d1d93dc | Graham Neubig | 22 April 2018, 02:57:29 UTC | Fixed batched matmul | 22 April 2018, 02:57:29 UTC |
c9c715d | Graham Neubig | 21 April 2018, 04:47:30 UTC | Added batched matrix multiplies on CUDA | 21 April 2018, 04:47:30 UTC |
a98db69 | Antonio Zhang | 20 April 2018, 13:09:48 UTC | Add function of topk. (#1328) | 20 April 2018, 13:09:48 UTC |
68bcc02 | Paul Michel | 20 April 2018, 12:49:49 UTC | Add the update flag back to Parameter.expr (#1353) * Add the update flag back to Parameter.expr * Clarify documentation | 20 April 2018, 12:49:49 UTC |
ddbf560 | Paul Michel | 18 April 2018, 15:26:49 UTC | Update init.cc | 18 April 2018, 15:26:49 UTC |
a5c959a | Paul Michel | 18 April 2018, 05:23:16 UTC | First commit (#1351) | 18 April 2018, 05:23:16 UTC |
a90dcc2 | Graham Neubig | 17 April 2018, 15:30:07 UTC | Upgrade eigen instructions (#1347) * Autobatching improvement for LSTM, addition for transpose * Upgraded Eigen version to fix CUDA9.1 compile | 17 April 2018, 15:30:07 UTC |
0eddde2 | Hao Zhang | 08 April 2018, 03:09:05 UTC | remove grid search functionality * Update readme.md * This is the commit message #3: * update README * add performance test * tffold single cpu time test | 11 April 2018, 18:00:51 UTC |
2bbc0b9 | zhiyong1997 | 17 March 2018, 02:21:07 UTC | Tree-LSTM example * re structure codes and add some other features. Purely tune on dev, test acc 0.498 * add readme * fix readme * update readme * time calc * fix some code quality problems * remove idea/ * fix static method bug and some others | 11 April 2018, 18:00:45 UTC |
e72ca35 | Arne Köhn | 06 April 2018, 16:22:12 UTC | Python example fixes (#1340) * update jupyter xor example to python3 - print() - no more dy.parameter() - use as dy.[...] package * RNN jupyter updated & converted to python3 The old code did not correspond to the output. An LSTM with two layers is unable to learn the given sequence in the given number of steps. Other changes: - Output prettified - no weight-sharing between lstm and rnn output layer | 06 April 2018, 16:22:12 UTC |
f906f14 | Graham Neubig | 06 April 2018, 16:21:08 UTC | Added autobatching for dropout (#1341) | 06 April 2018, 16:21:08 UTC |
4e68164 | Pengzhi Gao | 06 April 2018, 15:52:30 UTC | MNIST Benchmarks (#1334) * Rename README.md to README1.md * Rename examples/mnist/README1.md to examples/mnist/basic-mnist-benchmarks/README.md * Update README.md * Update README.md * Add files via upload * Update README.md * Update README.md * Update README.md * Add files via upload * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Update README.md * Delete mnist_pytorch.py * Add files via upload * Update README.md * Update README.md * Update mnist_pytorch.py * Update README.md * Update README.md * Update mnist_dynet_autobatch.py * Update mnist_dynet_minibatch.py * Update mnist_pytorch.py * Update mnist_dynet_minibatch.py * Update mnist_dynet_autobatch.py | 06 April 2018, 15:52:30 UTC |
857144a | Austin Matthews | 04 April 2018, 17:12:27 UTC | Merge branch 'master' of https://github.com/clab/dynet | 04 April 2018, 17:12:27 UTC |
0c23251 | Austin Matthews | 04 April 2018, 17:12:18 UTC | clean up message queues better in mp.h | 04 April 2018, 17:12:18 UTC |
