Commits · 4e6b28ad2cef21334e4e2437121c5761e7fa4c2e · ModelZoo / ResNet50_tensorflow

24 Jul, 2020 1 commit
- Fix typo. · 4e6b28ad
  Hongkun Yu authored Jul 24, 2020
```
PiperOrigin-RevId: 322960082
```
  4e6b28ad
21 Jul, 2020 2 commits

[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

Internal change · d032eec1
A. Unique TensorFlower authored Jul 21, 2020
```
PiperOrigin-RevId: 322428923
```
d032eec1

20 Jul, 2020 2 commits
- Internal change · 42b362ac
  Allen Wang authored Jul 20, 2020
```
PiperOrigin-RevId: 322216928
```
  42b362ac
- Modify the unit test of encoder scaffold to demonstrate that a subclass... · 1faf2d3d
  Hongkun Yu authored Jul 19, 2020
```
Modify the unit test of encoder scaffold to demonstrate that a subclass embedding network can be used.

PiperOrigin-RevId: 322083775
```
  1faf2d3d
17 Jul, 2020 1 commit
- Move beam search to nlp/modeling/ops · 55b82879
  Hongkun Yu authored Jul 17, 2020
```
PiperOrigin-RevId: 321817352
```
  55b82879
16 Jul, 2020 1 commit
- Adds clear documentation: Functional/Subclass API used for each network/model. · 597e59d2
  Hongkun Yu authored Jul 16, 2020
```
PiperOrigin-RevId: 321591514
```
  597e59d2
14 Jul, 2020 1 commit
- Internal change · 6487546a
  A. Unique TensorFlower authored Jul 14, 2020
```
PiperOrigin-RevId: 321238481
```
  6487546a
08 Jul, 2020 3 commits
- Migrate all DenseEinsum to tf.keras.experimental.EinsumDense · 9a9f0b65
  Hongkun Yu authored Jul 08, 2020
```
PiperOrigin-RevId: 320240466
```
  9a9f0b65
- Add a colab to explain how to use scaffold classes to build noval achitectures. · 0a1c281a
  Chen Chen authored Jul 08, 2020
```
PiperOrigin-RevId: 320149378
```
  0a1c281a
- Add a colab to introduce nlp/modeling library with examples showing how to... · edf8c8f5
  Chen Chen authored Jul 08, 2020
```
Add a colab to introduce nlp/modeling library with examples showing how to build pretrain/span labeling/classification models.

PiperOrigin-RevId: 320147054
```
  edf8c8f5
06 Jul, 2020 1 commit
- Internal change · e8659893
  Hongkun Yu authored Jul 06, 2020
```
PiperOrigin-RevId: 319839860
```
  e8659893
05 Jul, 2020 1 commit
- Internal change · 6bd738f2
  Hongkun Yu authored Jul 05, 2020
```
PiperOrigin-RevId: 319697990
```
  6bd738f2
30 Jun, 2020 2 commits
- Add ELECTRA pretrainer v2 configuration and adjust the visibility of ELECTRAPretrainer. · a36f85c6
  A. Unique TensorFlower authored Jun 30, 2020
```
Contributed by mickeystroller

PiperOrigin-RevId: 319073522
```
  a36f85c6
- Add ELECTRA pretrainer v2 configuration and adjust the visibility of ELECTRAPretrainer. · 842844e8
  A. Unique TensorFlower authored Jun 30, 2020
```
Contributed by mickeystroller

PiperOrigin-RevId: 319073522
```
  842844e8
29 Jun, 2020 2 commits
- Change the ELECTRA pretrainer output to a dict in order to be compatible with later ELECTRA task. · e569c04c
  A. Unique TensorFlower authored Jun 29, 2020
```
Contributed by mickeystroller

PiperOrigin-RevId: 318909403
```
  e569c04c
- Change the ELECTRA pretrainer output to a dict in order to be compatible with later ELECTRA task. · b7c8435d
  A. Unique TensorFlower authored Jun 29, 2020
```
Contributed by mickeystroller

PiperOrigin-RevId: 318909403
```
  b7c8435d
26 Jun, 2020 2 commits
