platform/upstream/caffe.git
4 years agoUpdated Intel's branch description master
Cyprien Noel [Sat, 2 Mar 2019 01:13:01 +0000 (21:13 -0400)]
Updated Intel's branch description

4 years agoUpdated Intel's branch description
Cyprien Noel [Sat, 2 Mar 2019 01:05:47 +0000 (21:05 -0400)]
Updated Intel's branch description

4 years agoMerge pull request #6499 from xerus/python_gpu
Przemysław Dolata [Tue, 21 Aug 2018 12:53:16 +0000 (14:53 +0200)]
Merge pull request #6499 from xerus/python_gpu

python: Set gpu device id before setting gpu mode

4 years agopython: Set gpu device id before setting gpu mode
Pavel Grunt [Tue, 14 Aug 2018 13:22:08 +0000 (15:22 +0200)]
python: Set gpu device id before setting gpu mode

Otherwise caffe allocates some memory on GPU#0

4 years agoMerge pull request #6461 from open-cv/patch_1
Przemysław Dolata [Tue, 21 Aug 2018 12:51:57 +0000 (14:51 +0200)]
Merge pull request #6461 from open-cv/patch_1

fix typos and add passing by reference

4 years agoMerge branch 'master' into patch_1
Przemysław Dolata [Tue, 21 Aug 2018 11:16:02 +0000 (13:16 +0200)]
Merge branch 'master' into patch_1

4 years agoMerge pull request #6455 from lengly/patch-1
Przemysław Dolata [Tue, 21 Aug 2018 11:11:30 +0000 (13:11 +0200)]
Merge pull request #6455 from lengly/patch-1

Fix typo in inner_product_layer.cpp

4 years agoMerge pull request #6346 from jerryz123/HDF5_config
Przemysław Dolata [Tue, 21 Aug 2018 07:44:25 +0000 (09:44 +0200)]
Merge pull request #6346 from jerryz123/HDF5_config

Added USE_HDF5 flag to build

4 years agoUpdate inner_product_layer.cpp
Yuda Liu [Sun, 8 Jul 2018 07:46:43 +0000 (15:46 +0800)]
Update inner_product_layer.cpp

4 years agoMerge pull request #6320 from Noiredd/clip
Przemysław Dolata [Mon, 20 Aug 2018 05:55:36 +0000 (07:55 +0200)]
Merge pull request #6320 from Noiredd/clip

Clip layer - resurrection

4 years agoCherry-picked USE_HDF5 from Android branch
Jerry Zhao [Mon, 16 Apr 2018 09:26:08 +0000 (02:26 -0700)]
Cherry-picked USE_HDF5 from Android branch

4 years agoClip layer documentation
Przemysław Dolata [Fri, 17 Aug 2018 12:45:04 +0000 (14:45 +0200)]
Clip layer documentation

4 years agotest case fix for Clip layer gradient
Noiredd [Fri, 30 Mar 2018 09:43:44 +0000 (11:43 +0200)]
test case fix for Clip layer gradient

minor lint fixes

4 years agoMerge pull request #6282 from Noiredd/pooling-mode
Przemysław Dolata [Fri, 17 Aug 2018 09:54:36 +0000 (11:54 +0200)]
Merge pull request #6282 from Noiredd/pooling-mode

PoolingLayer customizable output shape rounding mode

4 years agoAdd clip layer
Harm Berntsen [Mon, 18 Jan 2016 10:41:14 +0000 (11:41 +0100)]
Add clip layer

4 years agoMerge pull request #6238 from mitar/manual-sgd
Evan Shelhamer [Fri, 8 Jun 2018 03:57:31 +0000 (23:57 -0400)]
Merge pull request #6238 from mitar/manual-sgd

[pycaffe] expose interface for manual, step-by-step optimization

4 years agofix typos and some minor fixes.
Kuang Fangjun [Thu, 12 Jul 2018 08:36:06 +0000 (16:36 +0800)]
fix typos and some minor fixes.

