wassname/keras-contrib
1
0
Fork 0
mirror of https://github.com/wassname/keras-contrib.git synced 2026-06-27 16:10:11 +08:00
Code Issues Packages Projects Releases Wiki Activity
227 Commits 12 Branches 0 Tags
6936cf0de733bceac279f02c776cf8c22ed942e2
Commit Graph

227 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Michael Oliver 6936cf0de7 move constraints and initializers 2017-06-15 17:02:49 -07:00
Michael Oliver a42b437423 fix PEP8 2017-06-15 17:00:32 -07:00
Michael Oliver 6bbfdad66d move constraints and initializers 2017-06-15 16:58:33 -07:00
Michael Oliver 5b0a8ca337 fix inits 2017-06-15 16:49:02 -07:00
Ben ef2daecc58 Move activations, metrics, optimizers and regularizers (#94) 2017-06-15 16:15:59 -07:00
Michael Oliver 58a0d51ae6 Fix PEP8 error 2017-06-14 15:04:26 -07:00
jmtatsch 9dbb995cbc future proofing print function (#106) 
for python3
 2017-06-12 17:01:15 +04:00
Fariz Rahman 14d5ba1227 Add cntk backend (#103) 
* add cntk backend

* reorder imports
 2017-06-10 10:05:11 +04:00
Michael Oliver 0f78409087 fix sub_pixel_upscaling test 2017-06-09 09:08:17 -07:00
Michael Oliver 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
Ben 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
Ben f0d7fe852d Make callbacks into a directory. (#91) 2017-06-07 20:48:07 -07:00
Ben ec8010077c Move DSSIMObjective to submodule (#93) 
* Move DSSIMObjective to submodule

* fix losses/dssim_test.py
 2017-06-07 20:47:39 -07:00
Frédéric Branchaud-Charron 3ebf304737 fix dssim, add test (#86) 
* fix dssim, add test

* add more tests
 2017-05-20 15:51:31 -07:00
Andrew Hundt 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
Andrew Hundt 61e65f6d7b coco.py mscoco dataset support (#81) 
* coco.py initial implementation

* coco.py pep8 fixes
 2017-05-20 14:13:58 -07:00
Eric Xihui Lin 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
nzw 8a91b3a40e Ignore .DS_Store file (#68) 
- remove .DS_Store files
- Update .gitignore
 2017-05-06 20:12:39 +05:30
Michael Oliver 2b62fb2030 Fix batchnorm axis specification for Theano 
Batchnorm on correct axis for Theano
 2017-05-02 22:07:52 -07:00
Eric Xihui Lin fc1ff55507 changed to use up2date tensorflow (#79) 2017-05-02 22:01:19 -07:00
Michael Oliver f79f4a55c9 bug fixs for theano compatibility 2017-04-28 18:23:56 -07:00
Michael Oliver 2d56791066 Update improved_wgan.py 
Correctly sets the gradient_penalty hyperparameter to match the paper…
 2017-04-25 16:17:01 -07:00
Matt ccc1be8857 Adds improved_wgan.py to examples (#75) 
* Added improved_wgan.py to examples

Implements the improved WGAN with gradient penalty in Keras.

* Fixed PEP8 issues and one docstring mistake.

* Added a note to the discriminator to avoid BatchNormalization, as per the paper.

* Minor docstring correction to clarify description for wasserstein_loss function.

* Fixed a missing line in the generator

* Minor cleanup to make generating the label vectors a bit more elegant.

* Fixing typo in previous commit.

* Moved the model out of a main() function. Model now correctly respects
keras.backend.image_data_format

* Aaaand another PEP8 cleanup >.>

* Gradient penalty is now correctly based on the gradient w.r.t. the input averaged samples, rather than the weights of the discriminator.

