9f8f7775a8
Finalized tutorial. Removed asyncronous layer.
2016-02-29 19:16:03 -08:00
cf765b983a
Refactor and improve code style.
...
Fix some typos. Correct imports. Refactor data layers. Apply PEP8 formatting.
2016-02-29 19:09:59 -08:00
15a979df45
Added tutorial on how to use python datalayers and multilabel classification.
2016-02-29 19:07:55 -08:00
e5315fe702
Merge pull request #3747 from Nerei/master
...
[pycaffe] NetSpec: set tops by attribute or dictionary
2016-02-29 09:13:01 -08:00
cb277769a4
NetSpec: allow setting blob names by string
2016-02-29 18:01:11 +03:00
c2769c1096
Merge pull request #3725 from shaibagon/drop_nd_blobs
...
supporting N-D Blobs in Dropout layer Reshape
2016-02-28 00:31:17 -08:00
bef2c05d61
supporting N-D Blobs in Dropout layer Reshape
...
fixing lint errors
2016-02-28 08:53:18 +02:00
04aa36e271
Merge pull request #3740 from shelhamer/fix-docker-flags
...
Fix flags for nvidia-docker from #3518
2016-02-27 12:12:24 -08:00
cfa2c0cf59
fix flags in #3518 for nvidia-docker
...
nvidia-docker requires long args with equal sign as of docker 1.10:
see https://github.com/BVLC/caffe/pull/3518#issuecomment-189576419
2016-02-27 12:10:17 -08:00
59d099cba6
Merge pull request #3518 from zalando/feature/docker_images
...
[build] Add docker images for running caffe out-of-the-box (caffe:cpu, caffe:gpu)
2016-02-27 12:08:39 -08:00
6cba462401
Add Dockerfiles for creating Caffe executable images.
...
These can be used as direct replacements for the Caffe executable.
2016-02-27 10:50:28 +01:00
a04ac1124b
Merge pull request #3211 from shelhamer/input-layer
...
Add Input Layer to Replace `input`s
2016-02-26 23:20:39 -08:00
f88073aad8
Deprecate ForwardPrefilled(), Forward(bottom, loss) in lieu of dropping
...
Relax removal of `Forward()` variations by deprecating instead.
2016-02-26 22:37:50 -08:00
2cc3844cb2
[examples] switch examples + models to Input layers
2016-02-25 17:29:42 -08:00
0d9a78f5a0
collect Net inputs from Input layers
...
Restore the list of net inputs for compatibility with the
pycaffe and matcaffe interfaces and downstream C++.
2016-02-25 13:32:54 -08:00
51f79a837d
drop Net inputs + Forward with bottoms
...
Drop special cases for `input` fields, the `Net` input members,
and the `Net` interface for Forward with bottoms along with
Forward() / ForwardPrefilled() distinction.
2016-02-25 13:32:44 -08:00
bddd04b32c
deprecate input fields and upgrade automagically
2016-02-25 13:20:04 -08:00
00598ca84e
add InputLayer for Net input
...
Create an input layer to replace oddball Net `input` fields.
2016-02-25 13:06:24 -08:00
fe0f44112a
Merge pull request #3612 from kashefy/tied_weights_ip_transpose
...
Tied weights with transpose flag for InnerProduct layer
2016-02-25 11:17:19 -08:00
3b2e733f38
Merge pull request #3715 from olesalscheider/master
...
CMake: Do not include "${PROJECT_BINARY_DIR}/include" with SYSTEM option
2016-02-24 23:21:44 -08:00
08766ffa08
Merge pull request #3703 from shaibagon/pycaffe_nd_blobs
...
[pycaffe] make pycaffe support N-D blobs throughout
2016-02-24 17:37:56 -08:00
d392b53018
Merge pull request #3719 from shelhamer/new-tutorial-notebooks
...
[example] Improve Tutorial Notebooks on Classification, Learning LeNet, and Fine-tuning
2016-02-24 16:41:12 -08:00
ca22227089
CMake: Do not include "${PROJECT_BINARY_DIR}/include" with SYSTEM option
...
This is important for the include order. Without this patch, a
previously installed caffe.pb.h might be included instead of the one
that is generated during the build.
2016-02-24 17:00:58 +01:00
08edfddbba
[example] improve brewing logreg notebook
...
- create solvers inline through python protobuf
- drop manually written solver prototxt
- remove ordering prefix, since there is no real sequencing constraint
for this example
2016-02-24 00:35:35 -08:00
9580577804
[example] improve fine-tuning notebook
...
- add headings and text detail
- make nets by net spec
- define solvers inline through python protobuf
- do two-stage fine-tuning (first last layer alone, then end-to-end)
- show sample results
2016-02-24 00:35:34 -08:00
5f50a1f773
[example] improve learning LeNet notebook
...