4 years agoPoolingLayer customizable output shape rounding mode
Noiredd [Wed, 7 Mar 2018 12:57:56 +0000 (13:57 +0100)]
PoolingLayer customizable output shape rounding mode

4 years ago[pycaffe] test solver update
Valentin Tolmer [Wed, 22 Jun 2016 00:12:57 +0000 (17:12 -0700)]
[pycaffe] test solver update

4 years ago[pycaffe] expose mutable solver parameter, base lr, and effective lr
Mitar [Sun, 10 Dec 2017 11:11:26 +0000 (03:11 -0800)]
[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.

4 years agoincrement iteration during update, not step
Mitar [Sat, 28 Oct 2017 09:52:35 +0000 (02:52 -0700)]
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.

4 years ago[pycaffe] expose solver update to do manual solving
Mitar [Sat, 28 Oct 2017 09:35:17 +0000 (02:35 -0700)]
[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()`

4 years agoMerge pull request #6390 from open-cv/fix-6389
Evan Shelhamer [Wed, 6 Jun 2018 20:16:35 +0000 (16:16 -0400)]
Merge pull request #6390 from open-cv/fix-6389

drop unnecessary cast

fix issue #6389

4 years agofix issue #6389
Kuang Fangjun [Tue, 8 May 2018 02:46:54 +0000 (10:46 +0800)]
fix issue #6389

4 years agoMerge pull request #6388 from open-cv/fix-6387
Evan Shelhamer [Wed, 6 Jun 2018 20:13:36 +0000 (16:13 -0400)]
Merge pull request #6388 from open-cv/fix-6387

fix missing syncedmem constness

fix issue #6387

4 years agoMerge pull request #6219 from uhfband/fix-caffe_pb2-module
Przemysław Dolata [Tue, 17 Apr 2018 12:44:25 +0000 (14:44 +0200)]
Merge pull request #6219 from uhfband/fix-caffe_pb2-module

Fix incorrect namespace for pycaffe submodule caffe_pb2

4 years agofix issue #6387.
Kuang Fangjun [Tue, 8 May 2018 02:36:44 +0000 (10:36 +0800)]
fix issue #6387.

4 years agoMerge pull request #6342 from Noiredd/gauss-fill-test-fix
Przemysław Dolata [Thu, 12 Apr 2018 06:13:23 +0000 (08:13 +0200)]
Merge pull request #6342 from Noiredd/gauss-fill-test-fix

Gaussian filler tests adjustments

4 years agotweaked Gaussian filler tests for less false fails
Przemysław Dolata [Wed, 11 Apr 2018 13:32:25 +0000 (15:32 +0200)]
tweaked Gaussian filler tests for less false fails

4 years agoRevised guidelines for GitHub issues (#6327)
Przemysław Dolata [Tue, 10 Apr 2018 22:20:12 +0000 (00:20 +0200)]
Revised guidelines for GitHub issues (#6327)

revised guidelines for GitHub issues and caffe-users posts

4 years agoFix cmake < v3.7 compatibility in Cuda.cmake (#6338)
Viktor Richter [Mon, 9 Apr 2018 14:51:04 +0000 (16:51 +0200)]
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

4 years agoMerge pull request #6336 from Coderx7/master
Przemysław Dolata [Mon, 9 Apr 2018 07:28:53 +0000 (09:28 +0200)]
Merge pull request #6336 from Coderx7/master

Minor correction concerning compilation compatibility with CUDA 9.0 (see #6237)

4 years agoMinor correction concerning compilation compatibility with CUDA 9.0
Seyyed Hossein Hasanpour [Mon, 9 Apr 2018 05:36:49 +0000 (10:06 +0430)]
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)

4 years agoMerge pull request #6237 from jasjuang/master
Przemysław Dolata [Fri, 6 Apr 2018 14:16:48 +0000 (16:16 +0200)]
Merge pull request #6237 from jasjuang/master