348ca39 | YovaKem | 04 April 2018, 12:55:55 UTC | fixed time and word per sec reported in validation step (#1338) | 04 April 2018, 12:55:55 UTC |
20fd674 | Arne Köhn | 30 March 2018, 13:01:32 UTC | Swig fixes (#1331) * Fix swig bindings - move dynet::detail to expr.h so swig bindings can use it - two small fixes (include nodes.h, drop default parameter) * swig example: set learning rate instead of updateEpoch | 30 March 2018, 13:01:32 UTC |
060f451 | Hong Wu | 28 March 2018, 15:35:24 UTC | dynet-1320. Add / support for cdiv. (#1321) * dynet-1320. Add / support for cdiv. * comment typo fix | 28 March 2018, 15:35:24 UTC |
a3d2a4c | Graham Neubig | 26 March 2018, 17:09:48 UTC | Autobatching improvement for LSTM, addition for transpose (#1326) | 26 March 2018, 17:09:48 UTC |
d69bdc1 | Graham Neubig | 23 March 2018, 14:01:32 UTC | Fixed directions on README | 23 March 2018, 14:01:32 UTC |
967d545 | Graham Neubig | 23 March 2018, 13:26:37 UTC | Update to doc | 23 March 2018, 13:26:37 UTC |
568c45f | Hong Wu | 23 March 2018, 03:35:30 UTC | Fix arguments for flip_gradient in py (#1319) | 23 March 2018, 03:35:30 UTC |
d0f40f2 | Liang Zhang | 23 March 2018, 01:19:40 UTC | Update _dynet.pyx (#1318) Correct a minor typo in the python dynet.cg_version() documentatoin | 23 March 2018, 01:19:40 UTC |
6e394e7 | Hong Wu | 16 March 2018, 00:37:25 UTC | Fix HuberDistance::backward_dev_impl and log sigmoid doc. (#1311) | 16 March 2018, 00:37:25 UTC |
7c9b185 | Peng Wu | 15 March 2018, 23:26:53 UTC | vae examples and benchmarks vs pytorch (#1289) (#1307) | 15 March 2018, 23:26:53 UTC |
8a60b20 | Hong Wu | 15 March 2018, 22:28:50 UTC | hotfix | 15 March 2018, 22:28:50 UTC |
52a2cae | Zhechen Yan | 15 March 2018, 21:25:26 UTC | fix huber_distance error (#1310) * Fix huber_distance bug and make expression readable | 15 March 2018, 21:25:26 UTC |
689d16e | Hong Wu | 15 March 2018, 01:50:39 UTC | Dynet 1296. cuRAND support for multiple GPUs. (#1304) * dynet-1296. curand support for multi GPU. * add curandeng control inside GPU device * clean up global curandeng. * fix macro | 15 March 2018, 01:50:39 UTC |
9d2f668 | Hong Wu | 15 March 2018, 01:49:27 UTC | Fix current version (#1301) | 15 March 2018, 01:49:27 UTC |
df0cf07 | Hong Wu | 15 March 2018, 01:48:51 UTC | fix file permissions (#1303) | 15 March 2018, 01:48:51 UTC |
f7be0c2 | Hong Wu | 14 March 2018, 14:30:40 UTC | dynet-1298. Add ** support for pow op. (#1300) * dynet-1298. Add expr ** 2 and expr ** expr(not elementwise) support in python layer. * dynet-1298. Update pow description in _dynet.pyx | 14 March 2018, 14:30:40 UTC |
58b552b | Chris Dyer | 12 March 2018, 17:10:57 UTC | backward can throw, prevent Python from crashing | 12 March 2018, 17:10:57 UTC |
d060d11 | <pmichel31415@gmail.com> | 08 March 2018, 20:00:39 UTC | Put Expressions above Parameters | 08 March 2018, 20:00:39 UTC |
d1e8736 | Paul Michel | 08 March 2018, 19:40:56 UTC | Attempts to fix documentation Distinguishes between multiline strings and comments | 08 March 2018, 19:40:56 UTC |
75b7942 | Chris Dyer | 08 March 2018, 17:35:55 UTC | Merge pull request #1233 from clab/param_expression [WIP] simplify Parameters in python | 08 March 2018, 17:35:55 UTC |
