Commits · f9dbe73ae99c05971c50b4d12a0424708c663b66 · ModelZoo / ResNet50_tensorflow

11 Mar, 2022 1 commit
- Internal change · f9dbe73a
  Le Hou authored Mar 10, 2022
```
PiperOrigin-RevId: 433920851
```
  f9dbe73a
18 Jan, 2022 2 commits
- Internal change · 4242b549
  A. Unique TensorFlower authored Jan 18, 2022
```
PiperOrigin-RevId: 422612138
```
  4242b549
- Internal change · 871c4e0a
  A. Unique TensorFlower authored Jan 18, 2022
```
PiperOrigin-RevId: 422612138
```
  871c4e0a
02 Nov, 2021 2 commits

[bert_encoder] Found a typo in previous experiment and turns out that the... · f32dea32

Frederick Liu authored Nov 01, 2021

[bert_encoder] Found a typo in previous experiment and turns out that the checkpoints are compatible even when wrapped in models.

PiperOrigin-RevId: 406987505

f32dea32

[bert_encoder] Found a typo in previous experiment and turns out that the... · d7940205

Frederick Liu authored Nov 01, 2021

[bert_encoder] Found a typo in previous experiment and turns out that the checkpoints are compatible even when wrapped in models.

PiperOrigin-RevId: 406987505

d7940205

29 Oct, 2021 2 commits
- Internal change · 2fec36b2
  Frederick Liu authored Oct 28, 2021
```
PiperOrigin-RevId: 406277256
```
  2fec36b2
- Internal change · c0af8f0b
  Frederick Liu authored Oct 28, 2021
```
PiperOrigin-RevId: 406277256
```
  c0af8f0b
08 Oct, 2021 2 commits
- Merge BertEncoderV2 and BertEncoder. · 21ce83d8
  Hongkun Yu authored Oct 08, 2021
```
PiperOrigin-RevId: 401789124
```
  21ce83d8
- Merge BertEncoderV2 and BertEncoder. · 8bfa4d03
  Hongkun Yu authored Oct 08, 2021
```
PiperOrigin-RevId: 401789124
```
  8bfa4d03
07 Oct, 2021 2 commits
- [keras_nlp] Merge keras_nlp into tf_nlp. · 9b23daf9
  Frederick Liu authored Oct 07, 2021
```
PiperOrigin-RevId: 401593694
```
  9b23daf9
- [keras_nlp] Merge keras_nlp into tf_nlp. · 002b4240
  Frederick Liu authored Oct 07, 2021
```
PiperOrigin-RevId: 401593694
```
  002b4240
04 Jul, 2021 2 commits
- [nlp] Support norm_first option for Bert/Bigbird/Kernel encoders. · 097a8296
  Frederick Liu authored Jul 03, 2021
```
PiperOrigin-RevId: 382960239
```
  097a8296
- [nlp] Support norm_first option for Bert/Bigbird/Kernel encoders. · 72c47570
  Frederick Liu authored Jul 03, 2021
```
PiperOrigin-RevId: 382960239
```
  72c47570
13 Apr, 2021 2 commits

Use nonexperimental mixed precision API. · 9a4d14a9

Reed Wanderman-Milne authored Apr 12, 2021

This replaces symbols in tf.keras.mixed_precision.experimental with the corresponding nonexperimental symbols. In some cases, passing a Policy is replaced with passing a policy name for conciseness.

Additionally, for the Shakespeare model, the loss_scale flag is removed, since supporting it with the nonexperimental API is slightly more verbose and it is recommended users use the default loss scale.

PiperOrigin-RevId: 368123944

9a4d14a9

Use nonexperimental mixed precision API. · 4334a892

Reed Wanderman-Milne authored Apr 12, 2021

This replaces symbols in tf.keras.mixed_precision.experimental with the corresponding nonexperimental symbols. In some cases, passing a Policy is replaced with passing a policy name for conciseness.

PiperOrigin-RevId: 368123944

4334a892

10 Mar, 2021 2 commits
- Internal change · 5981350b
  Frederick Liu authored Mar 09, 2021
```
PiperOrigin-RevId: 361957289
```
  5981350b
- Internal change · 5a898973
  Frederick Liu authored Mar 09, 2021
```
PiperOrigin-RevId: 361957289
```
  5a898973
23 Oct, 2020 2 commits

Shift all attribute assignments in functional subclass models below the... · f5a1343f

A. Unique TensorFlower authored Oct 23, 2020

Shift all attribute assignments in functional subclass models below the super().__init__ call, and enable setattr tracking on all functional subclasses.

PiperOrigin-RevId: 338759531

f5a1343f

Shift all attribute assignments in functional subclass models below the... · 589f0269

A. Unique TensorFlower authored Oct 23, 2020

Shift all attribute assignments in functional subclass models below the super().__init__ call, and enable setattr tracking on all functional subclasses.

