0fa8ab5 | Jean Kossaifi | 06 August 2019, 17:16:06 UTC | Upload only once | 06 August 2019, 17:16:06 UTC |
c66c52e | Jean Kossaifi | 06 August 2019, 16:57:05 UTC | Use Travis to deploy to Pypi | 06 August 2019, 16:57:05 UTC |
44e3c07 | Jean Kossaifi | 06 August 2019, 16:11:53 UTC | Added test case for rank-1 CP decomposition | 06 August 2019, 16:11:53 UTC |
7636ad6 | Jean Kossaifi | 06 August 2019, 16:11:41 UTC | Tensorflow backend: update solve | 06 August 2019, 16:11:41 UTC |
ec215f5 | Jean Kossaifi | 06 August 2019, 15:41:15 UTC | Tensorflow backend: minor update Use tf.linalg.qr instead of the (deprecated) tf.qr | 06 August 2019, 15:41:15 UTC |
0b6eb27 | Jean Kossaifi | 06 August 2019, 14:16:26 UTC | Satisfy pydata sparse.. | 06 August 2019, 14:16:26 UTC |
ccbe247 | Jean Kossaifi | 06 August 2019, 14:05:08 UTC | Satisfy tensorflow... | 06 August 2019, 14:05:08 UTC |
26034e1 | Jean Kossaifi | 06 August 2019, 13:56:23 UTC | MXNet specific fix | 06 August 2019, 13:56:23 UTC |
e8ac360 | Jean Kossaifi | 06 August 2019, 13:52:24 UTC | Update | 06 August 2019, 13:52:24 UTC |
14ec121 | Jean Kossaifi | 06 August 2019, 13:44:36 UTC | FIX kruskal_norm | 06 August 2019, 13:44:36 UTC |
2bb3e8c | Jean Kossaifi | 06 August 2019, 13:04:20 UTC | Update tol | 06 August 2019, 13:04:20 UTC |
6782b4c | Jean Kossaifi | 06 August 2019, 13:00:48 UTC | Minor change in tensorflow backend | 06 August 2019, 13:00:48 UTC |
0965ef2 | Jean Kossaifi | 06 August 2019, 13:00:18 UTC | Updated version of Python used for tests | 06 August 2019, 13:00:18 UTC |
90c3745 | Jean Kossaifi | 06 August 2019, 12:59:52 UTC | FIX: kruskal normalise | 06 August 2019, 12:59:52 UTC |
d64eb49 | Jean Kossaifi | 06 August 2019, 12:41:32 UTC | FIX: kruskal normalisation + rec error estimation | 06 August 2019, 12:41:32 UTC |
56ad880 | Jean Kossaifi | 06 August 2019, 12:41:16 UTC | Adds outer-product | 06 August 2019, 12:41:16 UTC |
d4fca6a | Jean Kossaifi | 05 August 2019, 09:15:08 UTC | Merge pull request #123 from kingsj0405/feature/issue#122 Use UTF-8 encoding | 05 August 2019, 09:15:08 UTC |
8329b4f | kingsj0405 | 01 August 2019, 19:24:28 UTC | Use UTF-8 encoding | 01 August 2019, 19:24:28 UTC |
1fadece | Jean Kossaifi | 26 July 2019, 19:53:19 UTC | Add back mask to kruskal_to_tensor | 26 July 2019, 19:53:19 UTC |
02f084a | Jean Kossaifi | 26 July 2019, 19:52:30 UTC | Test for correctness of weights for Kruskal tensor | 26 July 2019, 19:52:30 UTC |
929a1fd | Jean Kossaifi | 26 July 2019, 19:52:00 UTC | Added diag to backend | 26 July 2019, 19:52:00 UTC |
28086e9 | Jean Kossaifi | 13 June 2019, 11:21:00 UTC | sparse DOC: kruskal_tensors have weights | 13 June 2019, 11:21:00 UTC |
4bfad4d | Jean Kossaifi | 13 June 2019, 11:17:34 UTC | Update sparse DOC | 13 June 2019, 11:17:34 UTC |
fd4b6f3 | Jean Kossaifi | 13 June 2019, 11:13:06 UTC | Add sparse functions to API | 13 June 2019, 11:13:06 UTC |
a8391c5 | Jean Kossaifi | 04 June 2019, 23:00:13 UTC | Merge branch 'master' of https://github.com/tensorly/tensorly | 04 June 2019, 23:00:13 UTC |
9ba7294 | Jean Kossaifi | 04 June 2019, 22:59:48 UTC | FIX: orthogonalisation | 04 June 2019, 22:59:48 UTC |
696aa5d | Jean Kossaifi | 31 May 2019, 09:41:45 UTC | FIX: use _get_backend_method in dispatch | 31 May 2019, 09:41:45 UTC |
6b46712 | Jean Kossaifi | 13 May 2019, 23:08:18 UTC | DOC: update for tucker tensor syntax + update API | 13 May 2019, 23:08:18 UTC |
47063bc | Jean Kossaifi | 13 May 2019, 22:51:08 UTC | Update to Tucker tensor as tuples | 13 May 2019, 22:51:08 UTC |