18ed6b7 | Paul Michel | 02 March 2018, 23:34:00 UTC | Merge pull request #1270 from jkkummerfeld/master Fixing equation mistake in documentation | 02 March 2018, 23:34:00 UTC |
5bb84d0 | Jonathan Kummerfeld | 02 March 2018, 22:39:20 UTC | Fixing equation mistake in documentation | 02 March 2018, 22:39:20 UTC |
2090525 | yoavg | 01 March 2018, 15:00:53 UTC | Fixed deprecation message. | 01 March 2018, 15:00:53 UTC |
f170e71 | Chris Dyer | 27 February 2018, 14:40:14 UTC | get rid of dy.parameter calls | 27 February 2018, 14:40:14 UTC |
2848388 | Graham Neubig | 25 February 2018, 17:12:16 UTC | Fixed corner case in autobatched exec (#1258) | 25 February 2018, 17:12:16 UTC |
c5420a5 | Graham Neubig | 23 February 2018, 16:10:52 UTC | Fix broken thing (#1257) | 23 February 2018, 16:10:52 UTC |
ef144c4 | shuheik | 23 February 2018, 15:03:56 UTC | softmax with optional dimension (#1253) | 23 February 2018, 15:03:56 UTC |
d28490c | Franck | 23 February 2018, 15:03:30 UTC | Added missing header files to CMakeLists.txt so that 'make install' takes them into account (#1252) | 23 February 2018, 15:03:30 UTC |
fbdef46 | Daniel Hershcovich | 23 February 2018, 15:03:07 UTC | Informative message when checking Cython version fails (#1251) Will help with issues such as #548 | 23 February 2018, 15:03:07 UTC |
fbd343c | Paul Michel | 23 February 2018, 15:02:27 UTC | first try (#1250) | 23 February 2018, 15:02:27 UTC |
1001a44 | Graham Neubig | 23 February 2018, 15:01:49 UTC | Check for empty lists in function calls (#1249) | 23 February 2018, 15:01:49 UTC |
02d8259 | Paul Michel | 23 February 2018, 14:55:01 UTC | Syntactic sugar for parameter initializers (#894) * Syntactic sugar for parameter initializers Former-commit-id: ab9de114cbac34cc8f9cf087d4ae4fca86ca46cc * Fix python 3 strings Former-commit-id: 5dbf73b6beb5f7f97a9a68d9265e0c11452ab3f3 * Fix numpy initialization for lookup parameters Former-commit-id: 0a5f0a425050dfb7b066cd0b41dde792049cc214 * Add example in API tutorial Former-commit-id: cecd5c998c01fe10939f77b295315bb80e032057 * Make interface consistent | 23 February 2018, 14:55:01 UTC |
96ef893 | Yoav Goldberg | 16 February 2018, 16:45:11 UTC | Exposing weight-decay-lambda through parameter collection. (#1242) * Exposing weight-decay-lambda through parameter collection. * weight decay inherited from parent model | 16 February 2018, 16:45:11 UTC |
878897c | yoavg | 13 February 2018, 08:40:15 UTC | apply also to LookupParameters. | 13 February 2018, 08:40:15 UTC |
bea27f5 | yoavg | 12 February 2018, 17:00:02 UTC | Merge branch 'master' into param_expression | 12 February 2018, 17:00:02 UTC |
35f917f | yoavg | 09 February 2018, 23:10:35 UTC | addo some type info | 09 February 2018, 23:10:35 UTC |
bae1fe7 | yoavg | 09 February 2018, 22:03:48 UTC | fix typo | 09 February 2018, 22:03:48 UTC |
7cb6455 | Graham Neubig | 09 February 2018, 21:54:04 UTC | Added mention of binary distribution (#1234) | 09 February 2018, 21:54:04 UTC |
f76bdd9 | yoavg | 09 February 2018, 21:34:28 UTC | small fix in const_parameter. | 09 February 2018, 21:34:28 UTC |
2d702d5 | yoavg | 09 February 2018, 21:29:59 UTC | less annoying deprecation warning. | 09 February 2018, 21:29:59 UTC |
