- 03 Sep, 2021 3 commits
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 394727655
-
Abdullah Rashwan authored
-- 8a30da7c by Srihari Humbarwadi <sriharihumbarwadi97@gmail.com>: remove normalization/denomalization in postprocess_ops PiperOrigin-RevId: 394707702
-
Isha Arkatkar authored
PiperOrigin-RevId: 394577222
-
- 02 Sep, 2021 6 commits
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 394568069
-
Vighnesh Birodkar authored
PiperOrigin-RevId: 394512536
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 394505975
-
Leandro Schelb authored
* Fixed deprecated tf.flags * Fixed deprecated tf.contrib.metrics
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 394355848
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 394354557
-
- 01 Sep, 2021 5 commits
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 394333189
-
Yukun Zhu authored
-
Yu-hui Chen authored
CenterNet meta arch to avoid using scatter_nd and tf.cond. Also, use static_or_dynamic_map_fn in the convert_strided_predictions_to_normalized_keypoints function to avoid introducing cycles in the graph that causes the TPU converter errors. PiperOrigin-RevId: 394152521
-
Yu-hui Chen authored
runs much slower in the browser. PiperOrigin-RevId: 394148346
-
Fan Yang authored
PiperOrigin-RevId: 394116606
-
- 31 Aug, 2021 4 commits
-
-
Xianzhi Du authored
PiperOrigin-RevId: 394064826
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 393981019
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 393926742
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 393909662
-
- 30 Aug, 2021 3 commits
-
-
Fan Yang authored
PiperOrigin-RevId: 393871715
-
Fan Yang authored
PiperOrigin-RevId: 393865977
-
Srihari Humbarwadi authored
-
- 28 Aug, 2021 2 commits
-
-
Hongkun Yu authored
PiperOrigin-RevId: 393545790
-
Vivek Rathod authored
PiperOrigin-RevId: 393480597
-
- 27 Aug, 2021 3 commits
-
-
Yuexin Wu authored
PiperOrigin-RevId: 393428352
-
Hongkun Yu authored
PiperOrigin-RevId: 393366505
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 393343072
-
- 26 Aug, 2021 3 commits
-
-
Shumin Kong authored
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 393039446
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 393016139
-
- 25 Aug, 2021 5 commits
-
-
Hongkun Yu authored
PiperOrigin-RevId: 392968271
-
Yuexin Wu authored
The current Funnel-Transformer contains only the encoder part and uses 1D-MaxPool for query pooling. PiperOrigin-RevId: 392961143
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 392931060
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 392901555
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 392782508
-
- 24 Aug, 2021 1 commit
-
-
Mark Daoust authored
This will be the default behavior. PiperOrigin-RevId: 392643474
-
- 23 Aug, 2021 4 commits
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 392539450
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 392534821
-
Hongkun Yu authored
PiperOrigin-RevId: 392499545
-
Fan Yang authored
Unify DataDecoder from retinanet and maskrcnn and move it into common so it can be used by other tasks. Add DataDecoder as optional field for classification and segmentation DataConfig so overriding with DataDecoder can work for all tasks. PiperOrigin-RevId: 392493075
-
- 20 Aug, 2021 1 commit
-
-
Vivek Rathod authored
PiperOrigin-RevId: 392061572
-