7349038 | Jean Kossaifi | 01 May 2019, 12:01:28 UTC | Merge pull request #87 from JeanKossaifi/tensor-classes Adding a KruskalTensor class and enforces that kruskal tensors (e.g. tensors decomposed with Parafac) should always be expressed as mappings (tuple like) object of the form (weights, factor_list). It also adds various function to check the validity of input decomposed tensors (CP, Tucker and MPS) and efficient operations on decomposed tensors. | 01 May 2019, 12:01:28 UTC |
31f025a | Jean Kossaifi | 23 April 2019, 16:37:23 UTC | FIX precision for multi-mode-dot tests | 23 April 2019, 16:37:23 UTC |
1779931 | Jean Kossaifi | 23 April 2019, 15:31:24 UTC | FIX: typos/non-tensorly tensor | 23 April 2019, 15:31:24 UTC |
86bd4ae | Jean Kossaifi | 23 April 2019, 15:30:58 UTC | Added tucker_mode_dot n-mode-product between Tucker tensor and matrix/vector | 23 April 2019, 15:30:58 UTC |
71fd23b | Jean Kossaifi | 23 April 2019, 15:23:56 UTC | Added MPS tensor validation | 23 April 2019, 15:23:56 UTC |
5de19fa | Jean Kossaifi | 23 April 2019, 15:12:29 UTC | Add tucker_tensor validation | 23 April 2019, 15:12:29 UTC |
99572fe | Jean Kossaifi | 23 April 2019, 13:35:47 UTC | FIX kruskal_tensor for sparse_backend Always carry weights around, e.g. kruskal_tensor = (weights, factors) always | 23 April 2019, 13:35:47 UTC |
b1f9077 | Jean Kossaifi | 23 April 2019, 13:28:48 UTC | FIX kruskal_tensor Now kruskal_tensor should always be (weights, factors) | 23 April 2019, 13:28:48 UTC |
47028b7 | Jean Kossaifi | 22 April 2019, 17:07:29 UTC | Merge branch 'master' into tensor-classes | 22 April 2019, 17:07:29 UTC |
ce9cfaa | Jean Kossaifi | 18 April 2019, 14:11:50 UTC | Merge branch 'master' of https://github.com/tensorly/tensorly | 18 April 2019, 14:11:50 UTC |
5ec54f4 | Jean Kossaifi | 18 April 2019, 13:48:43 UTC | nn-tucker: FIX when only one mode provided | 18 April 2019, 13:48:43 UTC |
82831d8 | Jean Kossaifi | 15 April 2019, 09:14:03 UTC | Merge pull request #90 from Quansight/sparse-robust-pca Sparse robust pca | 15 April 2019, 09:14:03 UTC |
bbc9141 | Jean Kossaifi | 15 April 2019, 08:51:20 UTC | Minor refactor: svd_thresholding always returns a tensor | 15 April 2019, 08:51:20 UTC |
4a64976 | Jean Kossaifi | 11 April 2019, 16:28:48 UTC | Merge branch 'master' into sparse-robust-pca | 11 April 2019, 16:28:48 UTC |
d329bac | Jean Kossaifi | 10 April 2019, 21:51:29 UTC | Merge branch 'master' of https://github.com/tensorly/tensorly | 10 April 2019, 21:51:29 UTC |
3699d2d | Jean Kossaifi | 10 April 2019, 21:50:51 UTC | FIX README: sparse SVD fails on int array... | 10 April 2019, 21:50:51 UTC |
58d6e34 | Jean Kossaifi | 10 April 2019, 12:11:10 UTC | Merge pull request #107 from JeanKossaifi/Quansight-sparse-docs Add sparse docs | 10 April 2019, 12:11:10 UTC |
74ed476 | Jean Kossaifi | 10 April 2019, 12:00:05 UTC | Update sparse documentation. | 10 April 2019, 12:00:05 UTC |
65250b8 | Jean Kossaifi | 10 April 2019, 11:21:27 UTC | Merge branch 'sparse-docs' of git://github.com/Quansight/tensorly into Quansight-sparse-docs | 10 April 2019, 11:21:27 UTC |
3909404 | Jean Kossaifi | 05 April 2019, 10:51:50 UTC | Merge pull request #105 from JeanKossaifi/sparse-missing-values Sparse missing values for PARAFAC | 05 April 2019, 10:51:50 UTC |
82175d1 | Jean Kossaifi | 05 April 2019, 10:51:36 UTC | Merge branch 'master' into sparse-missing-values | 05 April 2019, 10:51:36 UTC |
