss layer

8 years agoBetter normalization options for SoftmaxWithLoss layer.
Carl Doersch [Fri, 6 Nov 2015 22:41:30 +0000 (14:41 -0800)]
Better normalization options for SoftmaxWithLoss layer.

8 years agoMerge pull request #3363 from BonsaiAI/remove-opencv-include
Ronghang Hu [Fri, 20 Nov 2015 11:08:03 +0000 (03:08 -0800)]
Merge pull request #3363 from BonsaiAI/remove-opencv-include

Exclude core.hpp when building without OpenCV

8 years agoMerge pull request #3362 from eelstork/patch-2
Ronghang Hu [Fri, 20 Nov 2015 10:51:31 +0000 (02:51 -0800)]
Merge pull request #3362 from eelstork/patch-2

GetDB must return a value.

8 years agoExclude core.hpp when building without OpenCV
T.E.A de Souza [Fri, 20 Nov 2015 08:52:25 +0000 (16:52 +0800)]
Exclude core.hpp when building without OpenCV

8 years agoFunction must return a value
T.E.A de Souza [Fri, 20 Nov 2015 08:36:29 +0000 (16:36 +0800)]
Function must return a value

Currently compilation will fail with some compilers when LevelDB and LMDB are disabled.
Very similar to a recently fixed issue.

8 years agoConvert std::max args to Dtype
Tea [Thu, 12 Nov 2015 07:15:22 +0000 (15:15 +0800)]
Convert std::max args to Dtype

8 years agoMerge pull request #3359 from ronghanghu/fix-accuracy-layer-top
Evan Shelhamer [Thu, 19 Nov 2015 20:07:32 +0000 (12:07 -0800)]
Merge pull request #3359 from ronghanghu/fix-accuracy-layer-top

Fix MaxTopBlobs in Accuracy Layer

8 years agoFix MaxTopBlobs in Accuracy Layer
Ronghang Hu [Thu, 19 Nov 2015 18:05:48 +0000 (10:05 -0800)]
Fix MaxTopBlobs in Accuracy Layer

Fix the typo "MaxTopBlos" to "MaxTopBlobs". This typo causes maximum top number to be incorrect.

8 years agoSkip python layer tests if WITH_PYTHON_LAYER unset
Luke Yeager [Wed, 18 Nov 2015 18:38:32 +0000 (10:38 -0800)]
Skip python layer tests if WITH_PYTHON_LAYER unset

8 years agoMerge pull request #3321 from BonsaiAI/synced-mem-functions-will-return-a-value
Evan Shelhamer [Mon, 16 Nov 2015 07:19:58 +0000 (23:19 -0800)]
Merge pull request #3321 from BonsaiAI/synced-mem-functions-will-return-a-value

In syncedmem.cpp, functions shall return a value

8 years agoMerge pull request #3261 from kli-nlpr/patch-1
Evan Shelhamer [Mon, 16 Nov 2015 07:00:44 +0000 (23:00 -0800)]
Merge pull request #3261 from kli-nlpr/patch-1

fix plot_training_log.py.example usage text

8 years agoMerge pull request #3332 from alexlee-gk/master
Evan Shelhamer [Mon, 16 Nov 2015 06:51:51 +0000 (22:51 -0800)]
Merge pull request #3332 from alexlee-gk/master

[bug] fix outs and diffs being overwritten in forward_backward_all

8 years agoFix outs and diffs being overwritten in forward_backward_all.
Alex Lee [Sat, 14 Nov 2015 20:49:05 +0000 (12:49 -0800)]
Fix outs and diffs being overwritten in forward_backward_all.

8 years agoMerge pull request #3299 from kkhoot/fix_bn
Evan Shelhamer [Sat, 14 Nov 2015 19:53:26 +0000 (11:53 -0800)]
Merge pull request #3299 from kkhoot/fix_bn

Update BatchNormLayer: more numerical stability and backward with global stats

8 years agoMerge pull request #3323 from BonsaiAI/remove-unnecessary-includes
Evan Shelhamer [Sat, 14 Nov 2015 19:49:00 +0000 (11:49 -0800)]
Merge pull request #3323 from BonsaiAI/remove-unnecessary-includes

Remove un-necessary includes

8 years agoDisplay and store cuDNN version numbers during cmake.
Balint Cristian [Fri, 13 Nov 2015 11:58:49 +0000 (13:58 +0200)]
Display and store cuDNN version numbers during cmake.

