Evan Shelhamer [Fri, 30 Jan 2015 04:52:16 +0000 (20:52 -0800)]
Merge pull request #1654 from longjon/softmax-missing-values
Add missing value support to SoftmaxLossLayer
Jeff Donahue [Fri, 30 Jan 2015 03:17:46 +0000 (19:17 -0800)]
Merge pull request #1753 from jeffdonahue/enhance-debug-info
Enhance debug info
Jeff Donahue [Mon, 19 Jan 2015 19:52:04 +0000 (11:52 -0800)]
debug_info in NetParameter so it can be enabled outside training
Jeff Donahue [Tue, 7 Oct 2014 06:46:05 +0000 (23:46 -0700)]
debug_info: print param (and gradient) stats for whole Net after Backward
Jeff Donahue [Fri, 30 Jan 2015 03:07:12 +0000 (19:07 -0800)]
Add BlobMathTest with unit tests for sumsq and asum
Jeff Donahue [Tue, 7 Oct 2014 06:08:38 +0000 (23:08 -0700)]
Blob: add sumsq_{data,diff} methods
Jeff Donahue [Wed, 24 Sep 2014 22:52:14 +0000 (15:52 -0700)]
Enhancements for debug_info to display more information.
Now displays for:
-net inputs
-test nets
-params in ForwardDebugInfo
Jonathan L Long [Tue, 27 Jan 2015 21:27:48 +0000 (13:27 -0800)]
[test] gradient checks for softmax ignore_label and normalize: false
Jonathan L Long [Tue, 27 Jan 2015 21:09:32 +0000 (13:09 -0800)]
document the loss_param options to SoftmaxWithLossLayer
Evan Shelhamer [Mon, 26 Jan 2015 07:13:52 +0000 (23:13 -0800)]
Merge pull request #1555 from drdan14/draw-net-improvements
Improvements to network drawing via draw_net.py
Evan Shelhamer [Mon, 26 Jan 2015 07:08:38 +0000 (23:08 -0800)]
Merge pull request #1632 from 7hil/cifar_lmdb
switch cifar10 example to lmdb
Evan Shelhamer [Mon, 26 Jan 2015 07:06:57 +0000 (23:06 -0800)]
Merge pull request #1746 from dj1989/mat_hdf5_demo
Matlab demo for Caffe-compatible HDF5 read/write
Evan Shelhamer [Mon, 26 Jan 2015 07:05:33 +0000 (23:05 -0800)]
Merge pull request #1755 from jeffdonahue/softmax-optimization
SoftmaxLayer GPU optimization
Evan Shelhamer [Mon, 26 Jan 2015 04:37:52 +0000 (20:37 -0800)]
[pycaffe] de-dupe imports
Evan Shelhamer [Mon, 26 Jan 2015 00:04:51 +0000 (16:04 -0800)]
[example] lenet early stopping -> mnist examples
Jeff Donahue [Sun, 25 Jan 2015 22:06:48 +0000 (14:06 -0800)]
Merge pull request #1754 from jeffdonahue/softmax-loss-fix
SoftmaxWithLossLayer: use CreateLayer
Jeff Donahue [Fri, 23 Jan 2015 04:03:15 +0000 (20:03 -0800)]
Merge pull request #1787 from shelhamer/pytest-caffe-set
[fix] align pytest for solver with #1728
Evan Shelhamer [Fri, 23 Jan 2015 03:54:57 +0000 (19:54 -0800)]
[fix] align pytest for solver with #1728
Jeff Donahue [Fri, 23 Jan 2015 03:45:34 +0000 (19:45 -0800)]
Merge pull request #1786 from xianjiec/dev
fix bugs by adding const
Xianjie Chen [Fri, 23 Jan 2015 03:27:24 +0000 (19:27 -0800)]
fix bugs by adding const
Evan Shelhamer [Thu, 22 Jan 2015 08:29:35 +0000 (00:29 -0800)]
Merge pull request #1473 from longjon/pytest
Python testing
Jeff Donahue [Sun, 2 Nov 2014 09:56:19 +0000 (01:56 -0800)]
hdf5_save_nd_dataset takes a const string& (instead of const string)
Jeff Donahue [Sun, 2 Nov 2014 04:37:05 +0000 (21:37 -0700)]
SoftmaxWithLossLayer: use CreateLayer so that a CuDNNSoftmaxLayer
is created if available
Evan Shelhamer [Wed, 21 Jan 2015 23:43:49 +0000 (15:43 -0800)]
Back-merge fixes + docs
and other fixes and documentation updates.
