9b89154 | Przemysław Dolata | 13 February 2020, 07:20:36 UTC | Merge pull request #6878 from timgates42/bugfix/typo_overridden Fix simple typo: overrided -> overridden | 13 February 2020, 07:20:36 UTC |
388bf12 | Tim Gates | 12 December 2019, 09:30:01 UTC | Fix simple typo: overrided -> overridden Closes #6877 | 12 December 2019, 09:30:01 UTC |
04ab089 | Cyprien Noel | 02 March 2019, 01:13:01 UTC | Updated Intel's branch description | 02 March 2019, 01:13:01 UTC |
d6d179a | Cyprien Noel | 02 March 2019, 01:05:47 UTC | Updated Intel's branch description | 02 March 2019, 01:05:47 UTC |
99bd997 | Przemysław Dolata | 21 August 2018, 12:53:16 UTC | Merge pull request #6499 from xerus/python_gpu python: Set gpu device id before setting gpu mode | 21 August 2018, 12:53:16 UTC |
128797e | Przemysław Dolata | 21 August 2018, 12:51:57 UTC | Merge pull request #6461 from open-cv/patch_1 fix typos and add passing by reference | 21 August 2018, 12:51:57 UTC |
828dd10 | Przemysław Dolata | 21 August 2018, 11:16:02 UTC | Merge branch 'master' into patch_1 | 21 August 2018, 11:16:02 UTC |
8e97b8a | Przemysław Dolata | 21 August 2018, 11:11:30 UTC | Merge pull request #6455 from lengly/patch-1 Fix typo in inner_product_layer.cpp | 21 August 2018, 11:11:30 UTC |
e15898a | Przemysław Dolata | 21 August 2018, 07:44:25 UTC | Merge pull request #6346 from jerryz123/HDF5_config Added USE_HDF5 flag to build | 21 August 2018, 07:44:25 UTC |
dc6d330 | Przemysław Dolata | 20 August 2018, 05:55:36 UTC | Merge pull request #6320 from Noiredd/clip Clip layer - resurrection | 20 August 2018, 05:55:36 UTC |
4ac6443 | Przemysław Dolata | 17 August 2018, 12:45:04 UTC | Clip layer documentation | 17 August 2018, 12:45:04 UTC |
b56db67 | Noiredd | 30 March 2018, 09:43:44 UTC | test case fix for Clip layer gradient minor lint fixes | 17 August 2018, 12:21:20 UTC |
7f4f5d2 | Harm Berntsen | 18 January 2016, 10:41:14 UTC | Add clip layer | 17 August 2018, 12:21:12 UTC |
24b0905 | Przemysław Dolata | 17 August 2018, 09:54:36 UTC | Merge pull request #6282 from Noiredd/pooling-mode PoolingLayer customizable output shape rounding mode | 17 August 2018, 09:54:36 UTC |
4353628 | Pavel Grunt | 14 August 2018, 13:22:08 UTC | python: Set gpu device id before setting gpu mode Otherwise caffe allocates some memory on GPU#0 | 14 August 2018, 13:23:49 UTC |
f019d0d | Kuang Fangjun | 12 July 2018, 08:36:06 UTC | fix typos and some minor fixes. | 17 July 2018, 02:02:33 UTC |
72e953b | Yuda Liu | 08 July 2018, 07:46:43 UTC | Update inner_product_layer.cpp | 08 July 2018, 07:46:43 UTC |
2a1c552 | Evan Shelhamer | 08 June 2018, 03:57:31 UTC | Merge pull request #6238 from mitar/manual-sgd [pycaffe] expose interface for manual, step-by-step optimization | 08 June 2018, 03:57:31 UTC |
1bdcb74 | Valentin Tolmer | 22 June 2016, 00:12:57 UTC | [pycaffe] test solver update | 07 June 2018, 22:24:56 UTC |
cfcf74f | Mitar | 10 December 2017, 11:11:26 UTC | [pycaffe] expose mutable solver parameter, base lr, and effective lr `solver.lr` is the effective learning rate in use while `solver.base_lr` is the configured learning rate at initialization. the solver parameter is now editable for setting fields that are in use throughout the lifetime of the solver, such as the maximum iteration. | 07 June 2018, 22:18:21 UTC |
