Commit Graph

2201 Commits

Author SHA1 Message Date
William Falcon 94da5431cd using slurm flag to fine node nb 2019-07-08 14:01:59 -04:00
William Falcon 63c113d55b using slurm flag to fine node nb 2019-07-08 14:00:17 -04:00
William Falcon 2261eaac2e using slurm flag to fine node nb 2019-07-08 13:56:20 -04:00
William Falcon fac98e0846 using slurm flag to fine node nb 2019-07-08 13:51:04 -04:00
William Falcon 52a3c3137a using slurm flag to fine node nb 2019-07-08 13:48:59 -04:00
William Falcon 660b966a8f added multi-node locked ip search 2019-07-08 13:04:52 -04:00
William Falcon ae0b85f235 added multi-node locked ip search 2019-07-08 13:01:38 -04:00
William Falcon a83d00456b added multi-node locked ip search 2019-07-08 12:59:10 -04:00
William Falcon c0e3cb784a added multi-node locked ip search 2019-07-08 12:58:47 -04:00
William Falcon 615711131e added multi-node locked ip search 2019-07-08 12:54:20 -04:00
William Falcon c2987d3b40 added multi-node locked ip search 2019-07-08 12:51:07 -04:00
William Falcon f4ab46e1c9 added multi-node locked ip search 2019-07-08 12:45:20 -04:00
William Falcon 6462cab351 added multi-node locked ip search 2019-07-08 12:39:49 -04:00
William Falcon 6a1199b797 added multi-node locked ip search 2019-07-08 12:32:48 -04:00
William Falcon 212eabf626 added multi-node locked ip search 2019-07-08 12:30:38 -04:00
William Falcon fd194ab843 added multi-node locked ip search 2019-07-08 12:27:53 -04:00
William Falcon b563cfe598 testing slurm ddp 2019-07-08 11:48:28 -04:00
William Falcon 770aff5fc7 testing slurm ddp 2019-07-08 11:32:01 -04:00
William Falcon ae0349d449 testing slurm ddp 2019-07-08 10:30:55 -04:00
William Falcon cdbbf9abe3 moved cuda flags inside trainer 2019-07-08 10:00:04 -04:00
William Falcon 79ca5f6265 moved cuda flags inside trainer 2019-07-08 09:58:43 -04:00
William Falcon f5a87c5016 moved cuda flags inside trainer 2019-07-08 09:58:01 -04:00
William Falcon 523cc9f2be added multi-node proc 0 ip reading 2019-07-08 09:50:45 -04:00
William Falcon ef530af7b8 added multi-node proc 0 ip reading 2019-07-08 09:45:43 -04:00
William Falcon 77fb4441ab added multi-node proc 0 ip reading 2019-07-08 09:45:00 -04:00
William Falcon e1823e0d1a added multi-node proc 0 ip reading 2019-07-08 09:44:20 -04:00
William Falcon 3422f7610b added multi-node proc 0 ip reading 2019-07-08 09:42:13 -04:00
William Falcon 79d9adf004 added multi-node proc 0 ip reading 2019-07-08 09:36:27 -04:00
William Falcon f705f15c7a added multi-node proc 0 ip reading 2019-07-08 09:36:09 -04:00
William Falcon 5fbe00837e easy import for lightningModule 2019-07-08 09:33:58 -04:00
William Falcon 1e57a75ff9 easy import for lightningModule 2019-07-08 09:32:57 -04:00
William Falcon 7d08e52b5d easy import for lightningModule 2019-07-08 09:30:51 -04:00
William Falcon d540d476a0 easy import for lightningModule 2019-07-08 09:29:02 -04:00
William Falcon 4454b968f0 easy import for lightningModule 2019-07-08 09:27:16 -04:00
William Falcon ae81473464 easy import for lightningModule 2019-07-03 18:43:13 -04:00
William Falcon 153b95c01f checkpoint only on rank=0 now 2019-07-03 18:18:29 -04:00
William Falcon a9acae3ed0 checkpoint only on rank=0 now 2019-07-03 18:17:12 -04:00
