Evan Shelhamer [Sat, 15 Feb 2014 07:28:26 +0000 (23:28 -0800)]
define by := (no need for re-expansion)
Evan Shelhamer [Sat, 15 Feb 2014 02:14:56 +0000 (18:14 -0800)]
python requirements: don't fear the future
Evan Shelhamer [Fri, 14 Feb 2014 23:40:38 +0000 (15:40 -0800)]
add shebang to python scripts
for executing in the shell without call to python. Follows the example
of @kloudkl .
Evan Shelhamer [Thu, 23 Jan 2014 17:10:44 +0000 (09:10 -0800)]
add macro for numpy < 1.7
as suggested by @longjon
https://github.com/BVLC/caffe/issues/44#issuecomment-
32832810
Yangqing Jia [Thu, 13 Feb 2014 17:56:35 +0000 (09:56 -0800)]
Merge pull request #106 from tdomhan/sigmoidlayer
Sigmoidlayer
Tobias Domhan [Thu, 13 Feb 2014 17:20:27 +0000 (18:20 +0100)]
fixed copyright
Tobias Domhan [Thu, 13 Feb 2014 16:42:21 +0000 (17:42 +0100)]
sigmoid layer cpu and gpu code
Tobias Domhan [Thu, 13 Feb 2014 16:32:18 +0000 (17:32 +0100)]
added sigmoid layer
Evan Shelhamer [Thu, 13 Feb 2014 09:42:22 +0000 (01:42 -0800)]
Merge pull request #104 from sergeyk/master
Groom detection demo notebook, replace gflags with argparse in detector.py
Sergey Karayev [Thu, 13 Feb 2014 09:22:02 +0000 (01:22 -0800)]
selective_search_demo final updated version
Sergey Karayev [Thu, 13 Feb 2014 09:21:43 +0000 (01:21 -0800)]
detector.py refactored with argparse (was gflags)
Sergey Karayev [Thu, 13 Feb 2014 09:03:03 +0000 (01:03 -0800)]
Updated detection demo notebook.
- Works with new detector.py
- Everything is run automatically from cells.
Sergey Karayev [Thu, 13 Feb 2014 07:58:33 +0000 (23:58 -0800)]
git-ignoring ipython notebook checkpoints
Sergey Karayev [Thu, 13 Feb 2014 07:58:21 +0000 (23:58 -0800)]
moving selective_search_demo notebook to examples/
Yangqing Jia [Thu, 13 Feb 2014 06:18:28 +0000 (22:18 -0800)]
Update LICENSE
Removed the FreeBSD disclaimer (which should not be there) per http://opensource.org/licenses/BSD-2-Clause
Yangqing Jia [Thu, 13 Feb 2014 05:59:13 +0000 (21:59 -0800)]
Merge pull request #103 from Yangqing/master
bugfix regarding #100
Yangqing Jia [Thu, 13 Feb 2014 05:52:33 +0000 (21:52 -0800)]
bugfix regarding #100
Yangqing Jia [Thu, 13 Feb 2014 01:31:36 +0000 (17:31 -0800)]
Update net.cpp
Fixed bug raised by @tdomhan in issue #100.
