platform/upstream/caffeonacl.git
9 years agoMerge pull request #1112 from BVLC/next
Evan Shelhamer [Fri, 19 Sep 2014 05:22:02 +0000 (22:22 -0700)]
Merge pull request #1112 from BVLC/next

Next: release candidate

9 years agorelax precision of gradient-based solver tests
Evan Shelhamer [Fri, 19 Sep 2014 05:07:01 +0000 (22:07 -0700)]
relax precision of gradient-based solver tests

9 years ago[example] groom siamese notebook
Evan Shelhamer [Fri, 19 Sep 2014 03:46:49 +0000 (20:46 -0700)]
[example] groom siamese notebook

9 years agoMerge pull request #959 from nickcarlevaris/contrastive_loss
Evan Shelhamer [Fri, 19 Sep 2014 04:37:31 +0000 (21:37 -0700)]
Merge pull request #959 from nickcarlevaris/contrastive_loss

  Add contrastive loss layer, tests, and a siamese network example

9 years ago[docs] order ipython notebooks
Evan Shelhamer [Fri, 19 Sep 2014 04:25:10 +0000 (21:25 -0700)]
[docs] order ipython notebooks

9 years ago[example] resurrect imagenet training scripts
Evan Shelhamer [Fri, 19 Sep 2014 03:24:19 +0000 (20:24 -0700)]
[example] resurrect imagenet training scripts

9 years ago[model zoo] ignore models -- only for reference or zoo
Evan Shelhamer [Fri, 19 Sep 2014 03:15:50 +0000 (20:15 -0700)]
[model zoo] ignore models -- only for reference or zoo

9 years ago[model zoo] download from gist grooming
Evan Shelhamer [Fri, 19 Sep 2014 03:06:24 +0000 (20:06 -0700)]
[model zoo] download from gist grooming

- invoke by shell
- default download dir to models/
- save to flat dir of owner-gist instead of nested owner/gist

9 years agoMerge pull request #1110 from sergeyk/dev
Evan Shelhamer [Thu, 18 Sep 2014 23:27:52 +0000 (16:27 -0700)]
Merge pull request #1110 from sergeyk/dev

  [model zoo] download gist script

9 years ago[model zoo] download gist script
Sergey Karayev [Thu, 18 Sep 2014 23:11:07 +0000 (16:11 -0700)]
[model zoo] download gist script

9 years agoMerge pull request #594 from longjon/layer-reshaping
Evan Shelhamer [Thu, 18 Sep 2014 20:32:35 +0000 (13:32 -0700)]
Merge pull request #594 from longjon/layer-reshaping

On-the-fly net resizing, without reallocation (where possible)

9 years agocheck that LRN's local_size is odd as the current implementation requires
Jonathan L Long [Fri, 12 Sep 2014 23:07:34 +0000 (16:07 -0700)]
check that LRN's local_size is odd as the current implementation requires

9 years ago[docs] clarify the use of Blob::Reshape a bit
Jonathan L Long [Fri, 12 Sep 2014 22:33:49 +0000 (15:33 -0700)]
[docs] clarify the use of Blob::Reshape a bit

9 years ago[pycaffe] expose Net::Reshape
Jonathan L Long [Fri, 12 Sep 2014 22:23:11 +0000 (15:23 -0700)]
[pycaffe] expose Net::Reshape

9 years agoadd Net::Reshape for only reshaping
Jonathan L Long [Fri, 12 Sep 2014 22:20:52 +0000 (15:20 -0700)]
add Net::Reshape for only reshaping

Note that it is not normally necessary to call this function when using
reshapable nets, but sometimes it can be useful to compute the sizes of
intermediate layers without waiting for the forward pass.

9 years agoinclude Reshape in caffe time
Jonathan L Long [Fri, 12 Sep 2014 21:34:16 +0000 (14:34 -0700)]
include Reshape in caffe time

Since we are now calling Reshape in the Forward pass, it's only fair to
include it when timing. Reshape calls should normally be four or so
orders of magnitude faster than Forward calls; this change also makes it
easy to notice a mistake that causes something slow to happen in
Reshape.