8 years agoMerge pull request #3328 from w1res/patch-1
Evan Shelhamer [Fri, 13 Nov 2015 08:25:12 +0000 (00:25 -0800)]
Merge pull request #3328 from w1res/patch-1

[doc] Add parentheses to backward_{cpu,gpu} method.

8 years agoAdd parentheses to backward_{cpu,gpu} method.
Adam Siembida [Thu, 12 Nov 2015 21:03:41 +0000 (16:03 -0500)]
Add parentheses to backward_{cpu,gpu} method.

8 years agoMake backward pass work when global stats is active for BatchNormLayer
Kang Kim [Thu, 12 Nov 2015 17:20:02 +0000 (02:20 +0900)]
Make backward pass work when global stats is active for BatchNormLayer
including minor code cleaning

8 years agoUpdate computation of variance and global stats in BatchNormLayer
Kang Kim [Sat, 7 Nov 2015 03:49:15 +0000 (12:49 +0900)]
Update computation of variance and global stats in BatchNormLayer

8 years agoFunctions shall return a value in syncedmem
Tea [Thu, 12 Nov 2015 07:55:06 +0000 (15:55 +0800)]
Functions shall return a value in syncedmem

8 years agoRemove un-necessary includes
T.E.A de Souza [Thu, 12 Nov 2015 07:32:28 +0000 (15:32 +0800)]
Remove un-necessary includes

8 years agofix a bug that time duration may be 0 when downloading model binary
gdh1995 [Tue, 10 Nov 2015 14:41:55 +0000 (22:41 +0800)]
fix a bug that time duration may be 0 when downloading model binary

8 years agoMerge pull request #3127 from lukeyeager/install-lib-permissions
Evan Shelhamer [Wed, 11 Nov 2015 06:53:57 +0000 (22:53 -0800)]
Merge pull request #3127 from lukeyeager/install-lib-permissions

[build] Install libs as non-executable files

8 years agoMerge pull request #3235 from shelhamer/dlog-cudnn-workspace
Evan Shelhamer [Wed, 11 Nov 2015 06:51:25 +0000 (22:51 -0800)]
Merge pull request #3235 from shelhamer/dlog-cudnn-workspace

cuDNN: only log conv workspace in debug mode

8 years agoMerge pull request #3290 from ernest-tg/master
Evan Shelhamer [Wed, 11 Nov 2015 06:50:28 +0000 (22:50 -0800)]
Merge pull request #3290 from ernest-tg/master

[pycaffe] correct transposition & channel_swap in deprocess

8 years agoMerge pull request #3294 from panmari/simpler_diff
Evan Shelhamer [Wed, 11 Nov 2015 06:48:23 +0000 (22:48 -0800)]
Merge pull request #3294 from panmari/simpler_diff

[example] switch order of two layers for simpler diff with untuned file

8 years agoMerge pull request #3295 from timmeinhardt/fix_issue_3274
Evan Shelhamer [Wed, 11 Nov 2015 06:47:27 +0000 (22:47 -0800)]
Merge pull request #3295 from timmeinhardt/fix_issue_3274

[bug] fix issue #3274 -- shape argmax top carefully

8 years agoMerge pull request #3310 from gustavla/contrastive-doc-fix
Evan Shelhamer [Wed, 11 Nov 2015 06:44:46 +0000 (22:44 -0800)]
Merge pull request #3310 from gustavla/contrastive-doc-fix