39c1f27 | Jean Kossaifi | 05 April 2019, 10:47:27 UTC | Added reference | 05 April 2019, 10:47:27 UTC |
b201b5a | Jean Kossaifi | 03 April 2019, 11:00:07 UTC | Merge pull request #106 from JeanKossaifi/maximeguillaud-master Support for complex tensors in CP | 03 April 2019, 11:00:07 UTC |
8d8f035 | Jean Kossaifi | 31 March 2019, 00:09:32 UTC | Support for complex tensors in PARAFAC | 31 March 2019, 00:09:32 UTC |
12748bf | Jean Kossaifi | 31 March 2019, 00:09:27 UTC | Merge branch 'master' of git://github.com/maximeguillaud/tensorly into maximeguillaud-master | 31 March 2019, 00:09:27 UTC |
52b4ed1 | Jean Kossaifi | 29 March 2019, 20:15:42 UTC | Updated README | 29 March 2019, 20:15:42 UTC |
2a95291 | Jean Kossaifi | 29 March 2019, 20:14:27 UTC | Updated README Update tensorly paper reference. | 29 March 2019, 20:14:27 UTC |
0bd6e88 | Jean Kossaifi | 26 March 2019, 23:14:37 UTC | More efficient kruskal_to_tensor | 26 March 2019, 23:14:37 UTC |
a0bde0d | Jean Kossaifi | 26 March 2019, 23:14:11 UTC | Readibility of khatri-rao | 26 March 2019, 23:14:11 UTC |
429b4a7 | Aaron Meurer | 12 March 2019, 18:04:29 UTC | Use tl.kruskal_to_tensor Also remove an unused import. | 12 March 2019, 18:04:29 UTC |
d541246 | Aaron Meurer | 12 March 2019, 17:59:13 UTC | Merge branch 'master' into sparse-parafac-missing | 12 March 2019, 17:59:13 UTC |
d0976b2 | Jean Kossaifi | 12 March 2019, 11:10:40 UTC | Merge pull request #102 from JeanKossaifi/sparse_parafac Adding sparse parafac | 12 March 2019, 11:10:40 UTC |
7d60391 | Jean Kossaifi | 11 March 2019, 20:17:48 UTC | Added test for sparse parafac | 11 March 2019, 20:17:48 UTC |
61ea788 | Jean Kossaifi | 11 March 2019, 12:37:50 UTC | Tests for sparse tenalg | 11 March 2019, 12:37:50 UTC |
8a89e6a | Jean Kossaifi | 11 March 2019, 12:23:18 UTC | TYPO | 11 March 2019, 12:23:18 UTC |
dddc4ed | Jean Kossaifi | 11 March 2019, 12:19:43 UTC | Update Travis + test for sparse with numpy | 11 March 2019, 12:19:43 UTC |
85bab72 | Jean Kossaifi | 10 March 2019, 19:44:02 UTC | Sparse: minor refactor + test tenalg | 10 March 2019, 19:44:02 UTC |
181f83e | Jean Kossaifi | 10 March 2019, 19:00:45 UTC | Adding unfolding_dot_khatri_rao test + misc * wrap unfolding_dot_khatri_rao for sparse * added email for asmeurer | 10 March 2019, 19:00:45 UTC |
8ec55ae | Jean Kossaifi | 07 March 2019, 22:18:24 UTC | Remove unused variable | 07 March 2019, 22:18:24 UTC |
44d7608 | Jean Kossaifi | 07 March 2019, 22:17:44 UTC | Update authors list | 07 March 2019, 22:17:44 UTC |
ab257e6 | Jean Kossaifi | 07 March 2019, 22:09:16 UTC | Refactor mttkrp | 07 March 2019, 22:09:16 UTC |
4996a23 | Jean Kossaifi | 26 February 2019, 14:02:08 UTC | Merge branch 'sparse-parafac' of git://github.com/Quansight/tensorly into sparse_parafac | 26 February 2019, 14:02:08 UTC |
8206345 | Aaron Meurer | 21 February 2019, 02:28:13 UTC | Use tl.shape instead of tensor.shape | 21 February 2019, 02:28:13 UTC |
5d6290b | Aaron Meurer | 21 February 2019, 02:18:18 UTC | Use tl.reshape instead of tensor.reshape | 21 February 2019, 02:18:18 UTC |
d7f320a | Aaron Meurer | 20 February 2019, 23:48:46 UTC | More efficient mttkrp in parafac() It now computes along all ranks at once, while still computing in such a way so as to be sparse-safe (it does not create the full Khatri-Rao as an intermediate array). This is about 3x faster. | 21 February 2019, 00:05:32 UTC |
80e17b5 | Jean Kossaifi | 20 February 2019, 23:54:34 UTC | FIX: sparse imports | 20 February 2019, 23:54:34 UTC |
