- 19 May, 2020 12 commits
-
-
Chen Chen authored
PiperOrigin-RevId: 312375806
-
Chen Chen authored
PiperOrigin-RevId: 312366167
-
Hongkun Yu authored
Remove is_v2_0 PiperOrigin-RevId: 312336907
-
Chen Chen authored
PiperOrigin-RevId: 312313738
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 312232155
-
André Susano Pinto authored
A default of 1 all the times is bad for TPU users which end up not using the device effectively. A larger default all the times is bad for GPU users. So compromise and make this dependent on the devices available. PiperOrigin-RevId: 312230371
-
Hongkun Yu authored
PiperOrigin-RevId: 312225657
-
Jaeyoun Kim authored
Update a badge
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 312209760
-
Jaeyoun Kim authored
Add a "help wanted" badge
-
Ruoxin Sang authored
PiperOrigin-RevId: 312194218
-
Saurabh Saxena authored
PiperOrigin-RevId: 312193729
-
- 18 May, 2020 6 commits
-
-
nuka137 authored
-
Sanjay Parajuli authored
To fix the following error: File "/usr/local/lib/python3.6/dist-packages/absl/flags/_flagvalues.py", line 698, in get_value raise _exceptions.Error('Missing value for flag ' + arg) # pylint: disable=undefined-loop-variable absl.flags._exceptions.Error: Missing value for flag -v -
Chen Chen authored
PiperOrigin-RevId: 312116965
-
BasiaFusinska authored
* Changed DELF installation instructions to be Python3 preferred * Changed DELF landmark detection instructions to be Python3 preferred * Changed DELF extraction and matching instructions to be Python3 preferred * Changed DELF detect-to-retrieve instructions to be Python3 preferred * Changed DELF training instructions to be Python3 preferred * Added Python3 badge to DELF README
-
Hongkun Yu authored
PiperOrigin-RevId: 312099777
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 312096778
-
- 17 May, 2020 1 commit
-
-
A. Unique TensorFlower authored
Update nlp.modeling.layers.ReZeroTransformer, to have the same interface with nlp.modeling.layers.Transformer PiperOrigin-RevId: 311937563
-
- 15 May, 2020 3 commits
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 311800955
-
Hongkun Yu authored
PiperOrigin-RevId: 311773503
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 311746915
-
- 14 May, 2020 12 commits
-
-
nuka137 authored
-
Hongkun Yu authored
PiperOrigin-RevId: 311626933
-
nuka137 authored
-
Hongkun Yu authored
PiperOrigin-RevId: 311602262
-
Chen Chen authored
PiperOrigin-RevId: 311597242
-
Chen Chen authored
PiperOrigin-RevId: 311577663
-
Jaeyoun Kim authored
Add a Stack Overflow badge
-
Allen Wang authored
PiperOrigin-RevId: 311561279
-
Jaeyoun Kim authored
Add an unofficial implementation link
-
Jeremiah Harmsen authored
Add network and BERT model to perform per-token classification (e.g., for named entity recognition tasks). PiperOrigin-RevId: 311480326
-
Hongkun Yu authored
Profiler has been integrated with TensorBoard callback and released in TF 2.2 PiperOrigin-RevId: 311475711
-
Hongkun Yu authored
PiperOrigin-RevId: 311435012
-
- 13 May, 2020 5 commits
-
-
Hongkun Yu authored
PiperOrigin-RevId: 311430970
-
Chen Chen authored
PiperOrigin-RevId: 311428193
-
Jaeyoun Kim authored
Add new updates
-
Sarath Shekkizhar authored
The cifar dataset links are changed to download python version of files. Downloading binary files will throw an error with the current code
-
Scott Zhu authored
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
-
- 12 May, 2020 1 commit
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 311196489
-