c74913d | Mitar | 28 October 2017, 09:52:35 UTC | increment iteration during update, not step with update exposed it is important to increment the iteration when an update is made, whether by step or update alone. more fundementally, it's the update that defines an iterationa, so this is a natural place for the increment. | 07 June 2018, 22:16:08 UTC |
cc1c8fb | Mitar | 28 October 2017, 09:35:17 UTC | [pycaffe] expose solver update to do manual solving a sketch of `solver.step()` done out manually: 1. `solver.net.forward()` 2. `solver.net.backward()` 3. `solver.net.apply_update()` 4. `solver.net.clear_param_diffs()` | 07 June 2018, 22:13:30 UTC |
a357693 | Evan Shelhamer | 06 June 2018, 20:16:35 UTC | Merge pull request #6390 from open-cv/fix-6389 drop unnecessary cast fix issue #6389 | 06 June 2018, 20:16:35 UTC |
05a1436 | Evan Shelhamer | 06 June 2018, 20:13:36 UTC | Merge pull request #6388 from open-cv/fix-6387 fix missing syncedmem constness fix issue #6387 | 06 June 2018, 20:13:36 UTC |
6d912a3 | Kuang Fangjun | 08 May 2018, 02:46:54 UTC | fix issue #6389 | 08 May 2018, 02:46:54 UTC |
0536720 | Kuang Fangjun | 08 May 2018, 02:36:44 UTC | fix issue #6387. | 08 May 2018, 02:36:44 UTC |
8645207 | Przemysław Dolata | 17 April 2018, 12:44:25 UTC | Merge pull request #6219 from uhfband/fix-caffe_pb2-module Fix incorrect namespace for pycaffe submodule caffe_pb2 | 17 April 2018, 12:44:25 UTC |
3318a46 | Jerry Zhao | 16 April 2018, 09:26:08 UTC | Cherry-picked USE_HDF5 from Android branch | 16 April 2018, 09:30:19 UTC |
3066720 | Przemysław Dolata | 12 April 2018, 06:13:23 UTC | Merge pull request #6342 from Noiredd/gauss-fill-test-fix Gaussian filler tests adjustments | 12 April 2018, 06:13:23 UTC |
356a6cc | Przemysław Dolata | 11 April 2018, 13:32:25 UTC | tweaked Gaussian filler tests for less false fails | 11 April 2018, 13:32:25 UTC |
106bfcf | Przemysław Dolata | 10 April 2018, 22:20:12 UTC | Revised guidelines for GitHub issues (#6327) revised guidelines for GitHub issues and caffe-users posts | 10 April 2018, 22:20:12 UTC |
c46fc00 | Viktor Richter | 09 April 2018, 14:51:04 UTC | Fix cmake < v3.7 compatibility in Cuda.cmake (#6338) Fix for compatibility with CMake <3.7 (related conversation under 37e4289) * Fix cmake < v3.7 compatibility in Cuda.cmake * Fix version test variable naming in Cuda.cmake | 09 April 2018, 14:51:04 UTC |
723e552 | Przemysław Dolata | 09 April 2018, 07:28:53 UTC | Merge pull request #6336 from Coderx7/master Minor correction concerning compilation compatibility with CUDA 9.0 (see #6237) | 09 April 2018, 07:28:53 UTC |
08b3308 | Seyyed Hossein Hasanpour | 09 April 2018, 05:36:49 UTC | Minor correction concerning compilation compatibility with CUDA 9.0 Since CUDA 9.0 doesn't support sm_20 and sm_21 anymore. This PR allows Caffe to compile with CUDA 9.0 and newer versions successfully. This addresses the discussion concerning [#6237](https://github.com/BVLC/caffe/pull/6237) in [master (#6237)](https://github.com/BVLC/caffe/commit/cb150eca6d593ddb85e53acd05b8dcf709ea8337#diff-2004a3d3e6b4ed2e2812bb0b4b998f18) | 09 April 2018, 05:36:49 UTC |