PiperOrigin-RevId: 338759531

589f0269

09 Sep, 2020 2 commits
- Add dict outputs to BertEncoder and EncoderScaffold · b47eb2a2
  Hongkun Yu authored Sep 09, 2020
```
PiperOrigin-RevId: 330817736
```
  b47eb2a2
- Add dict outputs to BertEncoder and EncoderScaffold · f1b9d43f
  Hongkun Yu authored Sep 09, 2020
```
PiperOrigin-RevId: 330817736
```
  f1b9d43f
08 Sep, 2020 2 commits
- Internal change · eb34e04d
  A. Unique TensorFlower authored Sep 08, 2020
```
PiperOrigin-RevId: 330543007
```
  eb34e04d
- Internal change · 693e53c4
  A. Unique TensorFlower authored Sep 08, 2020
```
PiperOrigin-RevId: 330543007
```
  693e53c4
03 Sep, 2020 2 commits
- Adds test for encoder save()/load() · 8309ff13
  Hongkun Yu authored Sep 03, 2020
```
PiperOrigin-RevId: 329963956
```
  8309ff13
- Adds test for encoder save()/load() · c2d3fdc0
  Hongkun Yu authored Sep 03, 2020
```
PiperOrigin-RevId: 329963956
```
  c2d3fdc0
01 Sep, 2020 2 commits
- Add PositionEmbedding for keras_nlp. · 1e22d1fe
  Zhenyu Tan authored Sep 01, 2020
```
PiperOrigin-RevId: 329568227
```
  1e22d1fe
- Add PositionEmbedding for keras_nlp. · 2b166642
  Zhenyu Tan authored Sep 01, 2020
```
PiperOrigin-RevId: 329568227
```
  2b166642
27 Aug, 2020 2 commits
- Rename TransformerEncoder to BertEncoder. · e9f8dfa1
  Hongkun Yu authored Aug 27, 2020
```
PiperOrigin-RevId: 328829120
```
  e9f8dfa1
- Rename TransformerEncoder to BertEncoder. · e3a74e5b
  Hongkun Yu authored Aug 27, 2020
```
PiperOrigin-RevId: 328829120
```
  e3a74e5b
12 Aug, 2020 2 commits
- Internal change · 999fae62
  Hongkun Yu authored Aug 12, 2020
```
PiperOrigin-RevId: 326286926
```
  999fae62
- Internal change · 88253ce5
  Hongkun Yu authored Aug 12, 2020
```
PiperOrigin-RevId: 326286926
```
  88253ce5
31 Jul, 2020 2 commits
- Internal change · afee40a0
  Hongkun Yu authored Jul 30, 2020
```
PiperOrigin-RevId: 324137297
```
  afee40a0
- Internal change · a62c2bfc
  Hongkun Yu authored Jul 30, 2020
```
PiperOrigin-RevId: 324137297
```
  a62c2bfc
21 May, 2020 1 commit

Transformer Encoder: when embedding width differs from hidden size, add a... · 26565d0d

Hongkun Yu authored May 21, 2020

Transformer Encoder: when embedding width differs from hidden size, add a projection to hidden size.

PiperOrigin-RevId: 312708922

26565d0d

09 May, 2020 1 commit

Add an interface in nlp.modeling.networks.encoder_scaffold.EncoderScaffold and... · 5e641c43

A. Unique TensorFlower authored May 08, 2020

Add an interface in nlp.modeling.networks.encoder_scaffold.EncoderScaffold and nlp.modeling.networks.transformer_encoder.TransformerEncoder, to get the pooler Dense layer reference.

PiperOrigin-RevId: 310675150

5e641c43

05 May, 2020 1 commit
- Introduce output_range for transformer layer and encoder last layer. · 563d923a
  Hongkun Yu authored May 05, 2020
```
PiperOrigin-RevId: 310032518
```
  563d923a
12 Mar, 2020 1 commit
- Internal change · a12cec09
  Hongkun Yu authored Mar 11, 2020
```
PiperOrigin-RevId: 300477605
```
  a12cec09
08 Feb, 2020 1 commit
- Internal change · 347f4044
  Zongwei Zhou authored Feb 07, 2020
```
PiperOrigin-RevId: 293958491
```
  347f4044
05 Feb, 2020 1 commit

Adds return_all_encoder_outputs option to TransformerEncoder to build a... · 6d9256ce

Hongkun Yu authored Feb 05, 2020

Adds return_all_encoder_outputs option to TransformerEncoder to build a network returning all encoder layers outputs. This is useful for Transformer Seq2Seq.

PiperOrigin-RevId: 293395112

6d9256ce

13 Nov, 2019 1 commit
- Internal change · c3bd5082
  A. Unique TensorFlower authored Nov 12, 2019
```
PiperOrigin-RevId: 280123567
```
  c3bd5082