William Falcon f101152650 checkpoint only on rank=0 now 2019-07-03 18:14:34 -04:00
William Falcon 75e32daad4 clean up dead code 2019-07-03 17:09:39 -04:00
William Falcon 522af58504 clean up dead code 2019-07-03 17:05:20 -04:00
William Falcon 3ed02e4ed6 clean up dead code 2019-07-03 17:03:10 -04:00
William Falcon 9ef70bffa9 clean up dead code 2019-07-03 17:02:30 -04:00
William Falcon 9340e0a091 clean up dead code 2019-07-03 16:51:32 -04:00
William Falcon 0bfe0a993a clean up dead code 2019-07-03 16:49:53 -04:00
William Falcon 4b31f3d4bf clean up dead code 2019-07-03 16:47:39 -04:00
William Falcon 5bdad8a7b8 clean up dead code 2019-07-03 16:46:14 -04:00
William Falcon cd0d294236 clean up dead code 2019-07-03 16:44:18 -04:00
William Falcon e8abbb1e75 clean up dead code 2019-07-03 16:43:05 -04:00
William Falcon c10121c6ff clean up dead code 2019-07-03 16:39:33 -04:00
William Falcon 8630df5880 clean up dead code 2019-07-03 16:39:25 -04:00
William Falcon 23137ea08a added single node distdataparallel 2019-07-03 16:38:03 -04:00
William Falcon 32eddf492e added single node distdataparallel 2019-07-03 16:34:49 -04:00
William Falcon 7010d16752 added single node distdataparallel 2019-07-03 16:31:43 -04:00
William Falcon 080c308bcc added single node distdataparallel 2019-07-03 16:29:10 -04:00
William Falcon 8ddee926dd added single node distdataparallel 2019-07-03 16:24:10 -04:00
William Falcon 7e874dfb43 added single node distdataparallel 2019-07-03 16:23:12 -04:00
William Falcon 55b69f9fc5 added single node distdataparallel 2019-07-03 16:22:43 -04:00
William Falcon 8d3090c843 added single node distdataparallel 2019-07-03 16:21:56 -04:00
William Falcon 62774ffacb added single node distdataparallel 2019-07-03 16:17:56 -04:00
William Falcon 98a0a23158 added single node distdataparallel 2019-07-03 15:31:37 -04:00
William Falcon d52c92e09d added single node distdataparallel 2019-07-03 15:26:19 -04:00
William Falcon 09ed6904c2 added single node distdataparallel 2019-07-03 15:25:56 -04:00
William Falcon 970d1609e1 added single node distdataparallel 2019-07-03 15:25:33 -04:00
William Falcon 5f57792131 added single node distdataparallel 2019-07-03 15:24:56 -04:00
William Falcon 6eb7674e18 added single node distdataparallel 2019-07-03 15:24:16 -04:00
William Falcon 5ff3a90a6f added single node distdataparallel 2019-07-03 15:23:47 -04:00
William Falcon 22becf3915 added single node distdataparallel 2019-07-03 15:23:39 -04:00
William Falcon 5797f812ad added single node distdataparallel 2019-07-03 15:22:57 -04:00
William Falcon 251c2e964f added single node distdataparallel 2019-07-03 15:22:31 -04:00
William Falcon d67e80bf16 added single node distdataparallel 2019-07-03 15:21:13 -04:00
William Falcon 98db51eb95 added single node distdataparallel 2019-07-03 15:20:33 -04:00
William Falcon 129dce0d18 added single node distdataparallel 2019-07-03 15:18:47 -04:00
William Falcon 7f3c653747 added single node distdataparallel 2019-07-03 15:18:16 -04:00
William Falcon f06c650fc1 added single node distdataparallel 2019-07-03 15:18:10 -04:00
William Falcon b9f581ab87 added single node distdataparallel 2019-07-03 15:17:02 -04:00
