- 22 Jul, 2020 1 commit
-
-
Hongkun Yu authored
PiperOrigin-RevId: 322594580
-
- 21 Jul, 2020 1 commit
-
-
Hongkun Yu authored
PiperOrigin-RevId: 322387911
-
- 10 Jul, 2020 1 commit
-
-
André Susano Pinto authored
PiperOrigin-RevId: 320559100
-
- 08 Jul, 2020 1 commit
-
-
Hongkun Yu authored
PiperOrigin-RevId: 320124801
-
- 04 Jul, 2020 1 commit
-
-
Hongkun Yu authored
PiperOrigin-RevId: 319557230
-
- 23 Jun, 2020 1 commit
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 317898942
-
- 22 Jun, 2020 1 commit
-
-
Jeremiah Harmsen authored
PiperOrigin-RevId: 317638173
-
- 19 Jun, 2020 1 commit
-
-
Chen Chen authored
PiperOrigin-RevId: 317253522
-
- 17 Jun, 2020 1 commit
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 316801831
-
- 16 Jun, 2020 2 commits
-
-
Tianqi Liu authored
PiperOrigin-RevId: 316734574
-
Hongkun Yu authored
PiperOrigin-RevId: 316593329
-
- 12 Jun, 2020 2 commits
-
-
Maxim Neumann authored
PiperOrigin-RevId: 316134518
-
Maxim Neumann authored
Replace as well the regression loss with Keras loss object. PiperOrigin-RevId: 316062800
-
- 11 Jun, 2020 1 commit
-
-
Chen Chen authored
PiperOrigin-RevId: 315843901
-
- 10 Jun, 2020 1 commit
-
-
Hongkun Yu authored
PiperOrigin-RevId: 315792986
-
- 09 Jun, 2020 1 commit
-
-
Hongkun Yu authored
PiperOrigin-RevId: 315516440
-
- 04 Jun, 2020 1 commit
-
-
Tianqi Liu authored
PiperOrigin-RevId: 314822016
-
- 03 Jun, 2020 1 commit
-
-
Maxim Neumann authored
PiperOrigin-RevId: 314607393
-
- 02 Jun, 2020 3 commits
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 314417394
-
Hongkun Yu authored
PiperOrigin-RevId: 314394246
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 314270569
-
- 28 May, 2020 1 commit
-
-
Hongkun Yu authored
Deprecate old customized training loop for run_classifier.py as compile/fit fully satisfy needs/performance. PiperOrigin-RevId: 313660745
-
- 26 May, 2020 2 commits
-
-
Maxim Neumann authored
PiperOrigin-RevId: 313148142
-
André Susano Pinto authored
This allows one to finetune a BERT model into a task before using it for another task. E.g. SQuAD before finetune another QA type of tasks. PiperOrigin-RevId: 313145768
-
- 24 May, 2020 1 commit
-
-
Hongkun Yu authored
PiperOrigin-RevId: 312939899
-
- 23 May, 2020 2 commits
-
-
Hongkun Yu authored
PiperOrigin-RevId: 312923051
-
Hongkun Yu authored
PiperOrigin-RevId: 312889153
-
- 21 May, 2020 2 commits
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 312751112
-
Hongkun Yu authored
Transformer Encoder: when embedding width differs from hidden size, add a projection to hidden size. PiperOrigin-RevId: 312708922
-
- 19 May, 2020 4 commits
-
-
Hongkun Yu authored
Remove is_v2_0 PiperOrigin-RevId: 312336907
-
Chen Chen authored
PiperOrigin-RevId: 312313738
-
André Susano Pinto authored
A default of 1 all the times is bad for TPU users which end up not using the device effectively. A larger default all the times is bad for GPU users. So compromise and make this dependent on the devices available. PiperOrigin-RevId: 312230371
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 312209760
-
- 18 May, 2020 1 commit
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 312096778
-
- 14 May, 2020 3 commits
-
-
nuka137 authored
-
Hongkun Yu authored
PiperOrigin-RevId: 311602262
-
Chen Chen authored
PiperOrigin-RevId: 311577663
-
- 12 May, 2020 1 commit
-
-
Chen Chen authored
PiperOrigin-RevId: 311069693
-
- 06 May, 2020 1 commit
-
-
Chen Chen authored
PiperOrigin-RevId: 310104070
-
- 05 May, 2020 1 commit
-
-
Hongkun Yu authored
PiperOrigin-RevId: 310032518
-