[doc] Fix consistent typo in contrastive loss

8 years agoMerge pull request #3305 from ronghanghu/display-ignore-layer
Ronghang Hu [Tue, 10 Nov 2015 23:08:47 +0000 (15:08 -0800)]
Merge pull request #3305 from ronghanghu/display-ignore-layer

display 'ignore source layer' when initializing from existing parameters

8 years agoMerge pull request #3300 from BonsaiAI/replace-unistd
Ronghang Hu [Tue, 10 Nov 2015 23:08:22 +0000 (15:08 -0800)]
Merge pull request #3300 from BonsaiAI/replace-unistd

Replace unistd functions with cross platform counterparts

8 years agoReplace unistd functions with cross platform counterparts
Tea [Sat, 7 Nov 2015 06:09:59 +0000 (14:09 +0800)]
Replace unistd functions with cross platform counterparts

8 years agoDOC: Fix consistent typo in contrastive loss
Gustav Larsson [Mon, 9 Nov 2015 20:32:37 +0000 (14:32 -0600)]
DOC: Fix consistent typo in contrastive loss

If a pair is similar, it should take the squared distance and not the
distance. This is clearly what the code is doing.

8 years agoMerge pull request #3308 from cassinaj/master
Ronghang Hu [Mon, 9 Nov 2015 18:15:26 +0000 (10:15 -0800)]
Merge pull request #3308 from cassinaj/master

minor typo fix

8 years agoMerge pull request #1 from cassinaj/cassinaj-minor-typo-fix
Jan Issac [Mon, 9 Nov 2015 11:42:56 +0000 (12:42 +0100)]
Merge pull request #1 from cassinaj/cassinaj-minor-typo-fix

minor typo fix

8 years agoSwitched order of two layers for simpler diff with untuned file
panmari [Fri, 6 Nov 2015 11:53:16 +0000 (12:53 +0100)]
Switched order of two layers for simpler diff with untuned file

Untuned file is in models/bvlc_reference_caffenet/train_val.prototxt.

8 years agoMerge pull request #3303 from eelstork/patch-1
Ronghang Hu [Sun, 8 Nov 2015 19:51:24 +0000 (11:51 -0800)]
Merge pull request #3303 from eelstork/patch-1

GetDB must return a value

8 years agodisplay 'ignore source layer' when initializing from existing parameters
Ronghang Hu [Sun, 8 Nov 2015 19:20:32 +0000 (11:20 -0800)]
display 'ignore source layer' when initializing from existing parameters

This helps in the case to see which layer is initialized from existing parameters, and which layer is ignored. This helps identify the cases where the user types a error mismatch layer name.

8 years agoGetDB must return a value
T.E.A de Souza [Sun, 8 Nov 2015 10:50:29 +0000 (18:50 +0800)]
GetDB must return a value

As noted by @danst18, when USE_LEVELDB and USE_LMDB are disabled, a compiler error is issued since GetDB no longer returns a value.
At runtime a fatal error would be issued anyways. However to help users who don't need a DB backend, NULL should be returned here.

8 years agoFix ArgMaxLayer::Reshape for any num of bottom axes
Tim Meinhardt [Fri, 6 Nov 2015 13:51:46 +0000 (14:51 +0100)]
Fix ArgMaxLayer::Reshape for any num of bottom axes

8 years agoCorrect transposition & channel_swap in deprocess
ernest-tg [Thu, 5 Nov 2015 14:47:28 +0000 (15:47 +0100)]
Correct transposition & channel_swap in deprocess

The deprocess( ) function should invert the preprocess( ) function, however it only worked when the permutation of your channel_swap is of order 2 and the permutation of your transpose were of order 3. This is usually the case, which is why this bug went unnoticed for a long time.

To reproduce it (on former version), try to preprocess and then deprocess with
transformer.set_transpose('data', (0,2,1)) (or (1,0,2) or (2,1,0))

Or with
transformer.set_channel_swap('data', (2,0,1)) (or (1,2,0) )

Indeed, we had

L152  (in preprocess)   caffe_in = caffe_in[channel_swap, :, :]
L181  (in deprocess)    decaf_in = decaf_in[channel_swap, :, :]
So we applied [channel_swap,:,:] twice to the initial data => not always the identity

L154 (in preprocess)    caffe_in = caffe_in.transpose(transpose)
L183 (in deprocess)     decaf_in = decaf_in.transpose([transpose[t] for t in transpose])
The transposition [transpose[t] for t in transpose] is (tranpsose)² so we applied transpose[t] three times which is not always the identity.

