microsoft
/
caffe
зеркало из https://github.com/microsoft/caffe.git
1
0
Форкнуть 0
Код Задачи Пакеты Проекты Релизы Вики Активность
3 475 коммитов 3 Ветки 11 Теги 51 MiB
Граф коммитов

3475 Коммитов

Автор SHA1 Сообщение Дата
philkr 672f30ece3 CMake python version fix 2016-01-06 07:23:35 -08:00
Jeff Donahue b23e9b1b21 Merge pull request #3519 from philkr/faster_solver 
Speeding up ADAM (and maybe other solvers too)
 2016-01-05 21:20:54 -08:00
philkr 6d09ca2829 Speeding up the GPU solvers 2016-01-05 20:33:44 -08:00
Jeff Donahue b086cc3cb6 Merge pull request #3490 from fyu/spaceplus 
remove extra space before +
 2015-12-28 22:27:34 -08:00
Fisher Yu 708c1a122c remove extra space before + 2015-12-28 22:46:49 -05:00
Jon Long 08c5dfd53e Merge pull request #3487 from longjon/dilation 
An early implementation of this functionality for Caffe was written by @gpapan, which was extended and improved by @tamakoji in a previous implementation of this branch.
 2015-12-28 15:56:46 -08:00
Jonathan L Long bbc4e578a5 enable dilated deconvolution 
Since the underlying routines are shared, we need only upgrade
compute_output_shape.
 2015-12-28 15:07:40 -08:00
Jonathan L Long 3e3e9ce176 add short description of dilation to caffe.proto 2015-12-28 15:07:40 -08:00
Fisher Yu c25c579638 disable dilated deconvolution 2015-12-28 15:07:40 -08:00
Fisher Yu 7674799475 add and improve tests for dilated convolution/im2col 2015-12-28 15:07:39 -08:00
Fisher Yu 18c795ebe8 add support for N-D dilated convolution 2015-12-28 15:07:39 -08:00
Fisher Yu 93bfcb5312 add support for 2D dilated convolution 2015-12-28 15:07:35 -08:00
Jon Long 03a84bf464 Merge pull request #3468 from mnogu/blobs_lr-to-lr_mult 
Replace blobs_lr with lr_mult in readme.md.
 2015-12-20 15:49:58 -08:00
Muneyuki Noguchi f19896ccca Replace blobs_lr with lr_mult in readme.md. 
models/finetune_flickr_style/deploy.prototxt uses lr_mult now.
 2015-12-20 19:12:09 +09:00
Evan Shelhamer 79539180ed Merge pull request #3439 from flx42/cudnn_v4 
Add ifdef in CuDNNConvolutionLayer for cuDNN v4
 2015-12-12 01:00:00 -03:00
Felix Abecassis eb2b848df1 Fix CuDNNConvolutionLayer for cuDNN v4 
Add a macro to check the current cuDNN version
 2015-12-10 15:11:51 -08:00
Evan Shelhamer 541386054c Merge pull request #3432 from ianfhunter/patch-1 
[docs] fix typo in interfaces.md
 2015-12-09 12:31:45 -08:00
Ian Hunter b13bda2fcc Update interfaces.md 
typo
 2015-12-09 13:29:01 +00:00
Yangqing Jia 03a00e8290 Merge pull request #3090 from longjon/summarize-tool 
A Python script for at-a-glance net summary
 2015-12-08 17:38:00 -08:00
Jon Long 9c9f94e18a Merge pull request #3395 from BonsaiAI/extract_features-compatibility 
Fix compatibility issues with extract_features
 2015-12-04 13:11:30 -08:00
T.E.A de Souza 99571c471d Correct type of device_id; disambiguate shared_ptr 2015-12-04 13:59:55 +08:00
Jon Long 7e40583db0 Merge pull request #3404 from BonsaiAI/remove-hamming-dist 
Remove hamming_distance and popcount
 2015-12-02 00:11:26 -08:00
Tea 36bf811574 Remove hamming_distance and popcount 2015-12-02 15:39:19 +08:00
Evan Shelhamer fe3abd0a7e Merge pull request #3313 from gdh1995/master 
don't divide by 0 duration when downloading model binary
 2015-12-01 22:17:36 -08:00
Evan Shelhamer 0fa2607e83 Merge pull request #3267 from cbalint13/cmake-cudnn 
[build] Display and store cuDNN version numbers for CMake
 2015-12-01 22:05:37 -08:00
Evan Shelhamer 71abb92bf7 Merge pull request #3285 from longjon/cuda-dead-cpp 
Remove dead preprocessor code for number of CUDA threads
 2015-12-01 22:04:34 -08:00
Evan Shelhamer 196b995efe Merge pull request #3315 from shelhamer/layer-headers 
Dismantle Layer Headers
 2015-12-01 21:30:35 -08:00
Evan Shelhamer 300f43f3ae dismantle layer headers 
No more monolithic includes: split layers into their own headers for modular inclusion and build.