9 years agotest net reshaping
Jonathan L Long [Wed, 2 Jul 2014 19:21:10 +0000 (12:21 -0700)]
test net reshaping

9 years agodefault LayerSetUp to no-op instead of NOT_IMPLEMENTED
Jonathan L Long [Fri, 12 Sep 2014 20:58:10 +0000 (13:58 -0700)]
default LayerSetUp to no-op instead of NOT_IMPLEMENTED

Now that top blobs are set up in Layer::Reshape, it's Reshape that is
mandatory, and simple layers often don't need to implement LayerSetUp.
Reshape is (already) declared abstract, so not implementing it is a
compile-time error.

9 years agocall Reshape in Layer::SetUp
Jonathan L Long [Fri, 12 Sep 2014 20:56:38 +0000 (13:56 -0700)]
call Reshape in Layer::SetUp

Strictly speaking, Reshape doesn't need to be called until the first
Forward call; however, much existing code (especially tests) assumes
that top blobs will be set up in SetUp, so we may as well do it there.

9 years agosplit off Reshape for vision layers
Jonathan L Long [Thu, 11 Sep 2014 06:31:33 +0000 (23:31 -0700)]
split off Reshape for vision layers

Note that we are dropping some checks from LRN layer. However, these
checks are fairly redundant; something is very wrong if these layers
are producing top blobs that are different sizes than their inputs, and
tests are the right place to catch that. The thing that really should be
checked (that isn't) is that that local_size needs to be odd; this will
be added in a future commit.

9 years agosplit off Reshape for common layers
Jonathan L Long [Thu, 11 Sep 2014 05:42:45 +0000 (22:42 -0700)]
split off Reshape for common layers

9 years agosplit off Reshape for neuron layers
Jonathan L Long [Thu, 11 Sep 2014 04:48:51 +0000 (21:48 -0700)]
split off Reshape for neuron layers

9 years agosplit off Reshape for loss layers
Jonathan L Long [Thu, 11 Sep 2014 04:30:05 +0000 (21:30 -0700)]
split off Reshape for loss layers

9 years agosplit off Reshape for data layers
Jonathan L Long [Wed, 10 Sep 2014 21:57:07 +0000 (14:57 -0700)]
split off Reshape for data layers

9 years agoseparate setConvolutionDesc from createConvolutionDesc
Jonathan L Long [Thu, 11 Sep 2014 06:15:22 +0000 (23:15 -0700)]
separate setConvolutionDesc from createConvolutionDesc

9 years agoseparate setTensor4dDesc from createTensor4dDesc
Jonathan L Long [Thu, 11 Sep 2014 04:51:58 +0000 (21:51 -0700)]
separate setTensor4dDesc from createTensor4dDesc

This will make it possible to add reshaping to cuDNN layers.

9 years agoenable reshaping in the forward pass
Jonathan L Long [Wed, 10 Sep 2014 21:51:58 +0000 (14:51 -0700)]
enable reshaping in the forward pass

Note that calling Reshape when no reshape is necessary should be
effectively a no-op, so this is not a performance regression.

9 years agodon't reallocate blobs when shrinking memory use
Jonathan L Long [Wed, 2 Jul 2014 20:08:26 +0000 (13:08 -0700)]
don't reallocate blobs when shrinking memory use

This allows nets to be reshaped very quickly (essentially for free) as
long as sufficient memory has been allocated. Calling Blob::Reshape in
order to free up memory becomes impossible; however, this is not a
normal use case (and deleting blobs does free memory).

9 years agoadd abstract Layer::Reshape, and document the new method protocol
Jonathan L Long [Wed, 10 Sep 2014 21:43:11 +0000 (14:43 -0700)]
add abstract Layer::Reshape, and document the new method protocol

9 years agouse Blob directly instead of shared_ptr for EltwiseLayer::max_idx_
Jonathan L Long [Thu, 11 Sep 2014 05:06:15 +0000 (22:06 -0700)]
use Blob directly instead of shared_ptr for EltwiseLayer::max_idx_

This is in keeping with #742.

9 years agoMerge pull request #1104 from shelhamer/conv-comments-tests
Evan Shelhamer [Thu, 18 Sep 2014 16:45:31 +0000 (09:45 -0700)]
Merge pull request #1104 from shelhamer/conv-comments-tests

Document and Test Convolution

9 years agoMerge pull request #1100 from cNikolaou/issue1099
Evan Shelhamer [Thu, 18 Sep 2014 16:41:34 +0000 (09:41 -0700)]
Merge pull request #1100 from cNikolaou/issue1099

Polish mnist + cifar10 examples.