cb150ec | Przemysław Dolata | 06 April 2018, 14:16:48 UTC | Merge pull request #6237 from jasjuang/master Make caffe compile through cmake with CUDA 9.1 | 06 April 2018, 14:16:48 UTC |
18b09e8 | Przemysław Dolata | 27 March 2018, 11:10:42 UTC | Merge pull request #6277 from twmht/dev_issue_6268 check Embed index in debug mode | 27 March 2018, 11:10:42 UTC |
d09f157 | twmht | 23 March 2018, 14:21:06 UTC | check embed index in debug mode | 23 March 2018, 15:39:00 UTC |
dabbc91 | Mikhail Antonenka | 17 March 2018, 15:26:40 UTC | Added Swish layer (#6002) * added swish layer (cpu) * swish layer: added tests * swish layer: optimized backpropogation * swish layer: added cuda implementation * swish layer: added beta parameter * swish layer: incorporated sigmoid layer * swish layer: fix comment of last added parameter * swish layer: added REGISTER_LAYER_CLASS | 17 March 2018, 15:26:40 UTC |
f049522 | Przemysław Dolata | 12 March 2018, 09:52:04 UTC | Merge pull request #6286 from Noiredd/bilinear-filler-fix BilinearFiller tests refactored | 12 March 2018, 09:52:04 UTC |
eb62919 | Noiredd | 09 March 2018, 12:14:32 UTC | bilinear filter test refactor | 09 March 2018, 13:15:08 UTC |
69da2cf | Przemysław Dolata | 09 March 2018, 08:19:21 UTC | Merge pull request #6278 from Noiredd/filler-fix 1D blob handling in MSRA/Xavier fillers + new filler tests | 09 March 2018, 08:19:21 UTC |
527a1c1 | Noiredd | 08 March 2018, 13:02:10 UTC | Filler testing overhaul | 08 March 2018, 13:05:02 UTC |
d7da092 | Noiredd | 07 March 2018, 12:57:56 UTC | PoolingLayer customizable output shape rounding mode | 07 March 2018, 12:57:56 UTC |
7b3ac40 | nic25 | 07 March 2018, 11:40:52 UTC | Add lr_mult label to the network graph in draw_net.py (#6273) draw_net.py refactoring and optional LR visualization * refactoring `get_layer_label` rewrote the function body to make it more streamlined. does not affect inputs and outputs * optionally visualize LR when drawing the network adds an option to `python/draw_net.py` that allows to visualize information about the learning rate multiplier (if relevant) when drawing the network's graph. | 07 March 2018, 11:40:52 UTC |
412f18d | Noiredd | 06 March 2018, 12:39:49 UTC | 1D blob handling in MSRA/Xavier fillers | 06 March 2018, 12:39:49 UTC |
379a3ba | Przemysław Dolata | 26 February 2018, 09:56:10 UTC | Merge pull request #6249 from Noiredd/legacy-tools Remove legacy tools | 26 February 2018, 09:56:10 UTC |
8e09610 | Noiredd | 23 February 2018, 13:45:59 UTC | Remove legacy tools | 23 February 2018, 13:45:59 UTC |
5c6a290 | Przemysław Dolata | 21 February 2018, 10:39:39 UTC | Merge pull request #6104 from YaYaB/master_bvlc Check solver gamma and stepsize to avoid unexplained core dump | 21 February 2018, 10:39:39 UTC |
f7135ed | Przemysław Dolata | 20 February 2018, 13:03:14 UTC | Merge pull request #5149 from yanchen036/master fix extension extraction in matchExt | 20 February 2018, 13:03:14 UTC |
2571808 | Przemysław Dolata | 20 February 2018, 12:11:00 UTC | Merge pull request #6176 from qu1j0t3/simplify-pip-cmd Simplify pip requirements installation | 20 February 2018, 12:11:00 UTC |
