Commits · 2e41d8ca790fada5a98b46883f80f7a2d89d2790 · ModelZoo / ResNet50_tensorflow

14 Sep, 2020 1 commit
- Move `MultiHeadRelativeAttention` to relative_attention.py. · 2e41d8ca
  Allen Wang authored Sep 14, 2020
```
PiperOrigin-RevId: 331652519
```
  2e41d8ca
09 Sep, 2020 1 commit
- MultiHeadRelativeAttention compatibility changes with XLNet · b7f6e079
  Allen Wang authored Sep 09, 2020
```
PiperOrigin-RevId: 330751568
```
  b7f6e079
24 Aug, 2020 4 commits
- Internal changes. · b8013664
  Allen Wang authored Aug 24, 2020
```
PiperOrigin-RevId: 328225451
```
  b8013664
- Internal changes. · 3335e25d
  Allen Wang authored Aug 24, 2020
```
PiperOrigin-RevId: 328225451
```
  3335e25d
- Clean up attention layer imports · 7f824479
  Hongkun Yu authored Aug 23, 2020
```
PiperOrigin-RevId: 328085299
```
  7f824479
- Clean up attention layer imports · 24847953
  Hongkun Yu authored Aug 23, 2020
```
PiperOrigin-RevId: 328085299
```
  24847953
19 Aug, 2020 2 commits
- Enforce PY3 for official/nlp/modeling · e36a5fec
  Hongkun Yu authored Aug 18, 2020
```
PiperOrigin-RevId: 327363070
```
  e36a5fec
- Enforce PY3 for official/nlp/modeling · 8a78c154
  Hongkun Yu authored Aug 18, 2020
```
PiperOrigin-RevId: 327363070
```
  8a78c154
13 Aug, 2020 2 commits
- Replace tensorflow_models MultiHeadAttention with tf.keras.MultiHeadAttention. · 2444a510
  Zhenyu Tan authored Aug 13, 2020
```
PiperOrigin-RevId: 326496940
```
  2444a510
- Replace tensorflow_models MultiHeadAttention with tf.keras.MultiHeadAttention. · 197978fe
  Zhenyu Tan authored Aug 13, 2020
```
PiperOrigin-RevId: 326496940
```
  197978fe
07 Aug, 2020 2 commits
- Make sure the attention mask expand dim happens at the head dim. · 33fc3eeb
  Hongkun Yu authored Aug 07, 2020
```
PiperOrigin-RevId: 325454896
```
  33fc3eeb
- Make sure the attention mask expand dim happens at the head dim. · 9cbce60e
  Hongkun Yu authored Aug 07, 2020
```
PiperOrigin-RevId: 325454896
```
  9cbce60e
29 Jul, 2020 3 commits
- whitespace · 3e0fa932
  xinliupitt authored Jul 29, 2020
  
  3e0fa932
- docstrings · d39321b1
  xinliupitt authored Jul 29, 2020
  
  d39321b1
- transformer, attention layers · 23804bc5
  xinliupitt authored Jul 29, 2020
  
  23804bc5
21 Jul, 2020 2 commits

[MultiheadAttention] Apply suggestions from RFC: · 36101ab4

Hongkun Yu authored Jul 21, 2020

(1) call() consume kwargs and implement _build_from_signature (layers added inside init_scope)
(2) make build/call_attention as public.

PiperOrigin-RevId: 322454619

36101ab4

[MultiheadAttention] Apply suggestions from RFC: · 570d9a2b

Hongkun Yu authored Jul 21, 2020

(1) call() consume kwargs and implement _build_from_signature (layers added inside init_scope)
(2) make build/call_attention as public.

PiperOrigin-RevId: 322454619

570d9a2b

20 Jul, 2020 2 commits
- Internal change · 42b362ac
  Allen Wang authored Jul 20, 2020
```
PiperOrigin-RevId: 322216928
```
  42b362ac
- Internal change · cdda0906
  Allen Wang authored Jul 20, 2020
```
PiperOrigin-RevId: 322216928
```
  cdda0906
10 Jun, 2020 2 commits
- Fix typo. · 4cd908ef
  Hongkun Yu authored Jun 10, 2020
```
PiperOrigin-RevId: 315738983
```
  4cd908ef
- Changes the MaskedSoftmax to call(inputs, mask=None) · 99bdc3dc
  Hongkun Yu authored Jun 09, 2020
```
PiperOrigin-RevId: 315630320
```
  99bdc3dc
29 May, 2020 1 commit

Proposes the full functionality of MultiHeadAttention layer. This change first... · 8a13ca4e

Hongkun Yu authored May 29, 2020

Proposes the full functionality of MultiHeadAttention layer. This change first goes to model garden NLP library.

PiperOrigin-RevId: 313847485

8a13ca4e

12 May, 2020 1 commit
- Fixes a typo. · 3ae3aecf
  A. Unique TensorFlower authored May 12, 2020
```
PiperOrigin-RevId: 311196489
```
  3ae3aecf
10 May, 2020 1 commit
- Internal change · 09c5ae2f
  Hongkun Yu authored May 09, 2020
```
PiperOrigin-RevId: 310767440
```
  09c5ae2f
21 Apr, 2020 1 commit
- Internal change · 330b34fe
  Hongkun Yu authored Apr 21, 2020
```
PiperOrigin-RevId: 307689094
```
  330b34fe
15 Apr, 2020 1 commit
- Remove __init__ in CachedAttention, which is the same as its parent class. · 3c227a73
  Hongkun Yu authored Apr 15, 2020
```
PiperOrigin-RevId: 306748161
```
  3c227a73
09 Mar, 2020 1 commit
- Rename Attention to MultiheadAttention · f3a29bdd
  Hongkun Yu authored Mar 09, 2020
```
PiperOrigin-RevId: 299901483
```
  f3a29bdd
03 Mar, 2020 1 commit
- Attributes->Arguments. Be consistent with keras style. · 651677f5
  Hongkun Yu authored Mar 03, 2020
```
PiperOrigin-RevId: 298692558
```
  651677f5
21 Jan, 2020 1 commit

Remove compute_output_shape. · 0e0a94a6

Hongkun Yu authored Jan 21, 2020

Keras: "manual" shape inference is only required if the layer is dynamic (otherwise we use TF's static shape inference capabilities)

PiperOrigin-RevId: 290821518

0e0a94a6

25 Nov, 2019 1 commit
- Implement CachedAttention layer. This is useful for decoders. · 0b579232
  Hongkun Yu authored Nov 25, 2019
```
PiperOrigin-RevId: 282439719
```
  0b579232
13 Nov, 2019 1 commit
- Internal change · c3bd5082
  A. Unique TensorFlower authored Nov 12, 2019
```
PiperOrigin-RevId: 280123567
```
  c3bd5082
11 Nov, 2019 1 commit

Release keras bert: · f1d35b4e

Hongkun Yu authored Nov 11, 2019

- Update classifier example.
- Add new converted checkpoints.
- Update benchmark,

PiperOrigin-RevId: 279762797

f1d35b4e