William Falcon ac57dac235 added single node distdataparallel 2019-07-03 15:16:09 -04:00
William Falcon 96ab78dc41 added single node distdataparallel 2019-07-03 15:11:35 -04:00
William Falcon 7ef6db49d3 added single node distdataparallel 2019-07-03 15:11:17 -04:00
William Falcon c4aca832ba added single node distdataparallel 2019-07-03 15:09:49 -04:00
William Falcon 30e2fc6c4b added on_hpc_load and on_hpc_save hooks 2019-07-02 09:36:48 -04:00
William Falcon 62e091f48d added on_hpc_load and on_hpc_save hooks 2019-07-02 09:36:33 -04:00
William Falcon f257c080c0 added on_hpc_load and on_hpc_save hooks 2019-07-02 09:35:15 -04:00
William Falcon cd11b7de98 remove default tensor 2019-07-02 09:23:47 -04:00
William Falcon 49c27770da
fix dataparallel 2019-07-01 18:38:07 -04:00
William Falcon 0f5a7c322e
fix dataparallel 2019-07-01 18:33:24 -04:00
William Falcon 6ffb6fb010 verified tfx support 2019-06-29 17:45:26 -04:00
William Falcon 0a03042bf7 fixed multiprocessing import 2019-06-29 17:33:10 -04:00
William Falcon f2134a4ddd integrated tensorboardx test-tube 2019-06-29 15:58:47 -04:00
William Falcon 0bdb8533c6 added module properties docs 2019-06-28 18:42:53 -04:00
William Falcon a86ce398a9 added gradient clipping 2019-06-28 18:00:57 -04:00
William Falcon 63d84283a4 removed checkpoint save_function option 2019-06-28 17:14:18 -04:00
William Falcon 2840c7209f changed read me 2019-06-28 16:24:51 -04:00
William Falcon e44644e4ba added val loop options 2019-06-27 13:58:13 -04:00
William Falcon 7aaadad2c6 renamed options 2019-06-27 11:27:11 -04:00
William Falcon b1fdde5daf prog bar option 2019-06-27 11:22:13 -04:00
William Falcon 4f75515ca4 adding docs 2019-06-27 11:04:02 -04:00
William Falcon 39af973bd4 added trainer docs 2019-06-27 11:03:53 -04:00
William Falcon 3b7c7c65e4 added lightning model docs 2019-06-27 10:05:47 -04:00
William Falcon a40b21bce0 removed self.model refs 2019-06-26 18:27:25 -04:00
William Falcon 301a4992f4 removed self.model refs 2019-06-26 18:24:47 -04:00
William Falcon 8f9672603b removed self.model refs 2019-06-26 18:23:02 -04:00
William Falcon 5c8875130b removed self.model refs 2019-06-26 18:17:40 -04:00
William Falcon bf0f5a5cbb removed self.model refs 2019-06-26 18:12:33 -04:00
William Falcon df4ac681ed removed self.model refs 2019-06-26 18:08:46 -04:00
William Falcon bc0278252e removed self.model refs 2019-06-26 18:04:29 -04:00
William Falcon 12a0e98920 updated args 2019-06-26 17:54:59 -04:00
William Falcon 4a3c9de857 updated args 2019-06-26 17:53:05 -04:00
William Falcon 0b1e22ac51 updated args 2019-06-26 17:52:14 -04:00
William Falcon 808e86b17c updated args 2019-06-26 17:50:09 -04:00
William Falcon 71cd8f549d updated args 2019-06-26 17:49:58 -04:00
William Falcon 1ee6d21db2 updated args 2019-06-26 17:46:55 -04:00
William Falcon f8be24b09c updated args 2019-06-26 17:44:34 -04:00
William Falcon 1b497ac69a updated args 2019-06-25 20:32:20 -04:00
William Falcon d016431a3f updated args 2019-06-25 20:31:29 -04:00
William Falcon a2e4944f60 updated args 2019-06-25 20:31:10 -04:00
William Falcon 4d5123e379 updated args 2019-06-25 20:29:26 -04:00
William Falcon 5ce4e872de updated args 2019-06-25 20:28:33 -04:00
William Falcon 5eaaf82837 updated args 2019-06-25 20:27:17 -04:00