Jeff Donahue [Sun, 2 Nov 2014 04:22:11 +0000 (21:22 -0700)]
Unroll kernels in SoftmaxLayer...from terrible performance to mediocre
performance.
Jon Long [Tue, 20 Jan 2015 00:59:48 +0000 (16:59 -0800)]
Merge pull request #1756 from jeffdonahue/max-total-bytes-limit
Max out the protobuf file read size limit
Jeff Donahue [Thu, 16 Oct 2014 20:24:39 +0000 (13:24 -0700)]
SetTotalBytesLimit to the max (2 GB minus 1 byte)
Jon Long [Mon, 19 Jan 2015 04:29:47 +0000 (20:29 -0800)]
Merge pull request #1747 from yosinski/doc-up
Updated doc to suggest boost 1.57
Jason Yosinski [Sun, 18 Jan 2015 04:07:36 +0000 (23:07 -0500)]
Updated doc to suggest boost 1.57
Dinesh Jayaraman [Sun, 18 Jan 2015 00:23:48 +0000 (18:23 -0600)]
Matlab demo for Caffe-compatible HDF5 read/write
Jeff Donahue [Sat, 17 Jan 2015 23:59:11 +0000 (15:59 -0800)]
Merge pull request #1434 from pcampr/patch-1
fixed filename in build_docs.sh
Jeff Donahue [Sat, 17 Jan 2015 23:41:44 +0000 (15:41 -0800)]
Make comments for sparse GaussianFiller match actual behavior
(Fixes #1497 reported by @denizyuret)
Christos Nikolaou [Wed, 29 Oct 2014 23:05:12 +0000 (01:05 +0200)]
Update interfaces.md file
Proofread and update the /docs/tutorial/interfaces.md file.
Evan Shelhamer [Fri, 16 Jan 2015 23:59:50 +0000 (15:59 -0800)]
Merge pull request #1388 from rohitgirdhar/cifar_docu_bug
[docs] run CIFAR10 example from caffe root
Evan Shelhamer [Fri, 16 Jan 2015 22:41:52 +0000 (14:41 -0800)]
Merge pull request #1704 from longjon/friendlier-link-messages
Makefile: friendlier messages for link commands
Evan Shelhamer [Fri, 16 Jan 2015 21:41:34 +0000 (13:41 -0800)]
[docs] OpenCV version >= 2.4
Evan Shelhamer [Fri, 16 Jan 2015 21:19:31 +0000 (13:19 -0800)]
Merge pull request #1705 from longjon/origin-rpath
Makefile: specify RPATH using $ORIGIN
Jon Long [Fri, 16 Jan 2015 19:21:49 +0000 (11:21 -0800)]
Merge pull request #1686 from longjon/net-const
Improve const-ness of Net
Evan Shelhamer [Fri, 16 Jan 2015 06:31:25 +0000 (22:31 -0800)]
Merge pull request #1662 from seanbell/fix-python-resize_image
Fix caffe.io.resize_image for the case of constant images
Evan Shelhamer [Fri, 16 Jan 2015 05:59:16 +0000 (21:59 -0800)]
Merge pull request #1728 from shelhamer/pycaffe-mode-phase-device
Change Python interface for mode, phase, and device
Evan Shelhamer [Fri, 16 Jan 2015 05:47:50 +0000 (21:47 -0800)]
check for enough args to convert_imageset
(this might better be handled by making all args flags...)
