- 26 Oct, 2020 1 commit
-
-
Hongkun Yu authored
PiperOrigin-RevId: 339071563
-
- 21 Oct, 2020 1 commit
-
-
Hongkun Yu authored
PiperOrigin-RevId: 338309524
-
- 06 Oct, 2020 1 commit
-
-
Hongkun Yu authored
Add it to export. TODO: move the encoder and decoder layer out to layers/ or decoders/. PiperOrigin-RevId: 335560860
-
- 30 Sep, 2020 1 commit
-
-
Chenkai Kuang authored
PiperOrigin-RevId: 334517779
-
- 16 Sep, 2020 1 commit
-
-
Chen Chen authored
PiperOrigin-RevId: 332084664
-
- 13 Sep, 2020 1 commit
-
-
Hongkun Yu authored
PiperOrigin-RevId: 331359058
-
- 06 Sep, 2020 1 commit
-
-
Chen Chen authored
Fix a bug that the transformer model cannot be saved when save_weights_only is set to False: https://github.com/tensorflow/models/issues/9186 PiperOrigin-RevId: 330292460
-
- 27 Aug, 2020 1 commit
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 328773294
-
- 24 Aug, 2020 2 commits
-
-
Hongkun Yu authored
Keras model serialization causes a lot of problems. PiperOrigin-RevId: 328162551
-
Hongkun Yu authored
Keras model serialization causes a lot of problems. PiperOrigin-RevId: 328162551
-
- 23 Aug, 2020 2 commits
-
-
Hongkun Yu authored
PiperOrigin-RevId: 327984543
-
Hongkun Yu authored
PiperOrigin-RevId: 327984543
-
- 14 Aug, 2020 2 commits
-
-
xinliupitt authored
-
xinliupitt authored
-
- 12 Aug, 2020 2 commits
-
-
Hongkun Yu authored
PiperOrigin-RevId: 326286926
-
Hongkun Yu authored
PiperOrigin-RevId: 326286926
-
- 11 Aug, 2020 1 commit
-
-
xinliupitt authored
-
- 08 Aug, 2020 2 commits
-
-
xinliupitt authored
-
xinliupitt authored
-
- 29 Jul, 2020 2 commits
-
-
Hongkun Yu authored
PiperOrigin-RevId: 323685656
-
Hongkun Yu authored
PiperOrigin-RevId: 323685656
-
- 28 Jul, 2020 2 commits
-
-
Hongkun Yu authored
PiperOrigin-RevId: 323653596
-
Hongkun Yu authored
PiperOrigin-RevId: 323653596
-
- 22 Jul, 2020 2 commits
-
-
A. Unique TensorFlower authored
Explicit set the dtype in embedding layer. Otherwise, using the layer in TF1.x will create an int32 tensor. PiperOrigin-RevId: 322473236
-
A. Unique TensorFlower authored
Explicit set the dtype in embedding layer. Otherwise, using the layer in TF1.x will create an int32 tensor. PiperOrigin-RevId: 322473236
-
- 17 Jul, 2020 2 commits
-
-
Hongkun Yu authored
PiperOrigin-RevId: 321817352
-
Hongkun Yu authored
PiperOrigin-RevId: 321817352
-
- 08 Jul, 2020 2 commits
-
-
Hongkun Yu authored
PiperOrigin-RevId: 320124801
-
Hongkun Yu authored
PiperOrigin-RevId: 320124801
-
- 06 Jul, 2020 2 commits
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 319744469
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 319744469
-
- 28 Jun, 2020 2 commits
-
-
Hongkun Yu authored
PiperOrigin-RevId: 318714418
-
Hongkun Yu authored
PiperOrigin-RevId: 318714418
-
- 23 Jun, 2020 2 commits
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 317908656
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 317908656
-
- 17 Jun, 2020 1 commit
-
-
Abdullah Rashwan authored
PiperOrigin-RevId: 316797555
-
- 03 Jun, 2020 4 commits
-
-
Hongkun Yu authored
This reverts commit 4bb13e61.
-
Hongkun Yu authored
This reverts commit c3c2386c.
-
xinliupitt authored
* root dir * zone updated * print mask * preview emb * tf print * input only * emb * tf print * emb after mask * masked_softmax print * print scores * multi folder * first pos emb * check input shape * add test temp * import math * two classes * prints * all get_pos replace * make time scale private * pos emb comments * print input * embedding_inputs * tf shape * dimention list * tf_util * print tf_util * concise * transformer pos change to layer * keep length var * length as input * None as input * print time signal * print time signal * remove print * test input shape * double check shape * double check shape * double check shape * more test * shape check * shape check * print 97 info * print 97 info new * test if sam * assert same * remove assert * tf print same * tf print diff * output example * output example * output example * formal test * formal test length * raise valurerror * test valurerror * double check * comments * remove prints * rename relative * delet naive test * delete docs in xinliu branch * code reformat * import order * indentation fix * more files * adjust char number * disable not callable * comment to length * error of length unequal to input_shape * root dir * zone updated * print mask * preview emb * tf print * input only * emb * tf print * emb after mask * masked_softmax print * print scores * multi folder * remove docs * remove prints * root dir * zone updated * print mask * preview emb * tf print * input only * emb * tf print * emb after mask * masked_softmax print * print scores * multi folder * remove docs * apply revised 3 files * rm prints
-
Tianqi Liu authored
PiperOrigin-RevId: 314451720
-