Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Support for sparse computations and sparse neural network layers with (custom) Caffe #142

Merged
merged 9 commits into from
Jul 4, 2016
Merged

Support for sparse computations and sparse neural network layers with (custom) Caffe #142

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
9fe3c0d
first working sparse computations on text with Caffe as backend
beniz May 31, 2016
13e3aed
Merge branch 'master' into sparse_112
beniz Jun 6, 2016
9108620
fixed makefile typo
beniz Jun 6, 2016
1b723fd
support for sparse logistic regression + unit test
beniz Jun 6, 2016
7b556f8
multi-target objective + sparse inputs cannot be accomodated together…
beniz Jun 6, 2016
208cd71
svm file format support + working in-memory CPU Caffe models from API…
beniz Jun 10, 2016
e3669f0
added first pass on svm file to get max index
beniz Jun 14, 2016
b240095
full svm support + sparse + fixes
beniz Jun 22, 2016
f2e9acb
updated makefiles, readme and logistic regression weight decay before…
beniz Jul 4, 2016
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,7 +72,7 @@ else()
caffe_dd
PREFIX caffe_dd
INSTALL_DIR ${CMAKE_BINARY_DIR}
URL https://github.com/beniz/caffe/archive/master_dd_integ.tar.gz
URL https://github.com/beniz/caffe/archive/master.tar.gz
CONFIGURE_COMMAND ln -sf Makefile.config.gpu.cudnn Makefile.config && echo "OPENCV_VERSION:=${OPENCV_VERSION}" >> Makefile.config && make -j${N}
INSTALL_COMMAND ""
BUILD_IN_SOURCE 1
Expand All @@ -82,7 +82,7 @@ ExternalProject_Add(
caffe_dd
PREFIX caffe_dd
INSTALL_DIR ${CMAKE_BINARY_DIR}
URL https://github.com/beniz/caffe/archive/master_dd_integ.tar.gz
URL https://github.com/beniz/caffe/archive/master.tar.gz
CONFIGURE_COMMAND ln -sf Makefile.config.gpu Makefile.config && echo "OPENCV_VERSION:=${OPENCV_VERSION}" >> Makefile.config && make -j${N}
INSTALL_COMMAND ""
BUILD_IN_SOURCE 1
Expand All @@ -93,7 +93,7 @@ ExternalProject_Add(
caffe_dd
PREFIX caffe_dd
INSTALL_DIR ${CMAKE_BINARY_DIR}
URL https://github.com/beniz/caffe/archive/master_dd_integ.tar.gz
URL https://github.com/beniz/caffe/archive/master.tar.gz
CONFIGURE_COMMAND ln -sf Makefile.config.cpu Makefile.config && echo "OPENCV_VERSION:=${OPENCV_VERSION}" >> Makefile.config && make -j${N}
INSTALL_COMMAND ""
BUILD_IN_SOURCE 1
Expand Down
3 changes: 2 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,7 @@ Current features include:
- no database dependency and sync, all information and model parameters organized and available from the filesystem
- flexible template output format to simplify connection to external applications
- templates for the most useful neural architectures (e.g. Googlenet, Alexnet, ResNet, convnet, character-based convnet, mlp, logistic regression)
- support for sparse features and computations on both GPU and CPU

##### Documentation

Expand Down Expand Up @@ -79,7 +80,7 @@ None outside of C++ compiler and make

##### Caffe version

By default DeepDetect automatically relies on a modified version of Caffe, https://github.com/beniz/caffe/tree/master_dd_integ
By default DeepDetect automatically relies on a modified version of Caffe, https://github.com/beniz/caffe/tree/master

##### Implementation

Expand Down
3 changes: 1 addition & 2 deletions src/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,9 +3,8 @@ if (NOT CUDA_FOUND)
add_definitions(-DCPU_ONLY)
endif()

set(ddetect_SOURCES deepdetect.h deepdetect.cc caffelib.h caffelib.cc mllibstrategy.h mlmodel.h mlservice.h caffemodel.h caffemodel.cc inputconnectorstrategy.h imginputfileconn.h csvinputfileconn.h csvinputfileconn.cc txtinputfileconn.h txtinputfileconn.cc caffeinputconns.h caffeinputconns.cc commandlineapi.h commandlineapi.cc commandlinejsonapi.h commandlinejsonapi.cc apidata.h apidata.cc jsonapi.h jsonapi.cc httpjsonapi.cc httpjsonapi.h ext/rmustache/mustache.h ext/rmustache/mustache.cc)
set(ddetect_SOURCES deepdetect.h deepdetect.cc caffelib.h caffelib.cc mllibstrategy.h mlmodel.h mlservice.h caffemodel.h caffemodel.cc inputconnectorstrategy.h imginputfileconn.h csvinputfileconn.h csvinputfileconn.cc svminputfileconn.h svminputfileconn.cc txtinputfileconn.h txtinputfileconn.cc caffeinputconns.h caffeinputconns.cc commandlineapi.h commandlineapi.cc commandlinejsonapi.h commandlinejsonapi.cc apidata.h apidata.cc jsonapi.h jsonapi.cc httpjsonapi.cc httpjsonapi.h ext/rmustache/mustache.h ext/rmustache/mustache.cc)

#add_library(ddetect deepdetect.h deepdetect.cc caffelib.h caffelib.cc mllibstrategy.h mlmodel.h mlservice.h caffemodel.h caffemodel.cc inputconnectorstrategy.h imginputfileconn.h csvinputfileconn.h csvinputfileconn.cc txtinputfileconn.h txtinputfileconn.cc caffeinputconns.h caffeinputconns.cc commandlineapi.h commandlineapi.cc commandlinejsonapi.h commandlinejsonapi.cc apidata.h apidata.cc jsonapi.h jsonapi.cc httpjsonapi.cc httpjsonapi.h ext/rmustache/mustache.h ext/rmustache/mustache.cc)
if (USE_XGBOOST)
list(APPEND ddetect_SOURCES xgblib.cc xgblib.h xgbmodel.cc xgbmodel.h xgbinputconns.cc xgbinputconns.h)
endif()
Expand Down
Loading