9 years ago[docs] lenet grooming
Evan Shelhamer [Thu, 18 Sep 2014 16:41:19 +0000 (09:41 -0700)]
[docs] lenet grooming

9 years ago[docs] comment ConvolutionLayer
Evan Shelhamer [Thu, 18 Sep 2014 06:38:31 +0000 (23:38 -0700)]
[docs] comment ConvolutionLayer

9 years agotest convolution by random weights for robustness
Evan Shelhamer [Thu, 18 Sep 2014 15:40:00 +0000 (08:40 -0700)]
test convolution by random weights for robustness

9 years agotest convolution against explicit reference implementation
Evan Shelhamer [Wed, 17 Sep 2014 22:10:18 +0000 (15:10 -0700)]
test convolution against explicit reference implementation

To thoroughly check convolution, the output is compared against a
reference implementation by explicit looping. Simple and group
convolution by the Caffe and cuDNN engines are checked against the
reference.

9 years agoUpdated mnist/readme.md file with additional information.
Christos Nikolaou [Thu, 18 Sep 2014 09:49:17 +0000 (12:49 +0300)]
Updated mnist/readme.md file with additional information.

9 years agoUpdate readme.md files of cifar10 and mnist examples. Fixed broken links.
Christos Nikolaou [Wed, 17 Sep 2014 18:28:51 +0000 (21:28 +0300)]
Update readme.md files of cifar10 and mnist examples. Fixed broken links.

9 years agoMerge pull request #1093 from CellScope/io-cant-load-error-msg
Evan Shelhamer [Tue, 16 Sep 2014 23:01:13 +0000 (16:01 -0700)]
Merge pull request #1093 from CellScope/io-cant-load-error-msg

[fix] Move file reading error checking closer to actual file read command

9 years ago[Bugfix] Move error checking closer to file read
Daniel Golden [Tue, 9 Sep 2014 20:42:40 +0000 (13:42 -0700)]
[Bugfix] Move error checking closer to file read

Previously, if (height > 0 && width > 0) was true, the
cv::resize() function would be called before cv_img_origin was
confirmed valid; if the image file/filename was not valid, this
caused an opencv assert error like this:

terminate called after throwing an instance of 'cv::Exception'
  what():  /tmp/A3p0_4200_32550/batserve/A3p0/glnxa64/OpenCV/modules/imgproc/src/imgwarp.cpp:1725: error: (-215)
  ssize.area() > 0 in function resize

9 years agoMerge pull request #1088 from shelhamer/fix-solverstate-filename
longjon [Tue, 16 Sep 2014 22:38:05 +0000 (15:38 -0700)]
Merge pull request #1088 from shelhamer/fix-solverstate-filename

Fix snapshot filename for solver states

9 years agoMerge pull request #1091 from ronghanghu/fix_window_data_layer
Jeff Donahue [Tue, 16 Sep 2014 17:33:51 +0000 (10:33 -0700)]
Merge pull request #1091 from ronghanghu/fix_window_data_layer

set up datum size for WindowDataLayer

9 years agoset up datum size for WindowDataLayer
Ronghang Hu [Tue, 16 Sep 2014 16:56:11 +0000 (09:56 -0700)]
set up datum size for WindowDataLayer

9 years ago[fix] snapshot model weights as .caffemodel, solver state as .solverstate
Evan Shelhamer [Tue, 16 Sep 2014 15:19:02 +0000 (08:19 -0700)]
[fix] snapshot model weights as .caffemodel, solver state as .solverstate

9 years ago[example] update paths in net surgery
Evan Shelhamer [Tue, 16 Sep 2014 15:13:17 +0000 (08:13 -0700)]
[example] update paths in net surgery

9 years agoMerge pull request #1083 from longjon/fix-solver-gpu-init
Evan Shelhamer [Mon, 15 Sep 2014 22:59:17 +0000 (15:59 -0700)]
Merge pull request #1083 from longjon/fix-solver-gpu-init

Fix solver GPU initialization order (e.g., training with cuDNN on non-default device)

9 years agofix caffe train GPU initialization
Jonathan L Long [Mon, 15 Sep 2014 21:15:58 +0000 (14:15 -0700)]
fix caffe train GPU initialization

Previously, the solver constructed nets before the caffe train tool read
the --gpu flag, which can cause errors due to LayerSetUp executing on
the wrong device (breaking cuDNN, for example).