93f4ac6 | yoavg | 09 February 2018, 21:01:44 UTC | simplified back into the Parameters class only. | 09 February 2018, 21:07:00 UTC |
b71039a | yoavg | 09 February 2018, 20:10:13 UTC | parameter-expression working | 09 February 2018, 21:06:59 UTC |
c59bca9 | yoavg | 09 February 2018, 15:39:03 UTC | in progress | 09 February 2018, 21:06:59 UTC |
8462813 | draplater | 09 February 2018, 17:20:15 UTC | autobatch for conv2d (#1216) * autobatch for conv2d * Fixed random normal and made mean/stddev an option (#1220) * Argmax and straight-through estimator (#1208) * Initial argmax * Add missing file * Python implementation of argmax * straight-through * Use as_vector * Fixed on GPU * Change API * add __gitversion__ info to python build (#1229) * Added unit test | 09 February 2018, 17:20:15 UTC |
e7ad9b8 | Paul Michel | 09 February 2018, 17:19:50 UTC | Add cumulative sum operation (#1012) * Add cumsum operation with tests and doc Former-commit-id: a44bc03df6d269ab96dd5835467d26690d442cf4 * Add missing file and more explicit docs Former-commit-id: 4c38e6086ff733d8482169a0e9175c5306474e48 * Fix cmakelist for gpu Former-commit-id: 655240b0705414d66bf7418c69ca5aacae197592 * Check whether the issue comes from reverse On gpu Former-commit-id: 4938cb16f59d4a96d0fdf966d429b4a040577c49 * With scratch memory * Attempt to upgrade version of Eigen | 09 February 2018, 17:19:50 UTC |
0b1adce | Paul Michel | 09 February 2018, 16:50:07 UTC | Add AMSGrad to the python doc | 09 February 2018, 16:50:07 UTC |
0e5addb | Paul Michel | 09 February 2018, 16:00:04 UTC | Log sigmoid (#1224) * Log sigmoid * Fix on GPU (I think) * Second try * Use 32-bit functions in simd-functors | 09 February 2018, 16:00:04 UTC |
8ea37f6 | Yoav Goldberg | 09 February 2018, 15:54:47 UTC | fix initializing RNN state with given expressions (#1228) | 09 February 2018, 15:54:47 UTC |
d1c58a9 | Yoav Goldberg | 09 February 2018, 13:54:27 UTC | add __gitversion__ info to python build (#1229) | 09 February 2018, 13:54:27 UTC |
598906c | Paul Michel | 07 February 2018, 22:57:33 UTC | Argmax and straight-through estimator (#1208) * Initial argmax * Add missing file * Python implementation of argmax * straight-through * Use as_vector * Fixed on GPU * Change API | 07 February 2018, 22:57:33 UTC |
850c4c8 | Graham Neubig | 05 February 2018, 15:43:32 UTC | Fixed random normal and made mean/stddev an option (#1220) | 05 February 2018, 15:43:32 UTC |
5309f11 | Matt Richardson | 02 February 2018, 16:27:59 UTC | MSVC fixes (#1215) * template keyword required for compilation in MSVC. * std::iota needs #include <numeric> * Change to cross-platform getpid.h * Transformer example depends on Boost, only compile if boost enabled. * Moving curand library to top level so it is linked in python build as well | 02 February 2018, 16:27:59 UTC |
375afbb | Chris Dyer | 30 January 2018, 20:32:23 UTC | fix conflicts with GPU specification using new style parameters | 30 January 2018, 20:32:23 UTC |
ebddcb9 | Chris Dyer | 30 January 2018, 18:43:01 UTC | Allow --dynet_flag=arg argument format | 30 January 2018, 18:43:01 UTC |