William Falcon 45331b396f updated args 2019-06-25 20:24:43 -04:00
William Falcon 440f47b864 updated args 2019-06-25 20:24:03 -04:00
William Falcon 88606c581f updated args 2019-06-25 20:22:59 -04:00
William Falcon 078bbc5df5 updated args 2019-06-25 20:19:11 -04:00
William Falcon 4c556e9880 updated args 2019-06-25 20:19:02 -04:00
William Falcon e3f96d6f3a updated args 2019-06-25 20:17:50 -04:00
William Falcon d33048c67b updated args 2019-06-25 20:16:59 -04:00
William Falcon a76ae6bc48 updated args 2019-06-25 20:12:46 -04:00
William Falcon 0460821398 updated args 2019-06-25 20:12:41 -04:00
William Falcon d3b621dfd2 updated args 2019-06-25 20:04:27 -04:00
William Falcon ac88e3f832 updated args 2019-06-25 20:03:27 -04:00
William Falcon b59af1813b updated args 2019-06-25 19:56:12 -04:00
William Falcon 7814b2d449 updated args 2019-06-25 19:54:28 -04:00
William Falcon c941649532 updated args 2019-06-25 19:52:26 -04:00
William Falcon 0795e4d51b updated args 2019-06-25 19:46:49 -04:00
William Falcon 158aca26e2 updated args 2019-06-25 19:45:31 -04:00
William Falcon cf57be9dca updated args 2019-06-25 19:43:25 -04:00
William Falcon 8df13035eb updated args 2019-06-25 19:42:15 -04:00
William Falcon c54dd94295 updated args 2019-06-25 19:35:11 -04:00
William Falcon e801914d1d updated args 2019-06-25 19:18:27 -04:00
William Falcon 89410e9090 updated args 2019-06-25 19:17:17 -04:00
William Falcon c4da914747 updated args 2019-06-25 19:06:39 -04:00
William Falcon 41a935185c updated args 2019-06-25 19:06:19 -04:00
William Falcon 73b4976500 updated args 2019-06-25 19:04:49 -04:00
William Falcon 4d42b1ed5f updated args 2019-06-25 19:00:38 -04:00
William Falcon 0fd4d5e7a1 updated args 2019-06-25 18:59:37 -04:00
William Falcon d4ca295762 updated args 2019-06-25 18:51:41 -04:00
William Falcon c45a329df4 updated args 2019-06-25 18:44:11 -04:00
William Falcon 775ca3736b updated args 2019-06-25 18:29:16 -04:00
William Falcon a00b8f7861 updated args 2019-06-25 18:25:19 -04:00
William Falcon b9d5397196 updated args 2019-06-25 18:14:48 -04:00
William Falcon 3f8e133303 updated args 2019-06-25 18:13:01 -04:00
William Falcon 9bf3fcd45e adding support for interrupt signals 2019-06-14 09:59:28 -04:00
William Falcon 88ff860c90 adding support for interrupt signals 2019-06-14 09:46:41 -04:00
William Falcon edf03063a1 adding support for interrupt signals 2019-06-14 09:44:19 -04:00
William Falcon 32edc6d7b7 adding support for interrupt signals 2019-06-14 09:42:36 -04:00
William Falcon cd36b63167 adding support for interrupt signals 2019-06-14 09:39:52 -04:00
William Falcon 519d2e9321 adding support for interrupt signals 2019-06-14 09:28:23 -04:00
William Falcon 8cca02d652 adding support for interrupt signals 2019-06-14 09:25:46 -04:00
William Falcon 69274d304d adding support for interrupt signals 2019-06-14 09:24:51 -04:00
William Falcon d98e799404 adding dataparallel 2019-06-07 15:06:22 -04:00
William Falcon 96903c7910 added amp level option 2019-05-16 16:01:15 -04:00
William Falcon eb13bb8313 added amp level option 2019-05-16 15:58:58 -04:00
William Falcon 2d3977046e added amp level option 2019-05-16 15:58:06 -04:00
William Falcon 60d4b80322 added amp level option 2019-05-16 15:55:21 -04:00
