Commits · ac5fff19dcb54bb341b7bfb3cf9f554f2d5f92a5 · ModelZoo / ResNet50_tensorflow

12 May, 2020 2 commits
- Make Transformer Layer back compatible. · ac5fff19
  Hongkun Yu authored May 12, 2020
```
PiperOrigin-RevId: 311165658
```
  ac5fff19
- Internal Change · 2878da2e
  Chen Chen authored May 12, 2020
```
PiperOrigin-RevId: 311072125
```
  2878da2e
10 May, 2020 1 commit
- Internal change · 09c5ae2f
  Hongkun Yu authored May 09, 2020
```
PiperOrigin-RevId: 310767440
```
  09c5ae2f
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

08 May, 2020 1 commit

Add interfaces in nlp.modeling.networks.encoder_scaffold.EncoderScaffold,... · 56a2f704

A. Unique TensorFlower authored May 07, 2020

Add interfaces in nlp.modeling.networks.encoder_scaffold.EncoderScaffold, allowing it to output all hidden layer references, and all intermediate output data references.

PiperOrigin-RevId: 310509202

56a2f704

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
25 Apr, 2020 1 commit
- Make BertPretrainer to accept embedding_table explicitly · f7852565
  Sergey Mironov authored Apr 16, 2020
  
  f7852565
21 Apr, 2020 1 commit
- Internal change · 330b34fe
  Hongkun Yu authored Apr 21, 2020
```
PiperOrigin-RevId: 307689094
```
  330b34fe
20 Apr, 2020 2 commits
- Set the name when creating layers.PositionEmbedding object. · 1f685c54
  Chen Chen authored Apr 20, 2020
```
PiperOrigin-RevId: 307500045
```
  1f685c54
- In BERT's export to TF Hub, fix shape propagation for seq_length. · b3377b09
  A. Unique TensorFlower authored Apr 20, 2020
```
PiperOrigin-RevId: 307425903
```
  b3377b09
19 Apr, 2020 1 commit
- Fix get_config() in ReZeroTransformer. · 295b3b4f
  Le Hou authored Apr 19, 2020
```
PiperOrigin-RevId: 307297217
```
  295b3b4f
17 Apr, 2020 4 commits
- Add TalkingHeadsAttention to README. · 85b50c88
  Chen Chen authored Apr 17, 2020
```
PiperOrigin-RevId: 307082084
```
  85b50c88
- Add ReZeroTransformer to README. · f499e880
  Le Hou authored Apr 17, 2020
```
PiperOrigin-RevId: 307079383
```
  f499e880
- Internal change · 01c4ee81
  Chen Chen authored Apr 16, 2020
```
PiperOrigin-RevId: 306986791
```
  01c4ee81
- Add ReZero support (https://arxiv.org/abs/2003.04887) · dbd74385
  Le Hou authored Apr 16, 2020
```
PiperOrigin-RevId: 306971008
```
  dbd74385
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
13 Apr, 2020 1 commit
- Internal change · 057895af
  Chen Chen authored Apr 12, 2020
```
PiperOrigin-RevId: 306182576
```
  057895af
08 Apr, 2020 2 commits
- Rename arguments of EncoderScaffold: · db6aca44
  Chen Chen authored Apr 08, 2020
```
num_output_classes -> pooled_output_dim
classification_layer_initializer -> pooler_layer_initializer

PiperOrigin-RevId: 305550415
```
  db6aca44
- Add num_summed_dimensions to get_config · f3a6500f
  Yichao 'Peak' Ji authored Apr 08, 2020
  
  f3a6500f
01 Apr, 2020 1 commit
- Add a CompiledTransformer layer, which is compiled with XLA. · a3be7365
  George Karpenkov authored Apr 01, 2020
```
PiperOrigin-RevId: 304222530
```
  a3be7365
31 Mar, 2020 2 commits
- Minor code style updates · bd64315e
  Yichao 'Peak' Ji authored Mar 31, 2020
  