8 years agoMerge pull request #3287 from longjon/travis-install-whitespace
Jon Long [Thu, 5 Nov 2015 08:27:56 +0000 (00:27 -0800)]
Merge pull request #3287 from longjon/travis-install-whitespace

Fix whitespace in travis_install.sh

8 years agoremove dead cpp code for number of CUDA threads
Jonathan L Long [Thu, 5 Nov 2015 04:48:43 +0000 (20:48 -0800)]
remove dead cpp code for number of CUDA threads

__CUDA_ARCH__ is not defined in host code; the #if was vacuous and
misleading.

8 years ago[style] fix whitespace in travis_install.sh
Jonathan L Long [Thu, 5 Nov 2015 07:54:41 +0000 (23:54 -0800)]
[style] fix whitespace in travis_install.sh

8 years agoMerge pull request #3286 from longjon/fix-py3-travis-boost
Jon Long [Thu, 5 Nov 2015 07:49:15 +0000 (23:49 -0800)]
Merge pull request #3286 from longjon/fix-py3-travis-boost

[travis] fix boost/python3 conda conflict

8 years ago[travis] fix boost/python3 conda conflict
Jonathan L Long [Thu, 5 Nov 2015 06:10:25 +0000 (22:10 -0800)]
[travis] fix boost/python3 conda conflict

8 years agoMerge pull request #3275 from darxriggs/master
Jon Long [Thu, 5 Nov 2015 05:32:16 +0000 (21:32 -0800)]
Merge pull request #3275 from darxriggs/master

fix detect.py (invalid model path)

8 years agoMerge pull request #3276 from lukeyeager/bvlc/fix-travis-cmake-download
Evan Shelhamer [Tue, 3 Nov 2015 22:52:01 +0000 (14:52 -0800)]
Merge pull request #3276 from lukeyeager/bvlc/fix-travis-cmake-download

TravisCI: wget cmake with --no-check-certificate

8 years agoTravisCI: wget cmake with --no-check-certificate
Luke Yeager [Tue, 3 Nov 2015 22:42:24 +0000 (14:42 -0800)]
TravisCI: wget cmake with --no-check-certificate

```
--2015-11-03 22:31:11--  http://www.cmake.org/files/v3.2/cmake-3.2.3-Linux-x86_64.sh
Resolving www.cmake.org (www.cmake.org)... 66.194.253.19
Connecting to www.cmake.org (www.cmake.org)|66.194.253.19|:80... connected.
HTTP request sent, awaiting response... 301 Moved Permanently
Location: http://cmake.org/files/v3.2/cmake-3.2.3-Linux-x86_64.sh [following]
--2015-11-03 22:31:11--  http://cmake.org/files/v3.2/cmake-3.2.3-Linux-x86_64.sh
Resolving cmake.org (cmake.org)... 66.194.253.19
Connecting to cmake.org (cmake.org)|66.194.253.19|:80... connected.
HTTP request sent, awaiting response... 301 Moved Permanently
Location: https://cmake.org/files/v3.2/cmake-3.2.3-Linux-x86_64.sh [following]
--2015-11-03 22:31:11--  https://cmake.org/files/v3.2/cmake-3.2.3-Linux-x86_64.sh
Connecting to cmake.org (cmake.org)|66.194.253.19|:443... connected.
ERROR: no certificate subject alternative name matches
        requested host name `cmake.org'.
To connect to cmake.org insecurely, use `--no-check-certificate'.
```

8 years agofix detect.py (invalid model path)
René Scheibe [Tue, 3 Nov 2015 18:27:07 +0000 (19:27 +0100)]
fix detect.py (invalid model path)