Evan Shelhamer [Fri, 16 Jan 2015 05:04:43 +0000 (21:04 -0800)]
Merge pull request #1236 from mlapin/legacy_nvcc_support
Drop OpenCV includes from NVCC code for legacy reasons.
Evan Shelhamer [Fri, 16 Jan 2015 04:49:50 +0000 (20:49 -0800)]
Merge pull request #1740 from shelhamer/yosemite-makefile
Support OS X Yosemite / 10.10
Evan Shelhamer [Fri, 16 Jan 2015 04:43:24 +0000 (20:43 -0800)]
lint internal thread
Evan Shelhamer [Fri, 16 Jan 2015 04:43:53 +0000 (20:43 -0800)]
Merge pull request #1335 from ryotat/master
Fix leaking thread and groom internal thread implementation.
Evan Shelhamer [Fri, 16 Jan 2015 00:28:09 +0000 (16:28 -0800)]
support OS X Yosemite / 10.10
- pick libstdc++ for OS X (regardless of version)
- make gtest rely on its own tuple to not conflict with clang
(thanks @pluskid!)
- 10.10 has Accelerate while 10.9 has vecLib for BLAS
(thanks @leonardt and @drdan14)
Evan Shelhamer [Thu, 15 Jan 2015 01:56:23 +0000 (17:56 -0800)]
set mode, phase, device in pycaffe; fix #1700
Attach mode, phase, and device setters to caffe module itself
so that these can be set before making nets. This is needed to properly
initialize layers with the right device and phase configuration.
Update examples to new usage.
Evan Shelhamer [Wed, 14 Jan 2015 19:41:37 +0000 (11:41 -0800)]
Merge pull request #1724 from pannous/wtf
Tell users to go to the caffe-users mailing list
Pannous [Wed, 14 Jan 2015 17:43:49 +0000 (18:43 +0100)]
Message: Please ask usage questions and how to model different tasks on the caffe-users mailing list
Jonathan L Long [Sat, 10 Jan 2015 09:42:23 +0000 (01:42 -0800)]
[build] specify RPATH using $ORIGIN
Currently, when dynamically linking against libcaffe (right now, only
done for tests), RPATH is specified relative to the caffe source root.
This commit fixes RPATH using the special $ORIGIN variable to be
relative to the executable itself, so that there is no dependence on the
working directory.
Jonathan L Long [Sat, 10 Jan 2015 09:18:39 +0000 (01:18 -0800)]
[build] more meaningful messages for link commands
Jonathan L Long [Sat, 10 Jan 2015 09:16:12 +0000 (01:16 -0800)]
fix typo in layer_factory.cpp
Jonathan L Long [Wed, 7 Jan 2015 04:25:53 +0000 (20:25 -0800)]
improve const-ness of Net
Evan Shelhamer [Thu, 8 Jan 2015 04:00:27 +0000 (23:00 -0500)]
BVLC models are for unrestricted use (follow-up to #1650)
Jonathan L Long [Tue, 25 Nov 2014 02:53:14 +0000 (18:53 -0800)]
[pycaffe] basic, partial testing of Net and SGDSolver
Jonathan L Long [Fri, 21 Nov 2014 04:40:56 +0000 (20:40 -0800)]
[travis] run pytest
Jonathan L Long [Tue, 25 Nov 2014 19:07:52 +0000 (11:07 -0800)]
[travis] remove unneeded Makefile.config sed hacking
Make allows variable redefinition, so sed brittleness can be avoided.