69db31b | Aaron Meurer | 20 February 2019, 19:16:45 UTC | Fix dot in the numpy backend It must use a.dot(b) for the numpy backend parafac to work properly with sparse inputs. | 20 February 2019, 19:16:45 UTC |
26ce3d1 | Aaron Meurer | 18 February 2019, 19:01:54 UTC | Use direct slicing instead of reshape to create a new axis | 18 February 2019, 19:01:54 UTC |
b491ef1 | Jean Kossaifi | 11 February 2019, 22:57:30 UTC | Merge branch 'sparse-parafac' of git://github.com/Quansight/tensorly into Quansight-sparse-parafac | 11 February 2019, 22:57:30 UTC |
1d54a35 | Aaron Meurer | 11 February 2019, 21:27:36 UTC | Use transpose directly instead of moveaxis in the mttkrp This provides a slight performance improvement. | 11 February 2019, 21:27:36 UTC |
ad0c2a6 | Jean Kossaifi | 06 February 2019, 12:50:37 UTC | FIX for solve in PyTorch backend | 06 February 2019, 12:50:37 UTC |
ddc74bf | Aaron Meurer | 05 February 2019, 20:01:33 UTC | Remove duplicate stack definition | 05 February 2019, 20:01:33 UTC |
cd88d3f | Aaron Meurer | 05 February 2019, 19:45:23 UTC | Fix issues with mxnet backend Some custom methods were not being used because of a bad merge conflict resolution. | 05 February 2019, 19:45:23 UTC |
bbe5336 | Aaron Meurer | 05 February 2019, 18:24:32 UTC | Merge branch 'master' into sparse-parafac | 05 February 2019, 18:24:32 UTC |
2d56a42 | Jean Kossaifi | 05 February 2019, 18:18:43 UTC | Merge pull request #95 from JeanKossaifi/backend-manager Backend refactor + sparse support for numpy | 05 February 2019, 18:18:43 UTC |
114e663 | Jean Kossaifi | 01 February 2019, 15:11:57 UTC | Test backend: remove needless try | 01 February 2019, 15:11:57 UTC |
6fd2894 | Jean Kossaifi | 30 January 2019, 23:58:40 UTC | Add back dynamical dispatch for backend methods Also bump version | 30 January 2019, 23:58:40 UTC |
d4da362 | Maxime Guillaud | 24 January 2019, 19:47:58 UTC | Make parafac() robust to complex tensors | 24 January 2019, 19:47:58 UTC |
99f2d6a | Jean Kossaifi | 14 January 2019, 15:55:22 UTC | FIX sparse backend | 14 January 2019, 15:55:22 UTC |
87dc6d7 | Maxime Guillaud | 13 January 2019, 09:03:09 UTC | Make norm() from numpy backend robust to complex tensors | 13 January 2019, 09:03:09 UTC |
b742c47 | Jean Kossaifi | 10 January 2019, 20:44:06 UTC | FIX contraction tests | 10 January 2019, 20:44:06 UTC |
478d832 | Jean Kossaifi | 10 January 2019, 18:01:10 UTC | Fix the sparse backend | 10 January 2019, 18:01:10 UTC |
c10f44e | Jean Kossaifi | 08 January 2019, 21:55:22 UTC | Merge branch 'master' into backend-manager | 08 January 2019, 21:55:22 UTC |
e1361b8 | Jean Kossaifi | 08 January 2019, 15:55:14 UTC | FIX: forgotten backend registration | 08 January 2019, 15:55:14 UTC |
591f5b7 | Jean Kossaifi | 02 January 2019, 16:16:11 UTC | Revert to functions | 02 January 2019, 16:16:11 UTC |
91f85a5 | Jean Kossaifi | 28 December 2018, 12:10:37 UTC | Refactor + Thread Local + context manager | 28 December 2018, 12:10:37 UTC |
7e69725 | Jean Kossaifi | 25 December 2018, 21:57:43 UTC | update | 25 December 2018, 21:57:43 UTC |
247917c | Jean Kossaifi | 23 December 2018, 23:37:01 UTC | TYPO | 23 December 2018, 23:37:01 UTC |
f04806e | Jean Kossaifi | 23 December 2018, 23:32:26 UTC | MXNET: fix reshape with empty shape | 23 December 2018, 23:32:26 UTC |
05b6b2f | Jean Kossaifi | 23 December 2018, 23:13:49 UTC | Adds tensor contraction | 23 December 2018, 23:13:49 UTC |
3580c8f | Jean Kossaifi | 23 December 2018, 20:57:48 UTC | BackendManager draft | 23 December 2018, 20:57:48 UTC |