Evan Shelhamer [Mon, 8 Sep 2014 08:03:55 +0000 (10:03 +0200)]
[lint] cuDNN conv declaration
Evan Shelhamer [Mon, 8 Sep 2014 07:57:44 +0000 (09:57 +0200)]
Merge pull request #1046 from shelhamer/cudnn
cuDNN acceleration
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.
ZhiHeng NIU [Mon, 8 Sep 2014 06:46:43 +0000 (14:46 +0800)]
Fixed CMake script of FindOpenBLAS.
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
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
J Yegerlehner [Mon, 8 Sep 2014 04:10:33 +0000 (23:10 -0500)]
Fix more lint.
J Yegerlehner [Mon, 8 Sep 2014 02:46:38 +0000 (21:46 -0500)]
Repair crash in conv_layer due to weight pointer being NULL.
Evan Shelhamer [Sun, 7 Sep 2014 16:59:40 +0000 (18:59 +0200)]
[docs] include cuDNN in installation and performance reference
Evan Shelhamer [Sat, 6 Sep 2014 07:27:51 +0000 (00:27 -0700)]
report cuDNN error string
Evan Shelhamer [Sat, 6 Sep 2014 07:18:10 +0000 (00:18 -0700)]
CUDNN_CHECK
Evan Shelhamer [Sat, 6 Sep 2014 06:53:04 +0000 (23:53 -0700)]
strategize cuDNN softmax
Evan Shelhamer [Sat, 6 Sep 2014 05:43:58 +0000 (22:43 -0700)]
strategize cuDNN activations: ReLU, Sigmoid, TanH
Evan Shelhamer [Sat, 6 Sep 2014 04:47:56 +0000 (21:47 -0700)]
strategize cuDNN pooling
Evan Shelhamer [Tue, 2 Sep 2014 05:05:43 +0000 (22:05 -0700)]
strategize cuDNN convolution
Evan Shelhamer [Thu, 4 Sep 2014 00:45:14 +0000 (17:45 -0700)]
call __signbit for CUDA >= 6.5 implementation
Evan Shelhamer [Mon, 1 Sep 2014 21:51:24 +0000 (14:51 -0700)]
add cuDNN to build
Adam Kosiorek [Sun, 7 Sep 2014 17:03:44 +0000 (19:03 +0200)]
added common.cpp explicitly to tests
Adam Kosiorek [Sat, 6 Sep 2014 12:40:54 +0000 (14:40 +0200)]
cpp and cu files processed separately in test build
Adam Kosiorek [Fri, 5 Sep 2014 23:23:02 +0000 (01:23 +0200)]
enabled object file reusing in test builds
Jeff Donahue [Sun, 7 Sep 2014 07:44:58 +0000 (09:44 +0200)]
fix transform_param in mnist_autoencoder.prototxt
Jonathan L Long [Sun, 7 Sep 2014 05:10:29 +0000 (22:10 -0700)]
[docs] tutorial/layers: fix inner product sample
Jonathan L Long [Sun, 7 Sep 2014 05:09:13 +0000 (22:09 -0700)]
[docs] tutorial/layers: describe some more data layers
Jonathan L Long [Sun, 7 Sep 2014 04:42:35 +0000 (21:42 -0700)]
[docs] tutorial/layers: clean up sample markdown
Jonathan L Long [Sun, 7 Sep 2014 04:39:56 +0000 (21:39 -0700)]
[docs] tutorial/layers: brief descriptions of some loss layers
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.
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.