- add subheadings and list steps for structure
- edit text and comments for clarity
- switch paths and use chdir for idempotency of scripts [shelhamer]
- title accuracy plots, rename ip -> fc to fit common naming, and
rename output layer -> score [shelhamer]
- add experimentation section [shelhamer]
2016-02-24 00:34:26 -08:00
f1d245c78c
[data] get_mnist.sh rewrite; prevents prompt in tutorial notebooks
2016-02-24 00:34:26 -08:00
bd6b03f15e
[example] improve classification notebook
...
- add subheadings and list steps
- edit text, add comments, and try to make the code more understandable
- add new section for summary and encouragement to try your own image
2016-02-24 00:34:25 -08:00
29bb23fc92
removing all references to Blob.num property (that assumes Blob is 4D). Replacing it with accessing Blob.shape[0] - for Blobs with num_axes() != 4
2016-02-23 10:42:54 +02:00
4541f89005
Merge pull request #3696 from shelhamer/fix-osx-install-name
...
fix library install name on OS X for @rpath linking
2016-02-20 22:42:05 -08:00
25baf472e4
Merge pull request #3695 from shelhamer/fix-osx-elcap-cuda-link
...
Fix OS X El Capitan linking for CUDA
2016-02-20 22:39:30 -08:00
dac4d0962d
Fix OSX El Capitan CUDA incompatibility, by adding lib to rpath
2016-02-20 16:25:57 -08:00
b46133aff4
fix library install name on OSX for relative path linking
...
for linking of the caffe tools, tests, etc. the library install name
needs to include the @rpath set for the executables and interfaces
this was broken on OSX by #3311
2016-02-20 15:50:14 -08:00
8f847fa8fa
tranpose parameter added to IP layer to support tied weights in an autoencoder. Arguments to matrix multiplication function are conditioned on this parameter, no actual transposing takes place.
...
test ip gradient computation with transpose on
2016-02-20 15:40:05 +01:00
93e7c195b3
Merge pull request #3676 from flx42/leveldb_include_fix
...
Remove useless LevelDB include
2016-02-17 23:30:12 -08:00
a7b7cf09f5
Merge pull request #3687 from pra85/patch-2
...
Fix a typo in docs
2016-02-17 20:54:02 -08:00
d957481d07
Fix a typo in docs
...
`peformance` → `performance`
2016-02-18 10:13:34 +05:30
8800e4b42d
Remove useless LevelDB include
...
The tests could not compile with USE_LEVELDB=0 and LevelDB missing from the system
2016-02-15 16:52:32 -08:00
0c89b38b14
Merge pull request #3451 from intelcaffe/cmake-clang-fix
...
Fix to cmake build for clang on linux
2016-02-11 13:19:50 -08:00
33f2445b47
Merge pull request #3650 from intbots/cmake-matlab-fix
...
bugfix for incorrect behaviour in `caffe_parse_linker_libs`
2016-02-09 10:27:35 -08:00
68c751c6f7
bugfix for incorrect behaviour in caffe_parse_linker_libs function while extracting libflags from absolute library path with multiple (dots)
2016-02-09 02:45:46 -05:00
b590f1d27e
Merge pull request #3624 from drnikolaev/bvlc-print-gpu-names
...
Nicely prints gpu names
2016-02-02 22:05:07 -08:00
dd2099786f
Nicely prints GPU names
2016-02-02 16:37:14 -08:00
2ef584785c
Merge pull request #3587 from junshi15/distribute_proto
...
Include proto definition in distribute dir
2016-01-29 19:02:45 -08:00
eac9dd8145
Merge pull request #3545 from gdh1995/relative-path-for-soft-links
...
use relative paths on making build/tools/ links
2016-01-29 00:59:23 -08:00
14d0bb4767
use relative paths on making build/tools/ links
...
The old uses `abspath`, which I think is so harmful:
* If I `cp -a` the whole project, `build/tools/caffe` still refer to
the old file, until `make clean`, making debugging very hard
* For `tar` and `scp`, the soft links can not work
unless the target project folder has the same path
2016-01-29 16:10:16 +08:00
5592e59fbf
Merge pull request #2917 from ajkl/patch-2
...
fixing the database param
2016-01-27 10:43:29 -08:00
24f792d104
Merge pull request #3022 from jeffdonahue/expose-param-display-names
...
Net: expose param_display_names_
2016-01-27 10:37:48 -08:00
0acb338b9a
Merge pull request #3605 from jeffdonahue/bias-gemm-type-fix
...
Remove incorrect cast of gemm int arg to Dtype in BiasLayer
2016-01-27 10:34:20 -08:00
afcaf253da
Remove incorrect cast of gemm int arg to Dtype in BiasLayer
2016-01-26 23:09:27 -08:00
Oscar Beijbom
Evan Lezar
Evan Shelhamer
Anatoly Baksheev
Jeff Donahue
shai
Niels Ole Salscheider
Jonathan L Long
Mohamed Ezz
Youssef Kashef
Prayag Verma
Felix Abecassis
Abhijit Kundu
Sergei Nikolaev
gdh1995