8 years agoMerge pull request #3082 from gustavla/pycaffe-snapshot
Evan Shelhamer [Sat, 31 Oct 2015 06:08:12 +0000 (23:08 -0700)]
Merge pull request #3082 from gustavla/pycaffe-snapshot

Expose `Solver::Snapshot` to pycaffe

8 years agoUpdate plot_training_log.py.example
Kai Li [Thu, 29 Oct 2015 16:46:08 +0000 (00:46 +0800)]
Update plot_training_log.py.example

I find there is no plot_log.sh file

8 years agoMerge pull request #3254 from ronghanghu/cudnn3_accum_grad
Ronghang Hu [Wed, 28 Oct 2015 17:19:33 +0000 (10:19 -0700)]
Merge pull request #3254 from ronghanghu/cudnn3_accum_grad

CuDNNConvolutionLayer accumulate gradients

8 years agoCuDNNConvolutionLayer accumulate gradients
Ronghang Hu [Wed, 28 Oct 2015 05:49:28 +0000 (22:49 -0700)]
CuDNNConvolutionLayer accumulate gradients

8 years agoMerge pull request #3221 from BonsaiAI/cmake-forward-compatibility
Evan Shelhamer [Sun, 25 Oct 2015 00:05:12 +0000 (17:05 -0700)]
Merge pull request #3221 from BonsaiAI/cmake-forward-compatibility

Endorse CMP0046, CMP0054

8 years agocuDNN: only log conv workspace in debug mode
Evan Shelhamer [Fri, 23 Oct 2015 02:12:48 +0000 (19:12 -0700)]
cuDNN: only log conv workspace in debug mode

8 years agoMerge pull request #3229 from cdoersch/batchnorm2
Jeff Donahue [Fri, 23 Oct 2015 01:33:07 +0000 (18:33 -0700)]
Merge pull request #3229 from cdoersch/batchnorm2

Yet another batch normalization PR

8 years agoMerge pull request #3186 from lionleaf/makefile_opencv_imgcodecs
Ronghang Hu [Thu, 22 Oct 2015 22:17:26 +0000 (15:17 -0700)]
Merge pull request #3186 from lionleaf/makefile_opencv_imgcodecs

Add opencv_imgcodecs to library path in Makefile

8 years agoAdd opencv_imgcodecs to library path in Makefile
Andreas Løve Selvik [Tue, 13 Oct 2015 14:32:52 +0000 (16:32 +0200)]
Add opencv_imgcodecs to library path in Makefile

Project does not compile without opencv_imgcodecs in the library path if
you're using OpenCV 3.

This introduces a OPENCV_VERSION flag in Makefile.config that includes
the library if set to 3.  (Trying to include it with OpenCV 2 also
breaks the build)

8 years agoMerge pull request #3234 from rodrigob/patch-1
Ronghang Hu [Thu, 22 Oct 2015 17:11:30 +0000 (10:11 -0700)]
Merge pull request #3234 from rodrigob/patch-1

diff.ndim != 4 is outdated

8 years agodiff.ndim != 4 is outdated
Rodrigo Benenson [Thu, 22 Oct 2015 16:18:08 +0000 (18:18 +0200)]
diff.ndim != 4 is outdated

this code seems not to apply to the caffe head.
```
if diff.ndim != 4:
                raise Exception('{} diff is not 4-d'.format(top))
```

8 years agoCleanup batch norm layer, include global stats computation
Carl Doersch [Tue, 6 Oct 2015 21:19:59 +0000 (14:19 -0700)]
Cleanup batch norm layer, include global stats computation

8 years agoMerge pull request #3226 from kkhoot/clean_header
Ronghang Hu [Thu, 22 Oct 2015 04:22:24 +0000 (21:22 -0700)]
Merge pull request #3226 from kkhoot/clean_header

Clean includes

8 years agoAdded batch normalization layer with test and examples
Dmytro Mishkin [Wed, 25 Feb 2015 15:00:22 +0000 (17:00 +0200)]
Added batch normalization layer with test and examples

