microsoft
/
caffe
зеркало из https://github.com/microsoft/caffe.git
1
0
Форкнуть 0
Код Задачи Пакеты Проекты Релизы Вики Активность
1 196 коммитов 3 Ветки 11 Теги 51 MiB
Граф коммитов

1196 Коммитов

Автор SHA1 Сообщение Дата
Evan Shelhamer 2b0087194a reduce example image size 2014-05-22 00:30:12 -07:00
Evan Shelhamer a13e7ee43a Revert "setting canonical random seed" 
1701 is the canonical random seed, and as this test makes only one call
for seeding there's no need for a member var.
 2014-05-20 22:33:29 -07:00
Sergey Karayev efbea35092 Merge pull request #421 from sguada/argmax_layer 2014-05-20 22:13:59 -07:00
Sergey Karayev 4d52ca7df5 setting canonical random seed 2014-05-20 21:48:23 -07:00
Sergey Karayev 0033f9c607 Fixed lint errors due to ArgmaxLayer 2014-05-20 21:32:19 -07:00
Sergey Karayev a31dc6537e Documented ArgMax layer in vision_layers.hpp 2014-05-20 21:32:07 -07:00
Sergey Karayev a3fbe2d666 corrected the caffe.proto ids 2014-05-20 21:25:25 -07:00
Sergio Guadarrama f6c2d933c7 Change ArgMaxLayerParam to ArgMaxParam for consitency 2014-05-20 21:25:25 -07:00
Sergio Guadarrama 766dd362db Change ThresholdLayer to ArgMaxLayer in test_argmax 2014-05-20 21:25:25 -07:00
Sergio Guadarrama 91ab1f684c Fixed name of blob_bottom_ 2014-05-20 21:25:25 -07:00
Sergio Guadarrama d6748cb994 Fixed name of ArgMaxLayerParameter 2014-05-20 21:25:25 -07:00
Sergio Guadarrama aa57dfb84c Added missing ; 2014-05-20 21:25:25 -07:00
Sergio Guadarrama d19c180601 Added FLT_MAX to argmax layer 2014-05-20 21:25:24 -07:00
Sergio Guadarrama bdcd75e487 Fix types of ArgMax Layers params 
Conflicts:

	include/caffe/vision_layers.hpp
	src/caffe/proto/caffe.proto
 2014-05-20 21:25:24 -07:00
Sergio Guadarrama 69dbbc2c04 Fixed numbers in proto and name of ArgMaxParameter 
Conflicts:

	src/caffe/proto/caffe.proto
 2014-05-20 21:25:24 -07:00
Sergio cdebe7a617 Added Test for ArgMax Layer 2014-05-20 21:25:24 -07:00
Sergio Guadarrama 84788c61d7 Added ArgMax Layer 
Conflicts:

	src/caffe/proto/caffe.proto
 2014-05-20 21:25:24 -07:00
Evan Shelhamer c30bb24399 Merge pull request #404 from jeffdonahue/net-param-in-solver 
Specify net params in solver; log {Net,Solver} parameters; multiple test nets
 2014-05-20 15:03:54 -07:00
Evan Shelhamer 5c982ee9c8 link canonical bvlc site 2014-05-20 14:44:52 -07:00
Evan Shelhamer b6da40a57c fix detection notebook link 2014-05-20 14:43:02 -07:00
Evan Shelhamer a34816263c Merge pull request #429 from shelhamer/next 
Next: 0.999
 2014-05-20 14:20:15 -07:00
Evan Shelhamer c6b00a34a1 Back-merge changes in master 
* master:
  bundle presentation in gh-pages for now...
  fix typo pointed out by @yinxusen
  note support for non-MKL installation in dev
  include pretrained snapshot and performance details
  Document AlexNet model, include download script
  define AlexNet architecture
  polished ignore
 2014-05-20 12:44:51 -07:00
Evan Shelhamer f048bea989 Merge pull request #311 from shelhamer/python-fixes 
Improve python wrapper
 2014-05-20 12:20:00 -07:00
Evan Shelhamer 42bf2d2717 update notebook examples with new wrapper usage, re-organize 2014-05-20 12:16:09 -07:00
Evan Shelhamer 8830dc5b81 preprocess single inputs instead of lists 
For compositionality and expectations.
 2014-05-20 11:42:41 -07:00
Evan Shelhamer 02ecf1dacf windowed detection in python 2014-05-20 11:42:41 -07:00
Evan Shelhamer 111df0ecfc squash infuriating loop assignment bug in batching 2014-05-19 23:56:48 -07:00
Evan Shelhamer 2fc32d558a image classification in python 2014-05-19 23:56:48 -07:00
Evan Shelhamer bf4d7262bd fix padding for the last batch 2014-05-19 23:56:16 -07:00
Evan Shelhamer 6b85fd006d split drawnet into module code and script 
Don't run scripts in the module dir to avoid import collisions between
io and caffe.io.
 2014-05-19 23:55:22 -07:00
Evan Shelhamer 50d0b6d9c6 add caffe.io submodule for conversions, image loading and resizing 2014-05-19 23:55:21 -07:00
Evan Shelhamer 738c8758e3 fix python mean subtraction 2014-05-19 23:54:25 -07:00
Sergey Karayev 8534541f1d Merge pull request #376 from sergeyk/layer_reorg 
Layer definitions and declarations re-organization and documentation
 2014-05-19 15:50:33 -07:00
Sergey Karayev c5db25b203 Incorporated Evan’s comments for neuron layers 2014-05-19 11:12:13 -07:00
Sergey Karayev 1b735b5482 Cosmetic change in ConcatLayer 2014-05-19 10:44:21 -07:00
Sergey Karayev efeaf17ba5 Lil’ more docstring, and cosmetic change in EuclideanLossLayer 2014-05-19 10:44:07 -07:00
Sergey Karayev d01c6ed712 fwd/back math docs for neuron layers 2014-05-19 10:39:02 -07:00
Evan Shelhamer 37123a5126 drop cute names in favor of Net.{pre,de}process() for input formatting 
...and refer to inputs as inputs and not images since general vectors
and matrices are perfectly fine.
 2014-05-16 16:10:25 -07:00
Evan Shelhamer 51024131cc Net.caffeinate() and Net.decaffeinate() format/unformat lists 2014-05-16 16:10:25 -07:00
Evan Shelhamer 5d584c27f0 take blob args as ndarrays and assign on the python side 
Take blob args and give blob returns as single ndarrays instead of lists
of arrays.

Assign the net blobs and diffs as needed on the python side, which
reduces copies and simplifies the C++ side of the wrapper.

Thanks @longjon for the suggestion.
 2014-05-16 16:10:25 -07:00
Sergey Karayev 4051cef49e Cosmetic change in prep for data layer work 2014-05-16 10:58:38 -07:00
Sergey Karayev 48a8a64c9b Split all loss layers into own .cpp files 2014-05-16 10:58:38 -07:00
Sergey Karayev 2779ce9e0e layer definition reorganization and documentation 
- split out neuron, loss, and data layers into own header files
- added LossLayer class with common SetUp checks
- in-progress concise documentation of each layer's purpose
 2014-05-16 10:58:38 -07:00
Evan Shelhamer 025c64e71d resize to input dimensions when formatting in python 2014-05-15 13:52:53 -07:00
Evan Shelhamer 459c8c1dac replace iterator with indices for consistency 2014-05-15 13:06:17 -07:00
Evan Shelhamer a7f6750cc3 python style 2014-05-15 12:35:32 -07:00
Evan Shelhamer a3b307a385 fix accidental revert of Init() from f5c28581 2014-05-15 10:20:43 -07:00
Evan Shelhamer 1b23680244 batch inputs in python by forward_all() and forward_backward_all() 2014-05-14 23:48:01 -07:00
Evan Shelhamer 8af33e8ca2 don't squeeze blob arrays for python 
Preserve the non-batch dimensions of blob arrays, even for singletons.

The forward() and backward() helpers take lists of ndarrays instead of a
single ndarray per blob, and lists of ndarrays are likewise returned.

Note that for output the blob array could actually be returned as a
single ndarray instead of a list.
 2014-05-14 20:17:16 -07:00
Evan Shelhamer af0b857d54 python forward() and backward() extract any blobs and diffs 2014-05-14 20:14:55 -07:00