- Update weighted sparse categorical loss. Remove per-example loss. · 9d9aa387
  Hongkun Yu authored Jun 25, 2020
```
PiperOrigin-RevId: 318421049
```
  9d9aa387
- Update weighted sparse categorical loss. Remove per-example loss. · 1e4fd825
  Hongkun Yu authored Jun 25, 2020
```
PiperOrigin-RevId: 318421049
```
  1e4fd825
25 Jun, 2020 2 commits
- Multichannel attention: Override _build_attention method instead of build() · 658a45f2
  Hongkun Yu authored Jun 24, 2020
```
PiperOrigin-RevId: 318208409
```
  658a45f2
- Multichannel attention: Override _build_attention method instead of build() · 4140da21
  Hongkun Yu authored Jun 24, 2020
```
PiperOrigin-RevId: 318208409
```
  4140da21
22 Jun, 2020 2 commits
- Internal change · d4f5c193
  Chen Chen authored Jun 22, 2020
```
PiperOrigin-RevId: 317691679
```
  d4f5c193
- Internal change · 8aa44501
  Hongkun Yu authored Jun 21, 2020
```
PiperOrigin-RevId: 317596394
```
  8aa44501
20 Jun, 2020 1 commit
- Add ELECTRA TF 2.x pretrainer. · b708fd68
  A. Unique TensorFlower authored Jun 19, 2020
```
Contributed by mickeystroller

PiperOrigin-RevId: 317411747
```
  b708fd68
19 Jun, 2020 1 commit
- Move TransformerDecoderLayer to modeling/ · 58e805e0
  Hongkun Yu authored Jun 19, 2020
```
PiperOrigin-RevId: 317330705
```
  58e805e0
18 Jun, 2020 1 commit
- Internal change · 21b73d22
  A. Unique TensorFlower authored Jun 17, 2020
```
PiperOrigin-RevId: 317010998
```
  21b73d22
16 Jun, 2020 1 commit
- Internal change · 802488f1
  Hongkun Yu authored Jun 15, 2020
```
PiperOrigin-RevId: 316593329
```
  802488f1
12 Jun, 2020 2 commits
- Internal Change · 5a4c4e18
  Chen Chen authored Jun 11, 2020
```
PiperOrigin-RevId: 316054828
```
  5a4c4e18
- Internal change · 9cdb5d72
  Chen Chen authored Jun 11, 2020
```
PiperOrigin-RevId: 316053809
```
  9cdb5d72
10 Jun, 2020 5 commits
- Internal change · 9dadc325
  Hongkun Yu authored Jun 10, 2020
```
PiperOrigin-RevId: 315792986
```
  9dadc325
- Internal change · ef99be0b
  A. Unique TensorFlower authored Jun 10, 2020
```
PiperOrigin-RevId: 315789209
```
  ef99be0b
- Fix get_config() of MaskedSoftmax. · 8a1dbbad
  Chen Chen authored Jun 10, 2020
```
PiperOrigin-RevId: 315767729
```
  8a1dbbad
- 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
09 Jun, 2020 1 commit
- Update nlp.modeling.layers.ReZeroTransformer to be consistent with nlp.modeling.layers.Transformer · d4bb3055
  A. Unique TensorFlower authored Jun 09, 2020
```
PiperOrigin-RevId: 315584374
```
  d4bb3055
08 Jun, 2020 1 commit
- Enable bert pretraining on fp16. · ea61bbf0
  Hongkun Yu authored Jun 07, 2020
```
PiperOrigin-RevId: 315214450
```
  ea61bbf0
04 Jun, 2020 1 commit
- Creates configs folder inside nlp/ · 869a4806
  Hongkun Yu authored Jun 03, 2020
```
PiperOrigin-RevId: 314634299
```
  869a4806
03 Jun, 2020 3 commits

Revert "Revert "Add relative positional embedding to KerasBERT (#8617)" (#8619)" · a6c0e677
Hongkun Yu authored Jun 03, 2020
```
This reverts commit 4bb13e61.
```
a6c0e677
Revert "Add relative positional embedding to KerasBERT (#8617)" (#8619) · 4bb13e61
Hongkun Yu authored Jun 03, 2020
```
This reverts commit c3c2386c.
```
4bb13e61

Add relative positional embedding to KerasBERT (#8617) · c3c2386c

xinliupitt authored Jun 03, 2020

* 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

c3c2386c