9 years agoMerge pull request #1077 from bhack/glog_ppa
Jeff Donahue [Sun, 14 Sep 2014 22:14:46 +0000 (15:14 -0700)]
Merge pull request #1077 from bhack/glog_ppa

Add ppa for gflag and glog

9 years agoMerge pull request #1076 from kloudkl/cuda-6.5
Evan Shelhamer [Sun, 14 Sep 2014 21:18:52 +0000 (14:18 -0700)]
Merge pull request #1076 from kloudkl/cuda-6.5

Update CUDA to version 6.5 in the Travis install script

9 years agoFix a little typo
bhack [Sun, 14 Sep 2014 20:19:51 +0000 (22:19 +0200)]
Fix a little typo

9 years agoFix comments
bhack [Sun, 14 Sep 2014 19:16:38 +0000 (21:16 +0200)]
Fix comments

9 years agofix spelling error in caffe.proto
Jonathan L Long [Sun, 14 Sep 2014 01:30:52 +0000 (18:30 -0700)]
fix spelling error in caffe.proto

9 years agofix out-of-date next ID comment for SolverParameter
Jonathan L Long [Sun, 14 Sep 2014 01:30:32 +0000 (18:30 -0700)]
fix out-of-date next ID comment for SolverParameter

9 years agoUpdate CUDA to version 6.5 in the Travis install script
Kai Li [Fri, 12 Sep 2014 16:21:06 +0000 (00:21 +0800)]
Update CUDA to version 6.5 in the Travis install script

9 years agoAdd ppa for gflag and glog
bhack [Fri, 12 Sep 2014 17:50:15 +0000 (19:50 +0200)]
Add ppa for gflag and glog

9 years agoMerge pull request #1051 from jeffdonahue/travis-red-errors
Jeff Donahue [Thu, 11 Sep 2014 15:45:09 +0000 (17:45 +0200)]
Merge pull request #1051 from jeffdonahue/travis-red-errors

restore "red X" build failures in Travis

9 years agoadd -fPIC flag to CMake build
Jeff Donahue [Thu, 11 Sep 2014 14:08:12 +0000 (16:08 +0200)]
add -fPIC flag to CMake build

9 years agorestore "red X" build failures in Travis
Jeff Donahue [Mon, 8 Sep 2014 09:11:41 +0000 (11:11 +0200)]
restore "red X" build failures in Travis

9 years agoMerge pull request #1067 from bhack/lmdb
Jeff Donahue [Thu, 11 Sep 2014 05:00:33 +0000 (07:00 +0200)]
Merge pull request #1067 from bhack/lmdb

Get lmdb from openldap

9 years agoFix lmbdb travis with openldap
bhack [Wed, 10 Sep 2014 22:36:04 +0000 (00:36 +0200)]
Fix lmbdb travis with openldap

9 years agoMerge pull request #1053 from jeffdonahue/to3i-elem_max_layer
Jeff Donahue [Wed, 10 Sep 2014 13:49:45 +0000 (15:49 +0200)]
Merge pull request #1053 from jeffdonahue/to3i-elem_max_layer

rebase and fixup #688 from @to3i: elementwise max

9 years agoAdded contrastive loss layer, associated tests, and a siamese network example using...
Nick Carlevaris-Bianco [Thu, 21 Aug 2014 13:32:10 +0000 (09:32 -0400)]
Added contrastive loss layer, associated tests, and a siamese network example using shared weights and the contrastive loss.

