821eff3948
fix normalization tests
2017-09-22 13:14:15 -05:00
ff47da56fb
Merge branch 'master' of https://github.com/titu1994/keras-contrib
2017-09-08 11:28:05 -05:00
99c0c4b2d2
Remove dropout weight check
2017-09-08 11:27:56 -05:00
b185d2655b
densenet.py add name scope
2017-09-08 10:18:34 -04:00
72f6ca1716
Update MD5 for weights
2017-09-07 08:50:05 -05:00
5c6fd53a33
Fixed an incorrect passing of the dataformat to _preproce_input
2017-09-06 21:39:24 -05:00
5bef6b9e52
Apply corrections
2017-09-06 21:33:24 -05:00
7bae1db1f2
Update DenseNet with ImageNet weights and major code cleanup
2017-09-06 13:01:50 -05:00
156c7e8e24
Correct dense connectivity in DenseNet
2017-09-01 18:14:24 -05:00
c4d1a61746
fix missing paren
2017-08-16 21:01:26 -07:00
4ae3058c92
change np.exp to K.exp ( #128 )
...
* change np.exp to K.exp
To address https://github.com/farizrahman4u/keras-contrib/issues/127
* Update normalization.py
* Updates as suggested
2017-08-16 20:56:03 -07:00
5aed16cadc
Update ftml for Keras changes to optimizers ( #137 )
...
* Update ftml for Keras changes to optimizers
* fix import
2017-08-16 20:51:32 -07:00
157aa46f5a
Fix typo 'tf' -> 'channels_last' ( #135 )
2017-08-16 17:48:37 -07:00
13ec4b4174
Added Dead ReLU detector callback ( #115 )
2017-06-30 15:08:39 -10:00
8ec9c77382
Fix Pascal VOC installation for Python 3 ( #114 )
2017-06-21 09:42:47 -07:00
ee6c396475
pascal_voc.py fix runtime errors ( #112 )
...
* pascal_voc.py fix runtime errors
* Fix PEP8
2017-06-19 15:25:57 -07:00
f0bb5becbb
Instance Normalization layer ( #101 )
...
* Instance Normalization layer
* fix Instance Normalization for theano broadcasting rules
* Support rank 1 tensor in Instance Normalization
* address issue with axis parameter in instance normalization and add unit test for per channel correctness
* avoid assert_raises in normalization unit test
* Instance normalization set axis default to None
2017-06-19 08:57:54 -07:00
0b7eafa922
fix PEP8
2017-06-16 15:04:31 -07:00
ef6c770639
add tests for ftml
...
add missing self.epsilon to ftml
2017-06-16 13:20:09 -07:00
b5669f4100
Fix training difficulty for DenseNetFCN ( #96 )
2017-06-16 11:29:20 -07:00
ebd568283a
FTML optimizer ( #110 )
...
* add ftml.py and fix __init__.py
* fix PEP8
2017-06-16 11:28:43 -07:00
a466050b5b
add clip alias to correct place
2017-06-15 17:36:12 -07:00
cd0af91219
fix imports
2017-06-15 17:20:58 -07:00
6936cf0de7
move constraints and initializers
2017-06-15 17:02:49 -07:00
a42b437423
fix PEP8
2017-06-15 17:00:32 -07:00
6bbfdad66d
move constraints and initializers
2017-06-15 16:58:33 -07:00
5b0a8ca337
fix inits
2017-06-15 16:49:02 -07:00
ef2daecc58
Move activations, metrics, optimizers and regularizers ( #94 )
2017-06-15 16:15:59 -07:00
58a0d51ae6
Fix PEP8 error
2017-06-14 15:04:26 -07:00
9dbb995cbc
future proofing print function ( #106 )
...
for python3
2017-06-12 17:01:15 +04:00
14d5ba1227
Add cntk backend ( #103 )
...
* add cntk backend
* reorder imports
2017-06-10 10:05:11 +04:00
0182528dd2
Fix DSSIM definition ( #99 )
...
* Fix DSSIM definition
Fix covariance definition:
https://github.com/fchollet/keras/issues/4292#issuecomment-306976842
* second fix
* fix PEP8 error
2017-06-09 08:19:41 -07:00
4f619fa686
save_all_weights and load_all_weights ( #90 )
...
* save_all_weights and load_all_weights
* doc updates, fix test, remove .gitkeep
2017-06-07 20:59:48 -07:00
f0d7fe852d
Make callbacks into a directory. ( #91 )
2017-06-07 20:48:07 -07:00
ec8010077c
Move DSSIMObjective to submodule ( #93 )
...
* Move DSSIMObjective to submodule
* fix losses/dssim_test.py
2017-06-07 20:47:39 -07:00
3ebf304737
fix dssim, add test ( #86 )
...
* fix dssim, add test
* add more tests
2017-05-20 15:51:31 -07:00
a9905f1085
pascal_voc.py pascal voc 2012 dataset support ( #80 )
...
* pascal_voc.py initial implementation
* pascal_voc.py pep8
2017-05-20 14:14:18 -07:00
61e65f6d7b
coco.py mscoco dataset support ( #81 )
...
* coco.py initial implementation
* coco.py pep8 fixes
2017-05-20 14:13:58 -07:00
d1f4b6ba75
CRF for keras 2.x ( #76 )
...
* implemented CRF
* added test for CRF
* added a chunking example for CRF
* changed to use up2date tensorflow
* added conll2000 data
* minimize package dependency
* using logsumexp in keras instead
2017-05-18 10:28:17 -07:00
8a91b3a40e
Ignore .DS_Store file ( #68 )
...
- remove .DS_Store files
- Update .gitignore
2017-05-06 20:12:39 +05:30
692e8a5aef
Add SReLU activation function ( #77 )
...
* add srelu activation
* update srelu style
* make srelu and pelu work with any initializer
* add missing config line
* make initializations better match paper
2017-04-24 13:26:27 -07:00
a7520c8f52
Mod: Changes one line to fix the Deconvolution3D's error ( #73 )
2017-04-21 15:48:51 -07:00
fe227a0803
Fix keras argument spelling error in densenet.py ( #74 )
...
It looks like in 1d57dd3c63
2017-04-21 15:48:13 -07:00
1d57dd3c63
[Bugfix] Corrects activation for DenseNetFCNs ( #55 )
...
* Bugfix for DenseNetFCN + Activation parameter + revert to Keras 1 model
* Correct ordering of parameters (input_shape) for DenseNet models
* Updated to Keras 2 API
* Changed image_dim_ordering to image_data_format
* Corrected "th" to channels_first and "tf" to channels_last
* Fixed " to '
* PEP 8 fixes
* Fix PEP 8 again
2017-04-15 10:18:10 -07:00
8ef69698b8
Update BatchRenorm to Keras 2 API ( #69 )
...
* Update BatchRenorm to Keras 2 API
* update tests
* Remove mode 1 test (mode 1 doesnt exist anymore)
2017-04-15 09:43:55 -07:00
88c60d2459
Style fixes ( #71 )
2017-04-15 09:41:28 -07:00
4d33b69fd8
updated TF backend - redundant line in deconv3d causing errors ( #67 )
2017-04-11 23:08:42 -07:00
3c1594b967
Fix examples and applications to keras-2
2017-04-11 08:03:40 -07:00
db019c6034
PELU fixes and upgrade
2017-04-06 15:23:16 -07:00
d81887a6e0
Bug fix : Deconv3D
2017-04-07 02:53:57 +05:30
Somshubra Majumdar