Jonathan L Long [Fri, 21 Nov 2014 04:36:56 +0000 (20:36 -0800)]
add "make pytest" for running Python tests
Jeff Donahue [Wed, 7 Jan 2015 01:04:49 +0000 (17:04 -0800)]
Merge pull request #1228 from longjon/solver-step
Refactor Solver to allow interactive stepping
Jonathan L Long [Mon, 29 Sep 2014 23:49:49 +0000 (16:49 -0700)]
[pycaffe] expose SGDSolver.step
Jonathan L Long [Mon, 29 Sep 2014 23:47:06 +0000 (16:47 -0700)]
break out Step from Solver
Evan Shelhamer [Fri, 2 Jan 2015 18:08:47 +0000 (13:08 -0500)]
Merge pull request #1650 from shelhamer/unrestricted-bvlc-models
Open release of BVLC model weights
Jonathan L Long [Tue, 30 Dec 2014 20:31:53 +0000 (12:31 -0800)]
clean up formatting in SoftmaxLossLayer
Jonathan L Long [Tue, 30 Dec 2014 01:08:21 +0000 (17:08 -0800)]
add spatial normalization option to SoftmaxLossLayer
With missing values (and batches of varying spatial dimension),
normalizing each batch across instances can inappropriately give
different instances different weights, so we give the option of simply
normalizing by the batch size instead.
Jonathan L Long [Tue, 30 Dec 2014 01:05:47 +0000 (17:05 -0800)]
add missing value support to SoftmaxLossLayer
Sean Bell [Wed, 31 Dec 2014 01:06:31 +0000 (20:06 -0500)]
fixed resize_image for the case of constant images
Jeff Donahue [Wed, 31 Dec 2014 00:02:31 +0000 (16:02 -0800)]
Merge pull request #1661 from longjon/init-test-labels
Fix sketchy label initialization in NetTest
Jonathan L Long [Tue, 30 Dec 2014 20:52:53 +0000 (12:52 -0800)]
[tests] don't use Gaussian labels in NetTest's TinyNet
Previously, labels were being nonsensically filled with a zero-mean
Gaussian. Now they are just set to constant zero. Note that this is not
necessary for TrickyNet, neither forward nor backward are ever called.
Jon Long [Tue, 30 Dec 2014 10:33:43 +0000 (02:33 -0800)]
Merge pull request #1658 from jeffdonahue/make-everything-tweaks
'make everything' tweaks
Jeff Donahue [Tue, 30 Dec 2014 09:33:05 +0000 (01:33 -0800)]
don't do runtest as part of 'make everything'
Jeff Donahue [Tue, 30 Dec 2014 09:31:46 +0000 (01:31 -0800)]
only build matcaffe as part of 'make everything' if MATLAB_DIR is set
Jon Long [Tue, 30 Dec 2014 04:49:14 +0000 (20:49 -0800)]
Merge pull request #1656 from longjon/fix-softmax-loss-stubs
Fix an error made in removing the SoftmaxLossLayer GPU stubs
Evan Shelhamer [Tue, 30 Dec 2014 03:39:07 +0000 (22:39 -0500)]
Merge pull request #1449 from mprat/patch-1
add pyyaml requirement for python
Jonathan L Long [Tue, 30 Dec 2014 01:59:07 +0000 (17:59 -0800)]
remove SoftmaxLossLayer CPU_ONLY stubs, since there is no GPU version
Evan Shelhamer [Tue, 30 Dec 2014 01:48:07 +0000 (20:48 -0500)]
Merge pull request #1655 from longjon/softmax-loss-todo
Move softmax loss GPU todo comment from .cu file to header file
Jonathan L Long [Tue, 30 Dec 2014 01:36:08 +0000 (17:36 -0800)]
move softmax loss GPU todo comment to header file
There's no need to have GPU stubs just for a comment, and the absence of
a GPU-specific implementation is made more obvious by the nonexistence
of the .cu file.
Jon Long [Mon, 29 Dec 2014 22:57:41 +0000 (14:57 -0800)]
Merge pull request #1648 from longjon/find-warnings
Fix find warnings in upload_model_to_gist.sh
Evan Shelhamer [Mon, 29 Dec 2014 21:23:18 +0000 (16:23 -0500)]
[docs] open release of BVLC models for unrestricted use
See BVLC model license details on the model zoo page.