Jonathan L Long [Sun, 7 Sep 2014 04:05:56 +0000 (21:05 -0700)]
[docs] add LRN layer to tutorial/layers
Jonathan L Long [Sun, 7 Sep 2014 03:28:02 +0000 (20:28 -0700)]
[docs] fix pooling markdown and add some comments in tutorial
Jonathan L Long [Sun, 7 Sep 2014 03:23:55 +0000 (20:23 -0700)]
[doc] minor edits to convolution layer in tutorial
Jonathan L Long [Sun, 7 Sep 2014 03:14:28 +0000 (20:14 -0700)]
[docs] fixup the MathJax notation in tutorial/layers
Evan Shelhamer [Sun, 7 Sep 2014 01:47:46 +0000 (03:47 +0200)]
Merge pull request #1022 from shelhamer/engine
Add engine switch to pick computational backend
Evan Shelhamer [Sat, 6 Sep 2014 02:36:35 +0000 (19:36 -0700)]
revert separate strategies: engines will extend the caffe standards
Evan Shelhamer [Sat, 6 Sep 2014 02:16:55 +0000 (19:16 -0700)]
revert engine switch for build to always include caffe engine
Evan Shelhamer [Thu, 4 Sep 2014 00:14:59 +0000 (17:14 -0700)]
default engine to Caffe in case config is missing
Evan Shelhamer [Wed, 3 Sep 2014 22:47:35 +0000 (15:47 -0700)]
default engine to Caffe according to compile flag
Evan Shelhamer [Tue, 2 Sep 2014 05:21:33 +0000 (22:21 -0700)]
grooming: drop pointless overrides, stub layer comments
Evan Shelhamer [Tue, 2 Sep 2014 04:29:50 +0000 (21:29 -0700)]
strategize softmax
Evan Shelhamer [Tue, 2 Sep 2014 04:01:11 +0000 (21:01 -0700)]
strategize relu, sigmoid, tanh
Evan Shelhamer [Tue, 2 Sep 2014 03:27:33 +0000 (20:27 -0700)]
strategize pooling
Scaffold engine switching for pooling.
The Caffe pooling is instantiated without regard for engine in:
- LRNLayer
- PoolingLayer tests
- StochasticPoolingLayer tests
- MaxPoolingDropout tests
Evan Shelhamer [Tue, 2 Sep 2014 01:56:08 +0000 (18:56 -0700)]
strategize Caffe convolution
Evan Shelhamer [Tue, 2 Sep 2014 00:44:50 +0000 (17:44 -0700)]
ifdef engine default
Evan Shelhamer [Tue, 2 Sep 2014 00:15:33 +0000 (17:15 -0700)]
add engine parameter for multiple computational strategies
add `engine` switch to layers for selecting a computational backend when
there is a choice. Currently the standard Caffe implementation is the
only backend.
Evan Shelhamer [Mon, 1 Sep 2014 23:54:01 +0000 (16:54 -0700)]
groom proto: sort layer type parameters, put loss_weight after basics
Evan Shelhamer [Mon, 1 Sep 2014 22:43:36 +0000 (15:43 -0700)]
shift CUDA code out of common
Sergio [Sat, 6 Sep 2014 23:30:32 +0000 (16:30 -0700)]
Added initial Hinge Loss
Yangqing Jia [Sat, 6 Sep 2014 16:35:13 +0000 (09:35 -0700)]
more layers
Yangqing Jia [Sat, 6 Sep 2014 00:03:29 +0000 (17:03 -0700)]
conv and pooling
Yangqing Jia [Fri, 5 Sep 2014 23:44:06 +0000 (16:44 -0700)]
neuron layers doc
Yangqing Jia [Fri, 5 Sep 2014 20:47:11 +0000 (13:47 -0700)]
update net
Yangqing Jia [Fri, 5 Sep 2014 20:05:35 +0000 (13:05 -0700)]
fix leaky relu
Yangqing Jia [Fri, 5 Sep 2014 19:58:28 +0000 (12:58 -0700)]
more blob details
Yangqing Jia [Fri, 5 Sep 2014 18:06:26 +0000 (11:06 -0700)]
relu,sigmoid,tanh
Evan Shelhamer [Fri, 5 Sep 2014 17:42:45 +0000 (10:42 -0700)]