76f48fe | Przemysław Dolata | 20 February 2018, 07:31:01 UTC | Merge pull request #6240 from knsong/master Fix filler compatibility for ND convolution | 20 February 2018, 07:31:01 UTC |
ced55b0 | knsong | 17 February 2018, 07:56:32 UTC | Fix compatibility for ND convolution | 17 February 2018, 07:56:32 UTC |
b3deb95 | yanchen036 | 02 January 2017, 05:33:49 UTC | bug fix: ext should not include the '.' | 15 February 2018, 07:21:45 UTC |
37e4289 | jasjuang | 14 February 2018, 00:57:18 UTC | fix cuda 9.1 compilation | 14 February 2018, 00:57:18 UTC |
a44c444 | Przemysław Dolata | 12 February 2018, 08:35:27 UTC | Merge pull request #6123 from IlyaOvodov/master "weights" added to solver parameters, "snapshot_prefix" field default initialization | 12 February 2018, 08:35:27 UTC |
6fa4c62 | iovodov | 13 January 2018, 14:19:45 UTC | Automatic replacement of snapshot_prefix parameter if it is empty or points to a directory. See issue #6110 proposed improvement No.2 | 10 February 2018, 18:51:51 UTC |
c326294 | iovodov | 18 December 2017, 19:39:03 UTC | Weight parameter in solver is used in caffe.exe Loading weights is moved from caffe.exe to solver class, so new "weights" solver parameter is used not only from command line but when caffe is used as library (including python) corrected formatting fixed line length more formatting corrected | 10 February 2018, 18:51:51 UTC |
0582f84 | Yegor Bedarev | 08 February 2018, 11:05:21 UTC | Fix incorrect namespace for pycaffe submodule caffe_pb2 generated by protobuf | 08 February 2018, 11:05:21 UTC |
87e1512 | Przemysław Dolata | 06 February 2018, 07:46:25 UTC | Merge pull request #5598 from ZoroDerVonCodier/patch-1 Update euclidean_loss_layer.hpp with corrected reference in comment | 06 February 2018, 07:46:25 UTC |
cc521a0 | Przemysław Dolata | 03 February 2018, 16:41:46 UTC | Merge pull request #6210 from mzsanford/classfier_deprecation_warning Update Classifier and Detector to avoid deprecation warning | 03 February 2018, 16:41:46 UTC |
0050c20 | Matt Sanford | 02 February 2018, 21:23:23 UTC | Update Classifier and Detector to avoid deprecation warning | 02 February 2018, 21:23:23 UTC |
d2627e9 | Przemysław Dolata | 02 February 2018, 15:47:46 UTC | Merge pull request #5545 from brunobowden/shape_mismatch_checks Shape mismatch CHECK logging improvements | 02 February 2018, 15:47:46 UTC |
88c9618 | Przemysław Dolata | 01 February 2018, 13:43:44 UTC | corrected description of set_transpose in io.py | 01 February 2018, 13:43:44 UTC |
d1208db | Przemysław Dolata | 31 January 2018, 08:10:34 UTC | Merge pull request #5865 from cheshirekow/fix/caffe_rpath Fix cmake RPATH | 31 January 2018, 08:10:34 UTC |
08a95a4 | Evan Shelhamer | 29 January 2018, 19:31:14 UTC | Merge pull request #6202 from shelhamer/fix-scratch-bottom-diff Clear Scratch Diffs to Prevent Contaminating Backward through Splits | 29 January 2018, 19:31:14 UTC |
4116590 | Evan Shelhamer | 29 January 2018, 00:58:39 UTC | explain use of scratch diffs in comments a few layers make use of otherwise unused diffs to accumulate results, but unless the diffs are cleared in forward this contaminates the gradients when these layers share a bottom and their backward is skipped. | 29 January 2018, 01:09:43 UTC |