Evan Shelhamer [Mon, 29 Dec 2014 20:13:59 +0000 (15:13 -0500)]
[docs] groom model zoo intro + list
Jon Long [Mon, 29 Dec 2014 05:39:27 +0000 (21:39 -0800)]
Merge pull request #1561 from longjon/pretty-build
Pretty up the build
Jonathan L Long [Mon, 29 Dec 2014 04:57:37 +0000 (20:57 -0800)]
[scripts] fix find warnings in upload_model_to_gist.sh
Daniel Golden [Tue, 2 Dec 2014 19:20:58 +0000 (11:20 -0800)]
Better instructions for updating Homebrew after modifying formulae
Previous instructions glossed over how to deal with OpenCV-related update problems
Evan Shelhamer [Mon, 29 Dec 2014 04:41:07 +0000 (23:41 -0500)]
Merge pull request #1612 from sguada/googlenet_master
BVLC GoogLeNet
Jeff Donahue [Mon, 29 Dec 2014 02:36:19 +0000 (18:36 -0800)]
Merge pull request #1645 from longjon/remove-get-layer
Remove unused GetLayer function (replaced by LayerRegistry::CreateLayer)
Jonathan L Long [Mon, 29 Dec 2014 02:03:45 +0000 (18:03 -0800)]
remove unused GetLayer function (replaced by LayerRegistry::CreateLayer)
Jonathan L Long [Thu, 11 Dec 2014 22:45:38 +0000 (14:45 -0800)]
pretty the build with the Q variable
Unset Q (in the environment) to see full commands, or edit in
Makefile.config.
Jon Long [Mon, 29 Dec 2014 01:36:24 +0000 (17:36 -0800)]
Merge pull request #1472 from longjon/incremental-build
Makefile improvements: rule consolidation, dependency generation
Jonathan L Long [Mon, 24 Nov 2014 21:37:06 +0000 (13:37 -0800)]
automatic dependency generation
Yangqing Jia [Sun, 28 Dec 2014 21:34:43 +0000 (13:34 -0800)]
Merge pull request #1636 from longjon/get-layer-gone
Holiday merge - Update use of GetLayer to new registry function
Jonathan L Long [Sat, 27 Dec 2014 09:47:59 +0000 (01:47 -0800)]
update use of GetLayer -> LayerRegistry::CreateLayer
Sergio Guadarrama [Fri, 26 Dec 2014 19:13:40 +0000 (11:13 -0800)]
Merge pull request #1585 from longjon/check-malloc
Check host malloc result
Peihao.Huang [Tue, 23 Dec 2014 03:18:51 +0000 (11:18 +0800)]
switch cifar10 example to lmdb
Sergio [Sun, 21 Dec 2014 22:03:49 +0000 (14:03 -0800)]
Warning of fallback only the first time for cudnn_pooling_layer
Jon Long [Mon, 22 Dec 2014 07:27:09 +0000 (23:27 -0800)]
Merge pull request #1607 from kjkjava/master
Use valid MathJax delimiters.
Sergio [Sun, 21 Dec 2014 07:28:19 +0000 (23:28 -0800)]
Added credits and bvlc_googlenet to model_zoo.md
Sergio [Sun, 21 Dec 2014 07:24:32 +0000 (23:24 -0800)]
Added credits for training bvlc models
Sergio [Tue, 2 Dec 2014 21:10:57 +0000 (13:10 -0800)]
Added bvlc_googlenet prototxt and weights
Sergio [Thu, 16 Oct 2014 18:17:24 +0000 (11:17 -0700)]
Fix init current_step
Sergio [Sat, 4 Oct 2014 00:14:20 +0000 (17:14 -0700)]
Adapt lenet_multistep_solver.prototxt to current solvers
Sergio [Sat, 4 Oct 2014 00:14:20 +0000 (17:14 -0700)]
Added Multistep, Poly and Sigmoid learning rate decay policies
Conflicts:
include/caffe/solver.hpp
src/caffe/proto/caffe.proto
src/caffe/solver.cpp