[docs] fix br code
Evan Shelhamer [Fri, 5 Sep 2014 17:41:20 +0000 (10:41 -0700)]
[docs] link tutorial
Evan Shelhamer [Fri, 5 Sep 2014 17:40:39 +0000 (10:40 -0700)]
[docs] add titles
Evan Shelhamer [Fri, 5 Sep 2014 16:43:54 +0000 (09:43 -0700)]
Merge pull request #1036 from longjon/test-initialization-param
Add test_initialization option to allow skipping initial test
Evan Shelhamer [Fri, 5 Sep 2014 07:07:53 +0000 (00:07 -0700)]
Merge pull request #1039 from sergeyk/dev
[example] HDF5 classification
Evan Shelhamer [Fri, 5 Sep 2014 00:42:26 +0000 (17:42 -0700)]
Merge pull request #1040 from qipeng/solver-test-fix
fix gradient-solver test by reducing iterations to relax precision
qipeng [Fri, 5 Sep 2014 00:20:35 +0000 (17:20 -0700)]
Gradient-based solver test fix
Sergey Karayev [Fri, 5 Sep 2014 00:08:01 +0000 (01:08 +0100)]
added a two-layer network that gets higher accuracy
Jeff Donahue [Thu, 4 Sep 2014 22:40:04 +0000 (15:40 -0700)]
[docs] fix formatting and other errors in loss & solver
Evan Shelhamer [Thu, 4 Sep 2014 19:54:48 +0000 (12:54 -0700)]
[fix] stop cloc complaint about cu type
Evan Shelhamer [Thu, 4 Sep 2014 18:43:41 +0000 (11:43 -0700)]
fix fine-tuning example: paths, test acc., and total fine-tuning time
Sergey Karayev [Thu, 4 Sep 2014 17:06:31 +0000 (18:06 +0100)]
HDF5 classification example
Evan Shelhamer [Thu, 4 Sep 2014 09:38:19 +0000 (02:38 -0700)]
Merge pull request #917 from sergeyk/model_zoo
Define standard format for Caffe models to open the "model zoo"
Evan Shelhamer [Thu, 4 Sep 2014 09:37:04 +0000 (02:37 -0700)]
[example] update ImageNet timing for K40
Evan Shelhamer [Thu, 4 Sep 2014 09:33:19 +0000 (02:33 -0700)]
fix model download advice and prototxt name for fine-tuning
Jeff Donahue [Thu, 4 Sep 2014 06:34:05 +0000 (23:34 -0700)]
Merge pull request #624 from jeffdonahue/squash-layer
SILENCE layer -- takes 1 or more inputs and produces no output (kudos to @longjon for fixup)
Jeff Donahue [Fri, 4 Jul 2014 04:53:31 +0000 (21:53 -0700)]
add SILENCE layer -- takes one or more inputs and produces no output
This is useful for suppressing undesired outputs.
Jonathan L Long [Thu, 4 Sep 2014 03:55:00 +0000 (20:55 -0700)]
add test_initialization option to allow skipping initial test
Sergey Karayev [Thu, 4 Sep 2014 02:50:20 +0000 (03:50 +0100)]
script to upload/update model info as gist
Sergey Karayev [Thu, 4 Sep 2014 01:50:53 +0000 (02:50 +0100)]
flickr style fine-tuning model (separated from example read me)
Sergey Karayev [Thu, 4 Sep 2014 00:43:35 +0000 (01:43 +0100)]
minor fixes to docs
Sergey Karayev [Thu, 4 Sep 2014 00:08:19 +0000 (01:08 +0100)]
removed mention of getting_pretrained_models page and old paths
Sergey Karayev [Thu, 4 Sep 2014 00:13:29 +0000 (01:13 +0100)]
updating feature extraction example
Sergey Karayev [Thu, 4 Sep 2014 00:24:57 +0000 (01:24 +0100)]
Renaming CaffeNet model prototxts and unignoring models/*
Sergey Karayev [Wed, 3 Sep 2014 14:42:46 +0000 (15:42 +0100)]