William Falcon e052a3bc92 added amp level option 2019-05-16 15:52:00 -04:00
William Falcon 35ca80683e added amp level option 2019-05-16 15:47:21 -04:00
William Falcon 9d19ab5850 added amp level option 2019-05-16 15:45:56 -04:00
William Falcon 92f9b3e062 fixed alternating loss 2019-05-14 06:40:11 -04:00
William Falcon 5fa2a6a723 tng and val steps now have batch nbs 2019-05-14 06:37:56 -04:00
William Falcon 8531f33549 tng and val steps now have batch nbs 2019-05-14 06:36:26 -04:00
William Falcon c973245ba1 fixed error with shorter batch cycles 2019-05-14 06:11:16 -04:00
William Falcon a8e57602d3 added option to change default tensor 2019-05-13 22:03:47 -04:00
William Falcon 8836f4f7a5 added option to change default tensor 2019-05-13 22:02:53 -04:00
William Falcon f246ae7fab added option to change default tensor 2019-05-13 21:55:57 -04:00
William Falcon 1c7d477d03 added option to change default tensor 2019-05-13 21:52:02 -04:00
William Falcon 90a460ec62 added option to change default tensor 2019-05-13 21:47:07 -04:00
William Falcon 8a68466710 added option to change default tensor 2019-05-13 21:27:01 -04:00
William Falcon 4dbf38093a added option to change default tensor 2019-05-13 21:22:50 -04:00
William Falcon 8e49fc6cf7 added option to change default tensor 2019-05-13 21:19:07 -04:00
William Falcon 5f0a71c414 added option to change default tensor 2019-05-13 21:18:17 -04:00
William Falcon 88fbf6cc4b added option to change default tensor 2019-05-13 20:44:25 -04:00
William Falcon fecd6a00cb added option to change default tensor 2019-05-13 20:41:23 -04:00
William Falcon 4693276494 added option to change default tensor 2019-05-13 20:40:07 -04:00
William Falcon e3425ec6a0 added option to change default tensor 2019-05-13 19:30:06 -04:00
William Falcon 5a7ad19403 fixed gpu map location 2019-05-13 05:32:18 -04:00
William Falcon 12352f1949 fixed epoch continuation from checkpoint 2019-05-05 12:15:04 -04:00
William Falcon f881bf6750 added log saving when early epoch stop 2019-04-23 11:12:01 -04:00
William Falcon 2514f62913 early epoch stopping 2019-04-23 08:57:58 -04:00
William Falcon 95aee7ff96 early epoch stopping 2019-04-23 08:46:20 -04:00
William Falcon ffd6dc678c early epoch stopping 2019-04-23 08:27:27 -04:00
William Falcon 1961a6abb2 early epoch stopping 2019-04-23 08:26:48 -04:00
William Falcon 676d76d839 pointer to trainer in model 2019-04-23 07:25:09 -04:00
William Falcon 333f0fde9b fixed hooks 2019-04-21 14:16:54 -04:00
William Falcon 4b0b7e5ea3 if return -1 from a hook that loop stopps 2019-04-21 13:40:32 -04:00
William Falcon e89da15f18 if return -1 from a hook that loop stopps 2019-04-21 13:38:50 -04:00
William Falcon 398b709b76 fixex imports 2019-04-21 13:12:42 -04:00
Shreyas Bapat 18b0c5a122 Add src, docs and other important folders 2019-04-03 22:16:02 +05:30
William Falcon f26488bd16 fixes #4 2019-04-03 11:27:01 -04:00
William Falcon bca1c4b594
Update embeddings.py 2019-04-03 11:21:16 -04:00
William Falcon a01e2ade25
Update embeddings.py 2019-04-03 11:18:51 -04:00
William Falcon d286206e86 added example and verified 2019-03-31 16:29:50 -04:00
William Falcon 2117485550 updated lib name 2019-03-30 21:45:16 -04:00