  bd64315e
- Fix output shape of the position embedding layer · c93ac621
  Yichao 'Peak' Ji authored Mar 31, 2020
  
  c93ac621
27 Mar, 2020 1 commit
- Use mixed precision for gelu intermediate activation in BERT SQuAD model · 8849285f
  A. Unique TensorFlower authored Mar 27, 2020
```
PiperOrigin-RevId: 303407939
```
  8849285f
12 Mar, 2020 2 commits
- Internal change · c7adbbe4
  Hongkun Yu authored Mar 11, 2020
```
PiperOrigin-RevId: 300481917
```
  c7adbbe4
- Internal change · a12cec09
  Hongkun Yu authored Mar 11, 2020
```
PiperOrigin-RevId: 300477605
```
  a12cec09
09 Mar, 2020 1 commit
- Rename Attention to MultiheadAttention · f3a29bdd
  Hongkun Yu authored Mar 09, 2020
```
PiperOrigin-RevId: 299901483
```
  f3a29bdd
05 Mar, 2020 2 commits
- Internal change · 2565629c
  Hongkun Yu authored Mar 05, 2020
```
PiperOrigin-RevId: 299169021
```
  2565629c
- Add README files in nlp/modeling folder. · ab6d40ca
  Jing Li authored Mar 05, 2020
```
PiperOrigin-RevId: 299126470
```
  ab6d40ca
04 Mar, 2020 1 commit
- Creates a models folder to host all keras.Model end points. · 0066ae22
  Hongkun Yu authored Mar 04, 2020
```
PiperOrigin-RevId: 298905114
```
  0066ae22
03 Mar, 2020 2 commits
- Attributes->Arguments. Be consistent with keras style. · 651677f5
  Hongkun Yu authored Mar 03, 2020
```
PiperOrigin-RevId: 298692558
```
  651677f5
- Remove @tf.function(experimental_compile=True) annotation · add0620a
  George Karpenkov authored Mar 02, 2020
```
Removed with plans to re-add later once the feature stabilizes more.

PiperOrigin-RevId: 298486867
```
  add0620a
26 Feb, 2020 3 commits
- Test the Transformer layer with dynamic sequence · 2f9f2479
  George Karpenkov authored Feb 26, 2020
```
PiperOrigin-RevId: 297412889
```
  2f9f2479
- Add a class-based decorator for only adding tf.function in TF2 mode · f2cf0cf4
  George Karpenkov authored Feb 26, 2020
```
PiperOrigin-RevId: 297366405
```
  f2cf0cf4
- Do not recreate tf.function on different calls to the same layer · e0c2c302
  George Karpenkov authored Feb 26, 2020
```
PiperOrigin-RevId: 297366158
```
  e0c2c302
25 Feb, 2020 1 commit
- Only apply tf.function(experimental_compile=True) in eager mode · fe1fa6d6
  George Karpenkov authored Feb 25, 2020
```
Application in graph mode still leads to some crashes.

PiperOrigin-RevId: 297144398
```
  fe1fa6d6
21 Feb, 2020 1 commit

Enable XLA compilation using `@tf.function(experimental_compile=True) for transformer layer. · 393c1399

George Karpenkov authored Feb 21, 2020

To debug the tf.function this API can be used: https://www.tensorflow.org/api_docs/python/tf/config/experimental_run_functions_eagerly

PiperOrigin-RevId: 296458870

393c1399

13 Feb, 2020 1 commit
- Remove output_activation because it is not used anywhere. · e8140fa9
  Chen Chen authored Feb 12, 2020
```
PiperOrigin-RevId: 294813724
```
  e8140fa9
12 Feb, 2020 1 commit
- no need to use `tf.keras.backend` ops. Just use equivalent tf.* ops · 1b3b2839
  Hongkun Yu authored Feb 11, 2020
```
PiperOrigin-RevId: 294588219
```
  1b3b2839
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