Make caffe compile through cmake with CUDA 9.1

4 years agoMerge pull request #6277 from twmht/dev_issue_6268
Przemysław Dolata [Tue, 27 Mar 2018 11:10:42 +0000 (13:10 +0200)]
Merge pull request #6277 from twmht/dev_issue_6268

check Embed index in debug mode

4 years agoAdded Swish layer (#6002)
Mikhail Antonenka [Sat, 17 Mar 2018 15:26:40 +0000 (18:26 +0300)]
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

4 years agoMerge pull request #6286 from Noiredd/bilinear-filler-fix
Przemysław Dolata [Mon, 12 Mar 2018 09:52:04 +0000 (10:52 +0100)]
Merge pull request #6286 from Noiredd/bilinear-filler-fix

BilinearFiller tests refactored

4 years agobilinear filter test refactor
Noiredd [Fri, 9 Mar 2018 12:14:32 +0000 (13:14 +0100)]
bilinear filter test refactor

4 years agoMerge pull request #6278 from Noiredd/filler-fix
Przemysław Dolata [Fri, 9 Mar 2018 08:19:21 +0000 (09:19 +0100)]
Merge pull request #6278 from Noiredd/filler-fix

1D blob handling in MSRA/Xavier fillers + new filler tests

4 years agoFiller testing overhaul
Noiredd [Thu, 8 Mar 2018 13:02:10 +0000 (14:02 +0100)]
Filler testing overhaul

4 years agoAdd lr_mult label to the network graph in draw_net.py (#6273)
nic25 [Wed, 7 Mar 2018 11:40:52 +0000 (03:40 -0800)]
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.

4 years ago1D blob handling in MSRA/Xavier fillers
Noiredd [Tue, 6 Mar 2018 12:39:49 +0000 (13:39 +0100)]
1D blob handling in MSRA/Xavier fillers

6 years agocheck embed index in debug mode
twmht [Fri, 23 Mar 2018 14:21:06 +0000 (22:21 +0800)]
check embed index in debug mode

6 years agoMerge pull request #6249 from Noiredd/legacy-tools upstream/master-freeze
Przemysław Dolata [Mon, 26 Feb 2018 09:56:10 +0000 (10:56 +0100)]
Merge pull request #6249 from Noiredd/legacy-tools

Remove legacy tools

6 years agoRemove legacy tools
Noiredd [Fri, 23 Feb 2018 13:45:59 +0000 (14:45 +0100)]
Remove legacy tools

6 years agoMerge pull request #6104 from YaYaB/master_bvlc
Przemysław Dolata [Wed, 21 Feb 2018 10:39:39 +0000 (11:39 +0100)]
Merge pull request #6104 from YaYaB/master_bvlc

Check solver gamma and stepsize to avoid unexplained core dump

6 years agoMerge pull request #5149 from yanchen036/master
Przemysław Dolata [Tue, 20 Feb 2018 13:03:14 +0000 (14:03 +0100)]
Merge pull request #5149 from yanchen036/master

fix extension extraction in matchExt

6 years agoMerge pull request #6176 from qu1j0t3/simplify-pip-cmd
Przemysław Dolata [Tue, 20 Feb 2018 12:11:00 +0000 (13:11 +0100)]
Merge pull request #6176 from qu1j0t3/simplify-pip-cmd

Simplify pip requirements installation

6 years agoMerge pull request #6240 from knsong/master
Przemysław Dolata [Tue, 20 Feb 2018 07:31:01 +0000 (08:31 +0100)]
Merge pull request #6240 from knsong/master

Fix filler compatibility for ND convolution

6 years agoFix compatibility for ND convolution
knsong [Sat, 17 Feb 2018 07:56:32 +0000 (15:56 +0800)]
Fix compatibility for ND convolution

6 years agobug fix: ext should not include the '.'
yanchen036 [Mon, 2 Jan 2017 05:33:49 +0000 (13:33 +0800)]
bug fix: ext should not include the '.'

