- 03 8月, 2022 1 次提交
-
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 464934071
-
- 04 5月, 2022 1 次提交
-
-
由 Scott Zhu 提交于
PiperOrigin-RevId: 446219773
-
- 19 1月, 2022 1 次提交
-
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 422612138
-
- 11 11月, 2021 1 次提交
-
-
由 Frederick Liu 提交于
PiperOrigin-RevId: 408970557
-
- 08 10月, 2021 1 次提交
-
-
由 Frederick Liu 提交于
PiperOrigin-RevId: 401593694
-
- 25 8月, 2021 1 次提交
-
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 392901555
-
- 18 5月, 2021 1 次提交
-
-
由 Frederick Liu 提交于
PiperOrigin-RevId: 374236491
-
- 24 4月, 2021 1 次提交
-
-
由 Chen Chen 提交于
PiperOrigin-RevId: 370159521
-
- 13 3月, 2021 1 次提交
-
-
由 Chen Chen 提交于
PiperOrigin-RevId: 362610475
-
- 10 3月, 2021 1 次提交
-
-
由 Frederick Liu 提交于
PiperOrigin-RevId: 361957289
-
- 19 2月, 2021 1 次提交
-
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 358301569
-
- 21 12月, 2020 1 次提交
-
-
由 Samuel Marks 提交于
-
- 10 12月, 2020 1 次提交
-
-
由 Hongkun Yu 提交于
Ask users to use keras_nlp. PiperOrigin-RevId: 346621226
-
- 19 11月, 2020 2 次提交
- 28 10月, 2020 1 次提交
-
-
由 Le Hou 提交于
PiperOrigin-RevId: 339345258
-
- 27 10月, 2020 1 次提交
-
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 339071563
-
- 24 10月, 2020 1 次提交
-
-
由 A. Unique TensorFlower 提交于
Shift all attribute assignments in functional subclass models below the super().__init__ call, and enable setattr tracking on all functional subclasses. PiperOrigin-RevId: 338759531
-
- 14 10月, 2020 1 次提交
-
-
由 A. Unique TensorFlower 提交于
Lambda layers are fundamentally non-portable since they serialize Python bytecode. PiperOrigin-RevId: 336917172
-
- 12 9月, 2020 1 次提交
-
-
由 Zhenyu Tan 提交于
PiperOrigin-RevId: 331173006
-
- 10 9月, 2020 1 次提交
-
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 330817736
-
- 02 9月, 2020 1 次提交
-
-
由 Zhenyu Tan 提交于
PiperOrigin-RevId: 329568227
-
- 26 8月, 2020 2 次提交
-
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 328389991
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 328389991
-
- 20 8月, 2020 2 次提交
-
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 327518640
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 327518640
-
- 18 8月, 2020 2 次提交
-
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 327160430
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 327160430
-
- 13 8月, 2020 2 次提交
-
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 326286926
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 326286926
-
- 31 7月, 2020 2 次提交
-
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 324137297
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 324137297
-
- 17 7月, 2020 2 次提交
-
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 321591514
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 321591514
-
- 15 5月, 2020 1 次提交
-
-
由 Chen Chen 提交于
PiperOrigin-RevId: 311597242
-
- 14 5月, 2020 1 次提交
-
-
由 Chen Chen 提交于
PiperOrigin-RevId: 311428193
-
- 13 5月, 2020 1 次提交
-
-
由 Scott Zhu 提交于
The intention of this change is to reduce the code complexity within Keras class, especially for Network, which currently contains logic for both subclass Model and functional Model. After this change, the subclass model and functional model become individual class and become self contained. 1. Model is now the base class for subclass model. It doesn't contains network structure management, and the topology will be created within __init__ and __call__, which is for user to implement. It also contains compile/fit/eval/predict, which is the basic functionality for model training. 2. Functional is created based on existing Network class. It extends the Model, which allows it leverage compile/fit/eval/predict. In addition, it also take input/output as init parameter and manage the network topology. 3. Sequential model is now a subclass of Functional, since it will use Functional's method to manage it topology (layer stacking). Model(input, output) will create a Functional under the hood, and behave the same way as before. PiperOrigin-RevId: 311232972
-
- 09 5月, 2020 1 次提交
-
-
由 A. Unique TensorFlower 提交于
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
-
- 08 5月, 2020 1 次提交
-
-
由 A. Unique TensorFlower 提交于
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
-
- 21 4月, 2020 1 次提交
-
-
由 Chen Chen 提交于
PiperOrigin-RevId: 307500045
-