12a7038 | Evan Shelhamer | 29 January 2018, 00:42:07 UTC | clear scratch use of accuracy bottom diff | 29 January 2018, 01:05:37 UTC |
25c217c | linziyi | 18 January 2018, 19:07:45 UTC | clear scratch use of loss bottom diffs | 29 January 2018, 01:05:26 UTC |
7c573ca | Evan Shelhamer | 29 January 2018, 00:48:26 UTC | Merge pull request #5924 from bowang/cudnn_deconv speed-up: add cuDNN deconvolution layer and test | 29 January 2018, 00:48:26 UTC |
bb4ffa4 | Evan Shelhamer | 28 January 2018, 00:39:59 UTC | Merge pull request #6201 from shelhamer/official-aws-ami installation: switch pointer to official AWS AMI | 28 January 2018, 00:39:59 UTC |
ecdc289 | Evan Shelhamer | 28 January 2018, 00:37:06 UTC | docs: switch to official AWS AMI | 28 January 2018, 00:37:06 UTC |
7d2ecf9 | Toby Thain | 15 January 2018, 18:16:05 UTC | Simplify pip invocation. | 15 January 2018, 18:16:05 UTC |
7e97067 | Przemysław Dolata | 10 January 2018, 19:30:43 UTC | Merge pull request #6048 from sclarkson/master Fix Makefile parallel builds missing protobuf header | 10 January 2018, 19:30:43 UTC |
e963ef4 | Przemysław Dolata | 03 January 2018, 09:21:03 UTC | Merge pull request #6121 from xerus/typo Cuda.cmake: Fix a typo in a comment | 03 January 2018, 09:21:03 UTC |
c98de53 | Pavel Grunt | 20 December 2017, 12:07:47 UTC | Cuda.cmake: Fix a typo in a comment | 20 December 2017, 17:20:05 UTC |
c23b356 | YaYaB | 12 December 2017, 16:16:59 UTC | Add check values of gamma and stepsize to avoid unexplained core dump | 12 December 2017, 16:16:59 UTC |
9946622 | Przemysław Dolata | 29 November 2017, 11:28:31 UTC | Merge pull request #6084 from Noiredd/accuracy-count-fix Added count==0 safeguard to CPU accuracy calculation | 29 November 2017, 11:28:31 UTC |
3be5297 | Noiredd | 29 November 2017, 10:48:29 UTC | Added count==0 safeguard to CPU accuracy calculation | 29 November 2017, 10:48:29 UTC |
e93b5e2 | Przemysław Dolata | 28 November 2017, 10:36:47 UTC | Merge pull request #6079 from Noiredd/cuda9-makefile Makefile example comments for CUDA 9.0 compatibility | 28 November 2017, 10:36:47 UTC |
95d0001 | Noiredd | 28 November 2017, 10:00:51 UTC | Makefile example comments for CUDA 9.0 compatibility | 28 November 2017, 10:00:51 UTC |
fbdc1e1 | sclarkson | 12 November 2017, 02:20:11 UTC | Fix Makefile parallel builds missing protobuf header | 12 November 2017, 02:20:11 UTC |
c430690 | Przemysław Dolata | 07 November 2017, 11:56:12 UTC | Merge pull request #5972 from icyblade/icyblade-patch-1 add support for cuDNN v7 | 07 November 2017, 11:56:12 UTC |
613e13b | Przemysław Dolata | 06 November 2017, 14:42:07 UTC | Merge pull request #5719 from leemgs/upstream-issue5718 Fix: mean shape incompatible with input shape | 06 November 2017, 14:42:07 UTC |
bfc638d | Geunsik Lim | 29 June 2017, 04:12:53 UTC | Fix: mean shape in compatible with input shape This commit is to fix issue #5718. * reference: 1. https://groups.google.com/forum/#!topic/caffe-users/nBpWJCcJoCU 2. https://stackoverflow.com/questions/28692209/using-gpu-despite-setting-cpu-only-yielding-unexpected-keyword-argument Signed-off-by: Geunsik Lim <geunsik.lim@samsung.com> | 02 November 2017, 14:50:19 UTC |