Evan Shelhamer [Wed, 12 Feb 2014 09:34:42 +0000 (01:34 -0800)]
Merge pull request #98 from kloudkl/check_data_size
fix size initialization in convert_imageset
Kai Li [Wed, 12 Feb 2014 08:15:08 +0000 (16:15 +0800)]
Set data_size_initialized to true after data_size is initialized
Evan Shelhamer [Wed, 12 Feb 2014 03:55:41 +0000 (19:55 -0800)]
add CXXFLAGS for libstdc++ on OS X 10.9
Yangqing Jia [Tue, 11 Feb 2014 18:09:59 +0000 (10:09 -0800)]
Merge pull request #94 from kloudkl/image_data_size
Ensure all the images are of the same size before creating leveldb
Kai Li [Tue, 11 Feb 2014 11:39:02 +0000 (19:39 +0800)]
Add script to resize and crop images in parallel using mincepie
Kai Li [Tue, 11 Feb 2014 07:14:11 +0000 (15:14 +0800)]
Check data size when converting images into leveldb
Evan Shelhamer [Tue, 11 Feb 2014 08:41:01 +0000 (00:41 -0800)]
include pip requirements.txt for python deps
Evan Shelhamer [Tue, 11 Feb 2014 04:03:54 +0000 (20:03 -0800)]
Merge pull request #91 from kloudkl/plot_training_log
plot training/test measures against iterations/time
create mnist leveldb as separate script
Kai Li [Tue, 11 Feb 2014 02:59:53 +0000 (10:59 +0800)]
Remove trailing whitespace in example gnuplot script
Kai Li [Tue, 11 Feb 2014 02:54:15 +0000 (10:54 +0800)]
Add python matplotlib example to plot the training log
Kai Li [Tue, 11 Feb 2014 02:48:06 +0000 (10:48 +0800)]
Add gnuplot example to plot the training log
Kai Li [Mon, 10 Feb 2014 08:39:42 +0000 (16:39 +0800)]
Update script to parse log format that contains test iteration
Kai Li [Mon, 10 Feb 2014 08:03:15 +0000 (16:03 +0800)]
Print iteration along with every test score in Solver::Test
Kai Li [Mon, 10 Feb 2014 07:42:37 +0000 (15:42 +0800)]
Extract elapsed seconds since the start of solving from training log
Kai Li [Mon, 10 Feb 2014 06:18:36 +0000 (14:18 +0800)]
Extract learning rate from training log
Evan Shelhamer [Mon, 10 Feb 2014 23:31:59 +0000 (15:31 -0800)]
replace bundled install instructions with link to site
Evan Shelhamer [Mon, 10 Feb 2014 20:56:13 +0000 (12:56 -0800)]
Merge pull request #90 from sguada/parselog
Polish log parsing script
sguada [Sun, 9 Feb 2014 23:46:25 +0000 (15:46 -0800)]
Use sed instead of awk to find the Iteration
Sergio Guadarrama [Sun, 9 Feb 2014 22:08:10 +0000 (14:08 -0800)]
Update parselog.sh
Removed parameters
sguada [Sun, 9 Feb 2014 22:01:14 +0000 (14:01 -0800)]
Extract Iteration from log instead of computing it from parameters
Yangqing Jia [Sun, 9 Feb 2014 17:36:54 +0000 (09:36 -0800)]
Merge pull request #89 from sguada/parselog
Added bash script to parse log
sguada [Sun, 9 Feb 2014 03:46:01 +0000 (19:46 -0800)]
Added bash script to parse log and extract training loss, and test loss and accuracy
Evan Shelhamer [Fri, 7 Feb 2014 20:28:11 +0000 (12:28 -0800)]
Merge pull request #83 from sguada/net_speed
Add benchmarks
sguada [Fri, 7 Feb 2014 17:51:32 +0000 (09:51 -0800)]
More detailed net_speed_benchmark
Zhongwen Xu [Thu, 6 Feb 2014 12:55:40 +0000 (20:55 +0800)]
fix path problem in train_mnist.sh
Evan Shelhamer [Wed, 5 Feb 2014 21:13:12 +0000 (13:13 -0800)]
Merge pull request #70 from petewarden/buffer-overflow
Fix for buffer overflow problem with long filenames when setting up the LevelDB
Jeff Donahue [Wed, 5 Feb 2014 19:19:28 +0000 (11:19 -0800)]
Merge pull request #72 from sguada/solver_device_id
Rename devicequery.cpp to device_query.cpp
Sergio Guadarrama [Wed, 5 Feb 2014 19:09:00 +0000 (11:09 -0800)]
Rename devicequery.cpp to device_query.cpp
Match filename and usage
Pete Warden [Wed, 5 Feb 2014 01:20:57 +0000 (17:20 -0800)]
Fix for buffer overflow problem with long filenames when setting up the LevelDB
Evan Shelhamer [Tue, 4 Feb 2014 19:03:02 +0000 (11:03 -0800)]
Merge pull request #69 from sguada/solver_device_id
set device in solver config
Sergio Guadarrama [Mon, 3 Feb 2014 21:20:05 +0000 (13:20 -0800)]
Update solver.cpp
Added these two conditions before trying SetDevice
param_.solver_mode() && param_.has_device_id()
Sergio Guadarrama [Mon, 3 Feb 2014 21:09:43 +0000 (13:09 -0800)]
Update caffe.proto
Sergio Guadarrama [Mon, 3 Feb 2014 21:07:37 +0000 (13:07 -0800)]
Update devicequery.cpp
Changed Copyright
sguada [Mon, 3 Feb 2014 20:41:55 +0000 (12:41 -0800)]
Added device_query.cpp to examples/ to get basic information about the current GPU device or other device_id
sguada [Mon, 3 Feb 2014 20:40:43 +0000 (12:40 -0800)]
Added device_id to solver.prototxt and to solver.cpp
Evan Shelhamer [Mon, 3 Feb 2014 19:15:10 +0000 (11:15 -0800)]
fix flatten layer backwards to dummy return
Sergey Karayev [Mon, 3 Feb 2014 11:17:53 +0000 (03:17 -0800)]
removing Makefile.config
Sergey Karayev [Mon, 3 Feb 2014 11:14:13 +0000 (03:14 -0800)]
os x installation instructions
Sergey Karayev [Mon, 3 Feb 2014 10:41:44 +0000 (02:41 -0800)]
Makefile.config removed in favor of .example file
with more verbose explanations of paths.