9 years agolint & reduce gradient check stepsize to pass checks
Jeff Donahue [Mon, 8 Sep 2014 15:49:42 +0000 (17:49 +0200)]
lint & reduce gradient check stepsize to pass checks

9 years agoImplemented elementwise max layer
to3i [Fri, 11 Jul 2014 11:19:23 +0000 (13:19 +0200)]
Implemented elementwise max layer

9 years agoBack-merge to dev for slides
Evan Shelhamer [Mon, 8 Sep 2014 10:47:47 +0000 (12:47 +0200)]
Back-merge to dev for slides

9 years agoMerge pull request #1052 from shelhamer/caffe-presentation
Evan Shelhamer [Mon, 8 Sep 2014 10:46:21 +0000 (12:46 +0200)]
Merge pull request #1052 from shelhamer/caffe-presentation

Caffe tutorial slides

9 years ago[docs] replace intro slides with caffe tutorial
Evan Shelhamer [Mon, 8 Sep 2014 10:44:21 +0000 (12:44 +0200)]
[docs] replace intro slides with caffe tutorial

9 years agoRevert "call __signbit for CUDA >= 6.5 implementation" -- doesn't
Jeff Donahue [Mon, 8 Sep 2014 09:02:31 +0000 (11:02 +0200)]
Revert "call __signbit for CUDA >= 6.5 implementation" -- doesn't
compile on OSX w/ CUDA 6.5

This reverts commit 8819f5953b903ec8b48e541271737e89a2cd24e6.

9 years agoMerge pull request #1050 from jeffdonahue/linecount-more
Jeff Donahue [Mon, 8 Sep 2014 08:49:06 +0000 (10:49 +0200)]
Merge pull request #1050 from jeffdonahue/linecount-more

linecount counts more dirs than just src/

9 years agoMerge pull request #1044 from jeffdonahue/no-tmpnam
Jeff Donahue [Mon, 8 Sep 2014 08:48:49 +0000 (10:48 +0200)]
Merge pull request #1044 from jeffdonahue/no-tmpnam

change uses of tmpnam to mkstemp/mkdtemp

9 years agolinecount counts more dirs than just src/
Jeff Donahue [Mon, 8 Sep 2014 08:42:55 +0000 (10:42 +0200)]
linecount counts more dirs than just src/

9 years ago[lint] cuDNN conv declaration
Evan Shelhamer [Mon, 8 Sep 2014 08:03:55 +0000 (10:03 +0200)]
[lint] cuDNN conv declaration

9 years agoMerge pull request #1046 from shelhamer/cudnn
Evan Shelhamer [Mon, 8 Sep 2014 07:57:44 +0000 (09:57 +0200)]
Merge pull request #1046 from shelhamer/cudnn

cuDNN acceleration

9 years agoMerge pull request #1049 from niuzhiheng/dev
Jeff Donahue [Mon, 8 Sep 2014 07:28:49 +0000 (09:28 +0200)]
Merge pull request #1049 from niuzhiheng/dev

Fixed CMake script of FindOpenBLAS.

9 years agoFixed CMake script of FindOpenBLAS.
ZhiHeng NIU [Mon, 8 Sep 2014 06:46:43 +0000 (14:46 +0800)]
Fixed CMake script of FindOpenBLAS.

9 years agoMerge pull request #1045 from akosiorek/origin/dev
Jeff Donahue [Mon, 8 Sep 2014 06:41:38 +0000 (08:41 +0200)]
Merge pull request #1045 from akosiorek/origin/dev

Fixed CMake building test objects multiple times

9 years agoMerge pull request #1048 from jyegerlehner/conv_layer-init-weight
Jeff Donahue [Mon, 8 Sep 2014 05:34:46 +0000 (07:34 +0200)]
Merge pull request #1048 from jyegerlehner/conv_layer-init-weight

Conv layer: fix crash by setting weight pointer

9 years agoFix more lint.
J Yegerlehner [Mon, 8 Sep 2014 04:10:33 +0000 (23:10 -0500)]
Fix more lint.

9 years agoRepair crash in conv_layer due to weight pointer being NULL.
J Yegerlehner [Mon, 8 Sep 2014 02:46:38 +0000 (21:46 -0500)]
Repair crash in conv_layer due to weight pointer being NULL.