be6a5c4 | Przemysław Dolata | 02 November 2017, 11:52:30 UTC | Merge pull request #5813 from jqueguiner/patch-1 fix web demo install instruction link | 02 November 2017, 11:52:30 UTC |
e5b3fbe | Przemysław Dolata | 02 November 2017, 11:46:05 UTC | Merge pull request #5704 from ArneSuppe/dupDistDirFix Fixed bug where make distribute duplicates python files | 02 November 2017, 11:46:05 UTC |
d8b4283 | Przemysław Dolata | 02 November 2017, 11:34:54 UTC | Merge pull request #5969 from developius/fix-default-mode-warning Fix default mode warning in io.resize_image | 02 November 2017, 11:34:54 UTC |
3a0afbf | Przemysław Dolata | 02 November 2017, 10:56:53 UTC | Merge pull request #5866 from cijianzy/update_link_to_google_style_guide Update link to google style guide. | 02 November 2017, 10:56:53 UTC |
b4ffad8 | Przemysław Dolata | 19 October 2017, 07:53:59 UTC | Merge pull request #5973 from Noiredd/pytest Add absolute tolerance to test_net.py to prevent random Travis fails | 19 October 2017, 07:53:59 UTC |
79ddda7 | Mikhail Antonenka | 17 October 2017, 15:18:32 UTC | infogain loss: fix bottom blobs description | 18 October 2017, 13:20:31 UTC |
691febc | Evan Shelhamer | 11 October 2017, 17:02:53 UTC | Merge pull request #5925 from BVLC/williford-install-ubuntu-16.04-patch-1 [docs] packages needed by Ubuntu 16.04, not just Ubuntu 14.04 | 11 October 2017, 17:02:53 UTC |
243cd89 | Noiredd | 11 October 2017, 09:04:18 UTC | Add absolute tolerance to test_net.py to prevent random Travis fails | 11 October 2017, 09:04:18 UTC |
cd2a014 | Icyblade Dai | 11 October 2017, 07:29:21 UTC | add supports for cuDNN v7 | 11 October 2017, 07:29:21 UTC |
62e0c85 | Shai | 10 August 2017, 07:07:19 UTC | upgrading Accuracy layer: (1) efficient CPU implementation O(L) for top_k, no need for fancy priority_queue etc. (2) GPU implementation | 10 October 2017, 17:30:36 UTC |
e0feb7d | Finnian Anderson | 10 October 2017, 11:15:13 UTC | Fix default mode warning in io.resize_image Signed-off-by: Finnian Anderson <get@finnian.io> | 10 October 2017, 11:15:13 UTC |
fac7434 | Evan Shelhamer | 03 October 2017, 21:20:13 UTC | [docs] fix link to `AbsVal` layer | 03 October 2017, 21:20:13 UTC |
ef2eb4b | Evan Shelhamer | 03 October 2017, 02:05:50 UTC | Merge pull request #5713 from Noiredd/filler fix bilinear filler (and make constant filler more strict, as it should be) | 03 October 2017, 02:05:50 UTC |
888597e | Noiredd | 02 October 2017, 12:39:31 UTC | Fixed bilinear filler, added tests | 02 October 2017, 13:36:07 UTC |
effcdb0 | Evan Shelhamer | 19 September 2017, 11:32:56 UTC | Merge pull request #5904 from longjon/gpu-ptr Expose GPU pointers to Python | 19 September 2017, 11:32:56 UTC |
4705a37 | Jonathan R. Williford | 15 September 2017, 09:38:16 UTC | Packages needed by Ubuntu 16.04 also This line is needed for Ubuntu 16.04: sudo apt-get install libgflags-dev libgoogle-glog-dev liblmdb-dev For reference: * https://github.com/BVLC/caffe/wiki/Ubuntu-16.04-or-15.10-Installation-Guide * https://youtu.be/DnIs4DRjNL4 | 15 September 2017, 09:38:16 UTC |