936a494 | Hong Wu | 29 January 2018, 16:08:38 UTC | dynet-1201. Fix weight decay load issue. (#1206) * dynet-1201. Fix weight decay load issue. * dynet-1201. Add TestIOPartialWeightDecay in test.py. * add check for as_scale_vector | 29 January 2018, 16:08:38 UTC |
2329b88 | Paul Michel | 29 January 2018, 15:53:14 UTC | 1st attempt at SIMD sigmoid (#1200) * 1st attempt at SIMD sigmoid * Don't use fmin/fmax | 29 January 2018, 15:53:14 UTC |
6190925 | msperber | 29 January 2018, 15:44:07 UTC | Faster inputTensor() (#1194) * implemented a first faster version of inputTensor() * some more improvements * comments * fix negative indexing | 29 January 2018, 15:44:07 UTC |
50e48b9 | Vu Cong Duy Hoang | 29 January 2018, 15:41:42 UTC | Transformer example in C++ (#1186) * fixed a bug of dim in select_cols * corrected typo in concatenate's doc * added impl. for TensorTools::access_element() * added transformer example * added wrap-data script for transformer | 29 January 2018, 15:41:42 UTC |
ebd96d4 | Daniel Hershcovich | 29 January 2018, 13:35:23 UTC | Save/load with generators in Python API (#1180) * Add load_generator to Python API Same as load(), but the parameters are returned as a generator instead of a list. This allows saving memory or even showing a progress bar while loading the parameters. Example: import dynet as dy from tqdm import tqdm pc = dy.ParameterCollection() W = pc.add_parameters((100,50)) E = pc.add_lookup_parameters((1000,50)) builder = dy.LSTMBuilder(2, 50, 50, pc) dy.save("model", tqdm((E, builder, W), unit="param")) # then, when loading: pc = dy.ParameterCollection() E2, builder2, W2 = tqdm(dy.load_generator("model", pc), unit="param") * Test save/load with generators in Python API * Add informative messages to assertions in Python | 29 January 2018, 13:35:23 UTC |
b0037ff | Hong Wu | 24 January 2018, 15:36:10 UTC | dynet-1202. Fix lookup parameter updated bug when set_updated(False). (#1203) * dynet-1202. Fix lookup parameter updated bug when set_updated(False). * Test that set_updated(False) in Python works | 24 January 2018, 15:36:10 UTC |
151f7d7 | Dr. Kashif Rasul | 24 January 2018, 14:54:27 UTC | initial amsgrad implementation (#1185) * initial amsgrad implementation * added tests * added python binding * added swig definition and scala helpers | 24 January 2018, 14:54:27 UTC |
0d1037b | yanaiela | 24 January 2018, 14:52:27 UTC | customable flip gradient option: C++ and python support (#1158) * customable flip gradient option: C++ and python support * Refactoring to allow scaling | 24 January 2018, 14:52:27 UTC |
d0176db | Graham Neubig | 24 January 2018, 14:52:02 UTC | cuRAND support (#1154) * Initial pass at cublas * Added uniform distribution * Added bernoulli | 24 January 2018, 14:52:02 UTC |
210d6b9 | Chris Dyer | 23 January 2018, 12:25:22 UTC | use ptrdiff_t as index type in Eigen | 23 January 2018, 12:25:22 UTC |
e8a144a | Paul Michel | 22 January 2018, 17:31:26 UTC | Merge pull request #1197 from AmitMY/patch-1 docs(API): use dynet method not global | 22 January 2018, 17:31:26 UTC |
ca0f264 | Amit Moryossef | 20 January 2018, 08:46:05 UTC | docs(API): use dynet method not global | 20 January 2018, 08:46:05 UTC |
95145a3 | Paul Michel | 19 January 2018, 16:20:42 UTC | fix code formatting in installation instructions | 19 January 2018, 16:20:42 UTC |