9 years ago[docs] include cuDNN in installation and performance reference
Evan Shelhamer [Sun, 7 Sep 2014 16:59:40 +0000 (18:59 +0200)]
[docs] include cuDNN in installation and performance reference

9 years agoreport cuDNN error string
Evan Shelhamer [Sat, 6 Sep 2014 07:27:51 +0000 (00:27 -0700)]
report cuDNN error string

9 years agoCUDNN_CHECK
Evan Shelhamer [Sat, 6 Sep 2014 07:18:10 +0000 (00:18 -0700)]
CUDNN_CHECK

9 years agostrategize cuDNN softmax
Evan Shelhamer [Sat, 6 Sep 2014 06:53:04 +0000 (23:53 -0700)]
strategize cuDNN softmax

9 years agostrategize cuDNN activations: ReLU, Sigmoid, TanH
Evan Shelhamer [Sat, 6 Sep 2014 05:43:58 +0000 (22:43 -0700)]
strategize cuDNN activations: ReLU, Sigmoid, TanH

9 years agostrategize cuDNN pooling
Evan Shelhamer [Sat, 6 Sep 2014 04:47:56 +0000 (21:47 -0700)]
strategize cuDNN pooling

9 years agostrategize cuDNN convolution
Evan Shelhamer [Tue, 2 Sep 2014 05:05:43 +0000 (22:05 -0700)]
strategize cuDNN convolution

9 years agocall __signbit for CUDA >= 6.5 implementation
Evan Shelhamer [Thu, 4 Sep 2014 00:45:14 +0000 (17:45 -0700)]
call __signbit for CUDA >= 6.5 implementation

9 years agoadd cuDNN to build
Evan Shelhamer [Mon, 1 Sep 2014 21:51:24 +0000 (14:51 -0700)]
add cuDNN to build

9 years agoadded common.cpp explicitly to tests
Adam Kosiorek [Sun, 7 Sep 2014 17:03:44 +0000 (19:03 +0200)]
added common.cpp explicitly to tests

9 years agocpp and cu files processed separately in test build
Adam Kosiorek [Sat, 6 Sep 2014 12:40:54 +0000 (14:40 +0200)]
cpp and cu files processed separately in test build

9 years agoenabled object file reusing in test builds
Adam Kosiorek [Fri, 5 Sep 2014 23:23:02 +0000 (01:23 +0200)]
enabled object file reusing in test builds

9 years agoadd <cuda>/lib64 only if exists to suppress linker warnings
Jeff Donahue [Sun, 7 Sep 2014 09:47:31 +0000 (11:47 +0200)]
add <cuda>/lib64 only if exists to suppress linker warnings

9 years agoremove uses of tmpnam
Jeff Donahue [Fri, 5 Sep 2014 12:01:46 +0000 (05:01 -0700)]
remove uses of tmpnam

9 years agofix transform_param in mnist_autoencoder.prototxt
Jeff Donahue [Sun, 7 Sep 2014 07:44:58 +0000 (09:44 +0200)]
fix transform_param in mnist_autoencoder.prototxt

9 years ago[docs] tutorial/layers: fix inner product sample
Jonathan L Long [Sun, 7 Sep 2014 05:10:29 +0000 (22:10 -0700)]
[docs] tutorial/layers: fix inner product sample

9 years ago[docs] tutorial/layers: describe some more data layers
Jonathan L Long [Sun, 7 Sep 2014 05:09:13 +0000 (22:09 -0700)]
[docs] tutorial/layers: describe some more data layers

9 years ago[docs] tutorial/layers: clean up sample markdown
Jonathan L Long [Sun, 7 Sep 2014 04:42:35 +0000 (21:42 -0700)]
[docs] tutorial/layers: clean up sample markdown

9 years ago[docs] tutorial/layers: brief descriptions of some loss layers
Jonathan L Long [Sun, 7 Sep 2014 04:39:56 +0000 (21:39 -0700)]
[docs] tutorial/layers: brief descriptions of some loss layers

9 years ago[docs] in tutorial/layers, Options -> Parameters
Jonathan L Long [Sun, 7 Sep 2014 04:22:23 +0000 (21:22 -0700)]
[docs] in tutorial/layers, Options -> Parameters

It sounds funny to have optional options, and "parameters" is more in
line with the internal usage.

9 years ago[docs] split layer params in required/optional
Jonathan L Long [Sun, 7 Sep 2014 04:20:36 +0000 (21:20 -0700)]
[docs] split layer params in required/optional

Also, make the parameter name come first. This makes it much easier to
find/scan parameters.