Sergey Karayev [Mon, 3 Feb 2014 10:41:04 +0000 (02:41 -0800)]
remove linking against mkl_intel_thread: unneeded
and gives hard-to-debug errors on os x
Evan Shelhamer [Sat, 1 Feb 2014 03:02:48 +0000 (19:02 -0800)]
Merge pull request #62 from viirya/master
Fix example path + set number of CUDA threads according to architecture
Kai Li [Sun, 12 Jan 2014 07:56:47 +0000 (15:56 +0800)]
Fix test_data_layer segfault by adding destructor to join pthread
Evan Shelhamer [Fri, 31 Jan 2014 10:52:29 +0000 (02:52 -0800)]
note pretrained model licensing: academic / non-commercial use only
Evan Shelhamer [Fri, 31 Jan 2014 07:12:41 +0000 (23:12 -0800)]
read single input, load/save csv, and record windows
Load `--input_file` as a list of image filenames if .txt OR read as CSV
with fields filename,ymin,xmin,ymax,xmax (with labeled header) if .csv.
Save `--output_file` as HDF5 if .h5 or CSV if .csv. For CSV, enumerate
the class probabilities as numbered class fields.
Record crop windows in original image coordinates if `center_only` or
`corners` crop mode selected. Previously, these modes didn't report
locations.
Evan Shelhamer [Fri, 31 Jan 2014 07:26:40 +0000 (23:26 -0800)]
remove outdated reference to input size, debugging print
Liang-Chi Hsieh [Wed, 29 Jan 2014 10:39:16 +0000 (18:39 +0800)]
choose proper thread number per block according to CUDA architecture.
Liang-Chi Hsieh [Wed, 29 Jan 2014 09:37:57 +0000 (17:37 +0800)]
fix program path.
Evan Shelhamer [Wed, 29 Jan 2014 02:09:13 +0000 (18:09 -0800)]
align detector comments to reality
Evan Shelhamer [Tue, 28 Jan 2014 09:59:27 +0000 (01:59 -0800)]
Merge pull request #61 from kloudkl/master
Save the last batch of data in image set conversion
+ comment and output edits
Kai Li [Tue, 28 Jan 2014 07:35:56 +0000 (15:35 +0800)]
Save the last batch of data in image set conversion
Evan Shelhamer [Mon, 27 Jan 2014 23:20:29 +0000 (15:20 -0800)]
detect by window list
Do window detection on a list of predefined windows by adding a
crop_mode `list` that accepts a path to a text file of format:
image_filename xmin ymin xmax ymax
Evan Shelhamer [Mon, 27 Jan 2014 23:17:45 +0000 (15:17 -0800)]
replace magic numbers with variable names in comments
Evan Shelhamer [Sun, 26 Jan 2014 06:33:18 +0000 (22:33 -0800)]
fix ImageNet solver max iteration typo
max iteration no. is 450,000 (= 90 epochs)
caught by @SWu
https://github.com/BVLC/caffe/pull/33#issuecomment-
33175810
Evan Shelhamer [Sun, 26 Jan 2014 04:53:00 +0000 (20:53 -0800)]
automagically set detection batch size from network
Evan Shelhamer [Sun, 26 Jan 2014 03:58:18 +0000 (19:58 -0800)]
document power_wrapper -> detector in detection notebook
Jeff Donahue [Sun, 26 Jan 2014 02:04:56 +0000 (18:04 -0800)]
Merge pull request #56 from shelhamer/detection-wrapper
Make detection module for python wrapper
Evan Shelhamer [Sat, 25 Jan 2014 04:51:00 +0000 (20:51 -0800)]
promote power_wrapper to 'detection' submodule
Evan Shelhamer [Sat, 25 Jan 2014 04:33:24 +0000 (20:33 -0800)]
groom power_wrapper flags (cont'd)
Evan Shelhamer [Sat, 25 Jan 2014 03:31:25 +0000 (19:31 -0800)]
note power_wrapper TODOs