6 years agofix cuda 9.1 compilation
jasjuang [Wed, 14 Feb 2018 00:57:18 +0000 (16:57 -0800)]
fix cuda 9.1 compilation

6 years agoMerge pull request #6123 from IlyaOvodov/master
Przemysław Dolata [Mon, 12 Feb 2018 08:35:27 +0000 (09:35 +0100)]
Merge pull request #6123 from IlyaOvodov/master

"weights" added to solver parameters, "snapshot_prefix" field default initialization

6 years agoAutomatic replacement of snapshot_prefix parameter if it is empty or points to a...
iovodov [Sat, 13 Jan 2018 14:19:45 +0000 (17:19 +0300)]
replacement of snapshot_prefix parameter if it is empty or points to a directory. See issue #6110 proposed improvement No.2

6 years agoWeight parameter in solver is used in caffe.exe
iovodov [Mon, 18 Dec 2017 19:39:03 +0000 (22:39 +0300)]
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

6 years agoFix incorrect namespace for pycaffe submodule caffe_pb2 generated by protobuf
Yegor Bedarev [Thu, 8 Feb 2018 11:05:21 +0000 (18:05 +0700)]
Fix incorrect namespace for pycaffe submodule caffe_pb2 generated by protobuf

6 years agoMerge pull request #5598 from ZoroDerVonCodier/patch-1
Przemysław Dolata [Tue, 6 Feb 2018 07:46:25 +0000 (08:46 +0100)]
Merge pull request #5598 from ZoroDerVonCodier/patch-1

Update euclidean_loss_layer.hpp with corrected reference in comment

6 years agoMerge pull request #6210 from mzsanford/classfier_deprecation_warning
Przemysław Dolata [Sat, 3 Feb 2018 16:41:46 +0000 (17:41 +0100)]
Merge pull request #6210 from mzsanford/classfier_deprecation_warning

Update Classifier and Detector to avoid deprecation warning

6 years agoUpdate Classifier and Detector to avoid deprecation warning
Matt Sanford [Fri, 2 Feb 2018 21:23:23 +0000 (13:23 -0800)]
Update Classifier and Detector to avoid deprecation warning

6 years agoMerge pull request #5545 from brunobowden/shape_mismatch_checks
Przemysław Dolata [Fri, 2 Feb 2018 15:47:46 +0000 (16:47 +0100)]
Merge pull request #5545 from brunobowden/shape_mismatch_checks

Shape mismatch CHECK logging improvements

6 years agocorrected description of set_transpose in io.py
Przemysław Dolata [Thu, 1 Feb 2018 13:43:44 +0000 (14:43 +0100)]
corrected description of set_transpose in io.py

6 years agoMerge pull request #5865 from cheshirekow/fix/caffe_rpath
Przemysław Dolata [Wed, 31 Jan 2018 08:10:34 +0000 (09:10 +0100)]
Merge pull request #5865 from cheshirekow/fix/caffe_rpath

Fix cmake RPATH

6 years agoMerge pull request #6202 from shelhamer/fix-scratch-bottom-diff
Evan Shelhamer [Mon, 29 Jan 2018 19:31:14 +0000 (11:31 -0800)]
Merge pull request #6202 from shelhamer/fix-scratch-bottom-diff

Clear Scratch Diffs to Prevent Contaminating Backward through Splits

6 years agoexplain use of scratch diffs in comments
Evan Shelhamer [Mon, 29 Jan 2018 00:58:39 +0000 (16:58 -0800)]
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.

6 years agoclear scratch use of accuracy bottom diff
Evan Shelhamer [Mon, 29 Jan 2018 00:42:07 +0000 (16:42 -0800)]
clear scratch use of accuracy bottom diff

6 years agoclear scratch use of loss bottom diffs
linziyi [Thu, 18 Jan 2018 19:07:45 +0000 (03:07 +0800)]
clear scratch use of loss bottom diffs

6 years agoMerge pull request #5924 from bowang/cudnn_deconv
Evan Shelhamer [Mon, 29 Jan 2018 00:48:26 +0000 (16:48 -0800)]
Merge pull request #5924 from bowang/cudnn_deconv

speed-up: add cuDNN deconvolution layer and test

6 years agoMerge pull request #6201 from shelhamer/official-aws-ami
Evan Shelhamer [Sun, 28 Jan 2018 00:39:59 +0000 (16:39 -0800)]
Merge pull request #6201 from shelhamer/official-aws-ami

installation: switch pointer to official AWS AMI

6 years agodocs: switch to official AWS AMI
Evan Shelhamer [Sun, 28 Jan 2018 00:37:06 +0000 (16:37 -0800)]
docs: switch to official AWS AMI

6 years agoSimplify pip invocation.
Toby Thain [Mon, 15 Jan 2018 18:16:05 +0000 (13:16 -0500)]
Simplify pip invocation.