 2015-12-01 21:13:43 -08:00
Ronghang Hu 62ed0d2bd4 Merge pull request #3378 from BonsaiAI/fix-temp-dir-creation-failure 
Safely create temporary files and directories
 2015-11-27 20:53:46 -08:00
Tea 33905d5a80 Secure temporary file creation 2015-11-28 11:14:08 +08:00
T.E.A de Souza 34ee5df55d Secure implementation of MakeTempDir 2015-11-28 10:56:44 +08:00
Ronghang Hu 4e9b449ecb Merge pull request #3320 from BonsaiAI/disambiguate-dtype 
Cast std::max args to Dtype
 2015-11-27 11:29:15 -08:00
Ronghang Hu c9086ca0e5 Merge pull request #2693 from AdamStelmaszczyk/patch-1 
Deprecated OpenCV consts leading to compilation error
 2015-11-27 11:25:52 -08:00
Ronghang Hu c7ee2615a8 Merge pull request #3361 from BonsaiAI/avoid-snprintf 
replace snprintf with a C++98 equivalent
 2015-11-27 10:50:52 -08:00
Ronghang Hu 665649a50d Merge pull request #3352 from lukeyeager/bvlc/pytest-python-layer 
Skip python layer tests if WITH_PYTHON_LAYER unset
 2015-11-26 10:45:19 -08:00
Ronghang Hu f25f51494a Merge pull request #3389 from ronghanghu/remove-stepearly 
Remove bogus stepearly in MNIST example
 2015-11-26 10:34:09 -08:00
Ronghang Hu d3025f5ffb 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.
 2015-11-25 21:02:02 -08:00
Tea b72b0318e2 replace snprintf with a C++98 equivalent 2015-11-26 09:54:12 +08:00
Jeff Donahue 8e8d97d620 Merge pull request #3296 from cdoersch/normalize_batch 
Better normalization options for SoftmaxWithLoss layer
 2015-11-22 19:33:36 -08:00
Carl Doersch 8b2aa7093c Better normalization options for SoftmaxWithLoss layer. 2015-11-22 14:47:10 -08:00
Ronghang Hu df21b6a1c1 Merge pull request #3363 from BonsaiAI/remove-opencv-include 
Exclude core.hpp when building without OpenCV
 2015-11-20 03:08:03 -08:00
Ronghang Hu 70dbcd0860 Merge pull request #3362 from eelstork/patch-2 
GetDB must return a value.
 2015-11-20 02:51:31 -08:00
T.E.A de Souza e09329077d Exclude core.hpp when building without OpenCV 2015-11-20 16:52:25 +08:00
T.E.A de Souza 23e4e4621b 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.
 2015-11-20 16:36:29 +08:00
Tea 41d0c77e58 Convert std::max args to Dtype 2015-11-20 16:25:37 +08:00
Evan Shelhamer 5637fc8caf Merge pull request #3359 from ronghanghu/fix-accuracy-layer-top 
Fix MaxTopBlobs in Accuracy Layer
 2015-11-19 12:07:32 -08:00
Ronghang Hu 1b0716cfd7 Fix MaxTopBlobs in Accuracy Layer 
Fix the typo "MaxTopBlos" to "MaxTopBlobs". This typo causes maximum top number to be incorrect.
 2015-11-19 10:05:48 -08:00
Luke Yeager c4190a56ab Skip python layer tests if WITH_PYTHON_LAYER unset 2015-11-18 10:38:32 -08:00
Evan Shelhamer 603cbfb977 Merge pull request #3321 from BonsaiAI/synced-mem-functions-will-return-a-value 
In syncedmem.cpp, functions shall return a value
 2015-11-15 23:19:58 -08:00
Evan Shelhamer 8150ff1476 Merge pull request #3261 from kli-nlpr/patch-1 
fix plot_training_log.py.example usage text
 2015-11-15 23:00:44 -08:00