Evan Shelhamer [Sat, 25 Jan 2014 03:26:31 +0000 (19:26 -0800)]
generalize power_wrapper to different networks and inputs
generalize from the imagenet reference to other detection networks:
- refactor to configure for a given net and data source
- determine dimensions of net input and output automatically from blobs
Evan Shelhamer [Sat, 25 Jan 2014 03:24:58 +0000 (19:24 -0800)]
groom power_wrapper flags
Evan Shelhamer [Sat, 25 Jan 2014 01:36:46 +0000 (17:36 -0800)]
python lint
Evan Shelhamer [Sat, 25 Jan 2014 00:18:17 +0000 (16:18 -0800)]
ignore distribute dir
Evan Shelhamer [Fri, 24 Jan 2014 05:15:26 +0000 (21:15 -0800)]
give batch size efficiency advice
Evan Shelhamer [Fri, 24 Jan 2014 05:05:17 +0000 (21:05 -0800)]
default power_wrapper batch size to 10 (
aeca741a69 cont'd)
default command line arg and function arg to 10
remove global BATCH_SIZE in favor of arg
Yangqing Jia [Fri, 24 Jan 2014 02:09:43 +0000 (18:09 -0800)]
Merge pull request #51 from sguada/solver_test
Do snapshot after computing loss and test accuracy
Sergio Guadarrama [Wed, 22 Jan 2014 23:13:22 +0000 (15:13 -0800)]
Do snapshot after computing loss and test accuracy
Evan Shelhamer [Wed, 22 Jan 2014 02:50:07 +0000 (18:50 -0800)]
include install notes
Evan Shelhamer [Wed, 22 Jan 2014 02:37:51 +0000 (18:37 -0800)]
include intro, license, and citing in README
Evan Shelhamer [Tue, 21 Jan 2014 02:24:41 +0000 (18:24 -0800)]
License under BSD
Caffe is henceforth BSD licensed and welcomes community contributions!
Evan Shelhamer [Mon, 20 Jan 2014 05:17:43 +0000 (21:17 -0800)]
Merge pull request #11 from longjon/master
Python interface to blobs and blob data through boost::python
Evan Shelhamer [Sun, 19 Jan 2014 22:34:12 +0000 (14:34 -0800)]
cleanup whitespace
Evan Shelhamer [Sun, 19 Jan 2014 22:10:14 +0000 (14:10 -0800)]
Merge pull request #29 from kloudkl/master
Separate build, distribute, and src directories + build more cuda archs
Evan Shelhamer [Sun, 19 Jan 2014 06:59:33 +0000 (22:59 -0800)]
Merge pull request #34 from forresti/master
set default power_wrapper batch size to match the imagenet_deploy
compatible out-of-the-box with the ipython notebook tutorial
forresti [Wed, 15 Jan 2014 20:02:12 +0000 (12:02 -0800)]
setting default power_wrapper batch size to match the imagenet_deploy prototxt
Jonathan L Long [Tue, 14 Jan 2014 23:44:53 +0000 (15:44 -0800)]
Expose params in Python interface
Jonathan L Long [Sat, 7 Dec 2013 00:39:01 +0000 (16:39 -0800)]
Add Python interface to layer blobs
Kai Li [Mon, 13 Jan 2014 12:42:01 +0000 (20:42 +0800)]
Add removing distribute directory when make clean
Kai Li [Mon, 13 Jan 2014 12:25:30 +0000 (20:25 +0800)]
Add make proto target to seperately generate caffe/proto/caffe.pb.h
issue: #22
Kai Li [Mon, 13 Jan 2014 11:34:34 +0000 (19:34 +0800)]
Seperated build, distribute and source directories
issue: #1
Jeff Donahue [Sun, 22 Dec 2013 21:24:34 +0000 (13:24 -0800)]
Merge pull request #18 from jeffdonahue/bvlc
change imagenet_val batch size from 200 to intended 50
Jeff Donahue [Sun, 22 Dec 2013 21:13:47 +0000 (13:13 -0800)]
change imagenet_val batch size from 200 to intended 50