8 years agoMerge pull request #3088 from lukeyeager/bvlc/lmdb-nolock
Jon Long [Wed, 21 Oct 2015 02:17:06 +0000 (19:17 -0700)]
Merge pull request #3088 from lukeyeager/bvlc/lmdb-nolock

Open LMDB files with MDB_NOLOCK if no write access

8 years agoClean redundant/unnecessary headers
Kang Kim [Sun, 18 Oct 2015 15:58:55 +0000 (00:58 +0900)]
Clean redundant/unnecessary headers

8 years agoMove HDF5 defines to data_layers header
Kang Kim [Sun, 18 Oct 2015 07:52:19 +0000 (16:52 +0900)]
Move HDF5 defines to data_layers header

8 years agoEndorse CMP0046, CMP0054
T.E.A de Souza [Mon, 19 Oct 2015 10:13:57 +0000 (18:13 +0800)]
Endorse CMP0046, CMP0054

Set policies to NEW to silence warnings in CMake 3.02 and later.

8 years agoMerge pull request #3182 from bchu/tutorial-fix
Evan Shelhamer [Mon, 19 Oct 2015 22:21:32 +0000 (15:21 -0700)]
Merge pull request #3182 from bchu/tutorial-fix

[example] Fix class label index error in tutorial 00.

8 years agoMerge pull request #3185 from mausoomsarkar/master
Ronghang Hu [Mon, 19 Oct 2015 18:48:19 +0000 (11:48 -0700)]
Merge pull request #3185 from mausoomsarkar/master

PReLU speed up

8 years agoMerge pull request #3205 from shelhamer/test-layer-type-upgrade
Evan Shelhamer [Mon, 19 Oct 2015 18:46:14 +0000 (11:46 -0700)]
Merge pull request #3205 from shelhamer/test-layer-type-upgrade

[test] drop bogus OpenCV guard for layer type

8 years ago[test] drop bogus OpenCV guard for layer type
Evan Shelhamer [Sat, 17 Oct 2015 00:13:24 +0000 (17:13 -0700)]
[test] drop bogus OpenCV guard for layer type

8 years agoMerge pull request #3218 from shelhamer/cudnn3-compatible
Evan Shelhamer [Mon, 19 Oct 2015 18:43:59 +0000 (11:43 -0700)]
Merge pull request #3218 from shelhamer/cudnn3-compatible

[docs] mark cuDNN v3 compatible

8 years agoMerge pull request #3219 from shelhamer/install-caffe-users
Evan Shelhamer [Mon, 19 Oct 2015 18:43:36 +0000 (11:43 -0700)]
Merge pull request #3219 from shelhamer/install-caffe-users

[docs] direct installation questions to caffe-users

8 years ago[docs] cuDNN v3 compatible
Evan Shelhamer [Mon, 19 Oct 2015 18:39:29 +0000 (11:39 -0700)]
[docs] cuDNN v3 compatible

8 years agoinstallation questions -> caffe-users
Evan Shelhamer [Mon, 19 Oct 2015 18:36:38 +0000 (11:36 -0700)]
installation questions -> caffe-users

8 years agoMerge pull request #3217 from BonsaiAI/qualify-CUDA-status-message
Evan Shelhamer [Mon, 19 Oct 2015 17:05:14 +0000 (10:05 -0700)]
Merge pull request #3217 from BonsaiAI/qualify-CUDA-status-message

[build] Qualify messages issued by CMake when CUDA is unavailable

8 years agoQualify messages issued by CMake when CUDA is unavailable
T.E.A de Souza [Mon, 19 Oct 2015 10:19:38 +0000 (18:19 +0800)]
Qualify messages issued by CMake when CUDA is unavailable

8 years agoMoved the loop inside PReLUParamBackward to do the reduction inside the kernel
Mausoom Sarkar [Tue, 13 Oct 2015 13:05:32 +0000 (18:35 +0530)]
Moved the loop inside PReLUParamBackward to do the reduction inside the kernel
Now PReLU backward is taking the same time as forward

Code cleanup
Removed unnecessary code
Fixed indent
merge if(channed_shared_)