6ae942d | Paul Michel | 18 January 2018, 17:09:09 UTC | Merge pull request #1159 from tohtsky/master Implementing dropout for SimpleRNNBuilder | 18 January 2018, 17:09:09 UTC |
65bd7d8 | ootsuki_t | 18 January 2018, 02:54:48 UTC | added ``virtual`` specifiers for set_dropout(float d) and disable_dropout() | 18 January 2018, 02:54:48 UTC |
77c1672 | Graham Neubig | 17 January 2018, 21:56:59 UTC | Fixed errors on mac by removing "auto" calls (#1191) | 17 January 2018, 21:56:59 UTC |
0eeb191 | Yuval Pinter | 17 January 2018, 20:48:15 UTC | Added `Trainer.set_learning_rate()` #695 (#1176) | 17 January 2018, 20:48:15 UTC |
1790a40 | Hong Wu | 16 January 2018, 14:34:55 UTC | dynet-1187. Add python tests for dynet IO. (#1189) | 16 January 2018, 14:34:55 UTC |
80ca8ec | Vered Shwartz | 16 January 2018, 14:33:15 UTC | Remove the string requirement from the arguments of Parameters.populate_from_textfile, for compatibility with python 3 (#1188) | 16 January 2018, 14:33:15 UTC |
df20bc0 | Chris Dyer | 11 January 2018, 13:53:13 UTC | remove dead code, speed improvements on CPU | 11 January 2018, 13:53:13 UTC |
a5d4834 | Chris Dyer | 11 January 2018, 12:03:48 UTC | add comment about GPU impl of FFT | 11 January 2018, 12:03:48 UTC |
f0e42ec | Chris Dyer | 11 January 2018, 11:09:47 UTC | remove logging message | 11 January 2018, 11:09:47 UTC |
2eafde5 | Graham Neubig | 11 January 2018, 07:00:57 UTC | Support for in-place operations (#1156) * Some partial supports for READ-only inplaced operations. Sharing memories for Reshape(f/b), NoBackprop(f), FlipGradient(f). * Fixed broken assert code * Fix over-aggressive assert * Some fixes to backward checks * Fix exec.cc * Fixed messages * Removed extra message | 11 January 2018, 07:00:57 UTC |
a094a59 | msperber | 10 January 2018, 10:58:50 UTC | Expose set_weight_decay_lambda() to Python (#1173) * initial commit * update doc | 10 January 2018, 10:58:50 UTC |
7d9031c | Tomoki Ohtsuki | 07 January 2018, 04:59:38 UTC | Merge branch 'master' of https://github.com/tohtsky/dynet | 07 January 2018, 04:59:38 UTC |
c1cb5a6 | Tomoki Ohtsuki | 07 January 2018, 04:56:30 UTC | Revert GRUBuilder, modified DYNET_ARG_CHECK in set_dropout | 07 January 2018, 04:56:30 UTC |
67dccd9 | Tomoki Ohtsuki | 07 January 2018, 02:58:31 UTC | 1. Allowed separate dropout ratios for internal & input connections in SimpleRNNBuilder 2. Python bindings. | 07 January 2018, 02:58:31 UTC |
e2b858a | ootsuki_t | 25 December 2017, 05:27:14 UTC | fix indent | 25 December 2017, 05:27:14 UTC |
e6d3ca4 | Tomoki Ohtsuki | 25 December 2017, 01:42:36 UTC | GRU dropout following variational RNN. | 25 December 2017, 01:42:36 UTC |
a2c90aa | Tomoki Ohtsuki | 24 December 2017, 13:36:17 UTC | Removed overlapping in codes and added documentation for dropout implementation | 24 December 2017, 13:36:17 UTC |
79134c3 | Tomoki Ohtsuki | 24 December 2017, 13:18:36 UTC | Attempting to implement dropout for SimpleRNNBuilder | 24 December 2017, 13:18:36 UTC |
2faafe9 | Daniel Hershcovich | 23 December 2017, 10:38:01 UTC | Separate sdist to another job, fix version in setup.py (#1155) | 23 December 2017, 10:38:00 UTC |