removing unneeded scripts from imagenet example
Evan Shelhamer [Thu, 28 Aug 2014 23:28:51 +0000 (16:28 -0700)]
proofread model zoo
Evan Shelhamer [Thu, 28 Aug 2014 22:47:05 +0000 (15:47 -0700)]
snapshot model with caffemodel extension
Sergey Karayev [Wed, 13 Aug 2014 00:29:25 +0000 (17:29 -0700)]
[models] adding zoo readme; caffenet, alexnet, and rcnn models in zoo format
Evan Shelhamer [Thu, 4 Sep 2014 00:52:10 +0000 (17:52 -0700)]
Merge pull request #1034 from sergeyk/dev
[docs] default setting for layout
Sergey Karayev [Thu, 4 Sep 2014 00:44:28 +0000 (01:44 +0100)]
[docs] default setting for layout
Jeff Donahue [Wed, 3 Sep 2014 23:50:48 +0000 (16:50 -0700)]
Merge pull request #1033 from qipeng/dev
[example] convert mnist name fix (crashes xcode compiler)
qipeng [Wed, 3 Sep 2014 23:30:34 +0000 (16:30 -0700)]
[example] convert mnist name fix (crashes xcode compiler)
Evan Shelhamer [Wed, 3 Sep 2014 22:18:21 +0000 (15:18 -0700)]
[example] drop stale mentions of glog env var
Evan Shelhamer [Wed, 3 Sep 2014 21:28:03 +0000 (14:28 -0700)]
Merge pull request #1031 from CellScope/mnist-tutorial-update
fix MNIST tutorial details
Daniel Golden [Wed, 3 Sep 2014 21:13:18 +0000 (14:13 -0700)]
Inline latest lenet_solver.prototxt
Daniel Golden [Wed, 3 Sep 2014 20:18:48 +0000 (13:18 -0700)]
Correct reference to lenet_train_test.prototxt
Not lenet.prototxt
Daniel Golden [Wed, 3 Sep 2014 20:01:29 +0000 (13:01 -0700)]
Point to local file, not github file
This makes the readme file more consistent
Daniel Golden [Wed, 3 Sep 2014 20:00:58 +0000 (13:00 -0700)]
Update paths
Evan Shelhamer [Wed, 3 Sep 2014 21:04:06 +0000 (14:04 -0700)]
Merge pull request #955 from kloudkl/data-layers
Further simplify the data layers and extend the MemoryDataLayer.
- design BaseDataLayer and BasePrefectingDataLayer for simplification
- refactor DataLayer, ImageDataLayer, and WindowDataLayer
- pull up `transform_param` into layer message for de-duplication
- add transformation to MemoryDataLayer
Evan Shelhamer [Wed, 3 Sep 2014 20:58:00 +0000 (13:58 -0700)]
[example] upgrade fine-tuning example to new transformation param
Evan Shelhamer [Wed, 3 Sep 2014 20:27:48 +0000 (13:27 -0700)]
Merge pull request #973 from shelhamer/tutorial-docs
Document Caffe by a tour of key subjects + doxygen dev documentation
Evan Shelhamer [Wed, 3 Sep 2014 20:22:09 +0000 (13:22 -0700)]
[docs] configure doxygen + docs script for docs/doxygen site output
Evan Shelhamer [Wed, 3 Sep 2014 19:59:55 +0000 (12:59 -0700)]
update doxygen config to stop warnings
Evan Shelhamer [Wed, 3 Sep 2014 19:46:47 +0000 (12:46 -0700)]
[docs] suggest the CVPR14 deep learning tutorial for nice contrast
Evan Shelhamer [Wed, 3 Sep 2014 19:25:52 +0000 (12:25 -0700)]
[docs] draft data
Jeff Donahue [Wed, 3 Sep 2014 07:44:23 +0000 (00:44 -0700)]
wrap up solver.md -- add update info for all solvers with citations;
rules of thumb for SGD
Jeff Donahue [Sat, 30 Aug 2014 22:30:48 +0000 (15:30 -0700)]
net.hpp: Doxygen-format docs