6 years agoMerge pull request #6048 from sclarkson/master
Przemysław Dolata [Wed, 10 Jan 2018 19:30:43 +0000 (20:30 +0100)]
Merge pull request #6048 from sclarkson/master

Fix Makefile parallel builds missing protobuf header

6 years agoMerge pull request #6121 from xerus/typo
Przemysław Dolata [Wed, 3 Jan 2018 09:21:03 +0000 (10:21 +0100)]
Merge pull request #6121 from xerus/typo

Cuda.cmake: Fix a typo in a comment

6 years agoCuda.cmake: Fix a typo in a comment
Pavel Grunt [Wed, 20 Dec 2017 12:07:47 +0000 (13:07 +0100)]
Cuda.cmake: Fix a typo in a comment

6 years agoAdd check values of gamma and stepsize to avoid unexplained core dump
YaYaB [Tue, 12 Dec 2017 16:16:59 +0000 (16:16 +0000)]
Add check values of gamma and stepsize to avoid unexplained core dump

6 years agoMerge pull request #6084 from Noiredd/accuracy-count-fix
Przemysław Dolata [Wed, 29 Nov 2017 11:28:31 +0000 (12:28 +0100)]
Merge pull request #6084 from Noiredd/accuracy-count-fix

Added count==0 safeguard to CPU accuracy calculation

6 years agoAdded count==0 safeguard to CPU accuracy calculation
Noiredd [Wed, 29 Nov 2017 10:48:29 +0000 (11:48 +0100)]
Added count==0 safeguard to CPU accuracy calculation

6 years agoMerge pull request #6079 from Noiredd/cuda9-makefile
Przemysław Dolata [Tue, 28 Nov 2017 10:36:47 +0000 (11:36 +0100)]
Merge pull request #6079 from Noiredd/cuda9-makefile

Makefile example comments for CUDA 9.0 compatibility

6 years agoMakefile example comments for CUDA 9.0 compatibility
Noiredd [Tue, 28 Nov 2017 10:00:51 +0000 (11:00 +0100)]
Makefile example comments for CUDA 9.0 compatibility

6 years agoFix Makefile parallel builds missing protobuf header
sclarkson [Sun, 12 Nov 2017 02:20:11 +0000 (18:20 -0800)]
Fix Makefile parallel builds missing protobuf header

6 years agoMerge pull request #5972 from icyblade/icyblade-patch-1
Przemysław Dolata [Tue, 7 Nov 2017 11:56:12 +0000 (12:56 +0100)]
Merge pull request #5972 from icyblade/icyblade-patch-1

add support for cuDNN v7

6 years agoMerge pull request #5719 from leemgs/upstream-issue5718
Przemysław Dolata [Mon, 6 Nov 2017 14:42:07 +0000 (15:42 +0100)]
Merge pull request #5719 from leemgs/upstream-issue5718

Fix: mean shape incompatible with input shape

6 years agoFix: mean shape in compatible with input shape
Geunsik Lim [Thu, 29 Jun 2017 04:12:53 +0000 (13:12 +0900)]
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>
6 years agoMerge pull request #5813 from jqueguiner/patch-1
Przemysław Dolata [Thu, 2 Nov 2017 11:52:30 +0000 (12:52 +0100)]
Merge pull request #5813 from jqueguiner/patch-1

fix web demo install instruction link

6 years agoMerge pull request #5704 from ArneSuppe/dupDistDirFix
Przemysław Dolata [Thu, 2 Nov 2017 11:46:05 +0000 (12:46 +0100)]
Merge pull request #5704 from ArneSuppe/dupDistDirFix