* Gradient is now correctly calculated on the output of the discriminator, not the
K.mean() of the output (i.e. the loss).
 2017-04-24 23:38:03 -07:00
Michael Oliver 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
Tron a7520c8f52 Mod: Changes one line to fix the Deconvolution3D's error (#73) 2017-04-21 15:48:51 -07:00
DNGros fe227a0803 Fix keras argument spelling error in densenet.py (#74) 
It looks like in 1d57dd3c63 a spelling error ("kenel" not "kernal") was introduced into densenet.py that causes an argument error from keras when trying to use the network. This pull request corrects that.
 2017-04-21 15:48:13 -07:00
Somshubra Majumdar 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
Somshubra Majumdar 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
nzw 88c60d2459 Style fixes (#71) 2017-04-15 09:41:28 -07:00
Michael Oliver 2afcddffd8 Use theano release rather than bleeding edge (#72) 
To match Keras tests
 2017-04-15 09:38:58 -07:00
nzw 3b528baf46 Fix README for keras 2 (#70) 2017-04-15 17:35:58 +05:30
Anthony 4d33b69fd8 updated TF backend - redundant line in deconv3d causing errors (#67) 2017-04-11 23:08:42 -07:00
Junwei Pan d83277f683 Merge pull request #62 from kemaswill/FitExamplesAndApplicationsToKeras-220170331 
Fit examples and applications to keras-2
 2017-04-11 08:44:17 -07:00
Junwei Pan 3c1594b967 Fix examples and applications to keras-2 2017-04-11 08:03:40 -07:00
Michael Oliver db019c6034 PELU fixes and upgrade 2017-04-06 15:23:16 -07:00
Fariz Rahman d81887a6e0 Bug fix : Deconv3D 2017-04-07 02:53:57 +05:30
Fariz Rahman 671ca018a9 pep8 fix 2017-04-07 02:48:37 +05:30
Fariz Rahman d6d72aaad3 pep8 fix 2017-04-07 02:47:00 +05:30
Fariz Rahman 8491f9271e pep8 fix 2017-04-07 02:42:38 +05:30
Fariz Rahman b10fbfbc05 Update GUIDELINES.md 2017-04-06 22:29:13 +05:30
Armen c0ceaf02fe Implemented convolution aware initialization (#60) 
* Implemented convolution aware initialization

* added support for conv3d in the CAI scheme

* added tests for convolution aware initialization
 2017-04-06 08:20:15 -07:00
t.ae 52ebe4e7d5 Improve depth_to_space (#58) 
* Add `test_depth_to_space`

* Fix bug and refine `KCTH.depth_to_space`

* Remove extra blank lines
 2017-04-04 13:58:52 -07:00
t.ae 17cb8cce0c Fix: Namings in test_convolutional.py (#57) 2017-04-04 17:41:16 +05:30
Thomas Boquet 2b77a35fb0 Merge pull request #61 from ahundt/pep8 
test_convolutional.py pep8 compliance
 2017-04-01 09:51:13 -04:00
Andrew Hundt 116626c695 test_convolutional.py pep8 compliance 2017-03-30 22:39:42 -04:00
Junwei Pan fcd054fe40 Fit DenseNet examples to Keras-2 (#53) 
Update DenseNet example to K2

* Fit DenseNet examples to keras-2
 2017-03-29 01:55:43 +05:30
Abhai Kollara Dilip 531c4dcab8 Fixes in tests and TF backend (#49) 
* Fix tests

* Fix extract_image_patches on TF backend

* Fix tests

* Fix extract_image_patches on TF backend

* Fix in conv2d TF backend
 2017-03-20 03:12:34 +05:30
Fariz Rahman 2e3a752d8c Merge pull request #50 from tboquet/doc_clean 
Fix doc style in DSSIM objective
 2017-03-20 02:52:11 +05:30
tboquet 399fbe82bc * fix doc style 2017-03-19 13:43:50 -04:00
farizrahman4u c23d3540f3 nb->num 2017-03-19 22:39:10 +05:30