Fixed bug where make distribute duplicates python files

6 years agoMerge pull request #5969 from developius/fix-default-mode-warning
Przemysław Dolata [Thu, 2 Nov 2017 11:34:54 +0000 (12:34 +0100)]
Merge pull request #5969 from developius/fix-default-mode-warning

Fix default mode warning in io.resize_image

6 years agoMerge pull request #5866 from cijianzy/update_link_to_google_style_guide
Przemysław Dolata [Thu, 2 Nov 2017 10:56:53 +0000 (11:56 +0100)]
Merge pull request #5866 from cijianzy/update_link_to_google_style_guide

Update link to google style guide.

6 years agoMerge pull request #5973 from Noiredd/pytest
Przemysław Dolata [Thu, 19 Oct 2017 07:53:59 +0000 (09:53 +0200)]
Merge pull request #5973 from Noiredd/pytest

Add absolute tolerance to test_net.py to prevent random Travis fails

6 years agoinfogain loss: fix bottom blobs description
Mikhail Antonenka [Tue, 17 Oct 2017 15:18:32 +0000 (18:18 +0300)]
infogain loss: fix bottom blobs description

6 years agoMerge pull request #5925 from BVLC/williford-install-ubuntu-16.04-patch-1
Evan Shelhamer [Wed, 11 Oct 2017 17:02:53 +0000 (10:02 -0700)]
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

6 years agoAdd absolute tolerance to test_net.py to prevent random Travis fails
Noiredd [Wed, 11 Oct 2017 09:04:18 +0000 (11:04 +0200)]
Add absolute tolerance to test_net.py to prevent random Travis fails

6 years agoadd supports for cuDNN v7
Icyblade Dai [Wed, 11 Oct 2017 07:29:21 +0000 (15:29 +0800)]
add supports for cuDNN v7

6 years agoupgrading Accuracy layer: (1) efficient CPU implementation O(L) for top_k, no need...
Shai [Thu, 10 Aug 2017 07:07:19 +0000 (10:07 +0300)]
upgrading Accuracy layer: (1) efficient CPU implementation O(L) for top_k, no need for fancy priority_queue etc. (2) GPU implementation

6 years agoFix default mode warning in io.resize_image
Finnian Anderson [Tue, 10 Oct 2017 11:15:13 +0000 (12:15 +0100)]
Fix default mode warning in io.resize_image

Signed-off-by: Finnian Anderson <get@finnian.io>
6 years ago[docs] fix link to `AbsVal` layer
Evan Shelhamer [Tue, 3 Oct 2017 21:20:13 +0000 (14:20 -0700)]
[docs] fix link to `AbsVal` layer

6 years agoMerge pull request #5713 from Noiredd/filler
Evan Shelhamer [Tue, 3 Oct 2017 02:05:50 +0000 (03:05 +0100)]
Merge pull request #5713 from Noiredd/filler

fix bilinear filler (and make constant filler more strict, as it should be)

6 years agoFixed bilinear filler, added tests
Noiredd [Mon, 2 Oct 2017 12:39:31 +0000 (14:39 +0200)]
Fixed bilinear filler, added tests

6 years agoMerge pull request #5904 from longjon/gpu-ptr
Evan Shelhamer [Tue, 19 Sep 2017 11:32:56 +0000 (12:32 +0100)]
Merge pull request #5904 from longjon/gpu-ptr

Expose GPU pointers to Python

6 years agoPackages needed by Ubuntu 16.04 also
Jonathan R. Williford [Fri, 15 Sep 2017 09:38:16 +0000 (11:38 +0200)]
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

6 years agoFix format
Bo Wang [Thu, 14 Sep 2017 22:03:21 +0000 (15:03 -0700)]
Fix format

6 years agoImplement CuDNN-based deconvolution layer and test
Bo Wang [Sun, 10 Sep 2017 04:57:20 +0000 (21:57 -0700)]
Implement CuDNN-based deconvolution layer and test